@Article{info:doi/10.2196/18607, author="Chung, Kyungmi and Cho, Hee Young and Park, Jin Young", title="A Chatbot for Perinatal Women's and Partners' Obstetric and Mental Health Care: Development and Usability Evaluation Study", journal="JMIR Med Inform", year="2021", month="Mar", day="3", volume="9", number="3", pages="e18607", keywords="chatbot; mobile phone; instant messaging; mobile health; perinatal care; usability; user experience; usability testing", abstract="Background: To motivate people to adopt medical chatbots, the establishment of a specialized medical knowledge database that fits their personal interests is of great importance in developing a chatbot for perinatal care, particularly with the help of health professionals. Objective: The objectives of this study are to develop and evaluate a user-friendly question-and-answer (Q{\&}A) knowledge database--based chatbot (Dr. Joy) for perinatal women's and their partners' obstetric and mental health care by applying a text-mining technique and implementing contextual usability testing (UT), respectively, thus determining whether this medical chatbot built on mobile instant messenger (KakaoTalk) can provide its male and female users with good user experience. Methods: Two men aged 38 and 40 years and 13 women aged 27 to 43 years in pregnancy preparation or different pregnancy stages were enrolled. All participants completed the 7-day-long UT, during which they were given the daily tasks of asking Dr. Joy at least 3 questions at any time and place and then giving the chatbot either positive or negative feedback with emoji, using at least one feature of the chatbot, and finally, sending a facilitator all screenshots for the history of the day's use via KakaoTalk before midnight. One day after the UT completion, all participants were asked to fill out a questionnaire on the evaluation of usability, perceived benefits and risks, intention to seek and share health information on the chatbot, and strengths and weaknesses of its use, as well as demographic characteristics. Results: Despite the relatively higher score of ease of learning (EOL), the results of the Spearman correlation indicated that EOL was not significantly associated with usefulness ($\rho$=0.26; P=.36), ease of use ($\rho$=0.19; P=.51), satisfaction ($\rho$=0.21; P=.46), or total usability scores ($\rho$=0.32; P=.24). Unlike EOL, all 3 subfactors and the total usability had significant positive associations with each other (all $\rho$>0.80; P<.001). Furthermore, perceived risks exhibited no significant negative associations with perceived benefits ($\rho$=−0.29; P=.30) or intention to seek (SEE; $\rho$=−0.28; P=.32) or share (SHA; $\rho$=−0.24; P=.40) health information on the chatbot via KakaoTalk, whereas perceived benefits exhibited significant positive associations with both SEE and SHA. Perceived benefits were more strongly associated with SEE ($\rho$=0.94; P<.001) than with SHA ($\rho$=0.70; P=.004). Conclusions: This study provides the potential for the uptake of this newly developed Q{\&}A knowledge database--based KakaoTalk chatbot for obstetric and mental health care. As Dr. Joy had quality contents with both utilitarian and hedonic value, its male and female users could be encouraged to use medical chatbots in a convenient, easy-to-use, and enjoyable manner. To boost their continued usage intention for Dr. Joy, its Q{\&}A sets need to be periodically updated to satisfy user intent by monitoring both male and female user utterances. ", doi="10.2196/18607", url="https://medinform.jmir.org/2021/3/e18607", url="https://doi.org/10.2196/18607", url="http://www.ncbi.nlm.nih.gov/pubmed/33656442" } @Article{info:doi/10.2196/23612, author="Kowatsch, Tobias and Lohse, Kim-Morgaine and Erb, Val{\'e}rie and Schittenhelm, Leo and Galliker, Helen and Lehner, Rea and Huang, Elaine M", title="Hybrid Ubiquitous Coaching With a Novel Combination of Mobile and Holographic Conversational Agents Targeting Adherence to Home Exercises: Four Design and Evaluation Studies", journal="J Med Internet Res", year="2021", month="Feb", day="22", volume="23", number="2", pages="e23612", keywords="ubiquitous coaching; augmented reality; health care; treatment adherence; design science research; physiotherapy; chronic back pain; pain; chronic pain; exercise; adherence; treatment; conversational agent; smartphone; mobile phone", abstract="Background: Effective treatments for various conditions such as obesity, cardiac heart diseases, or low back pain require not only personal on-site coaching sessions by health care experts but also a significant amount of home exercises. However, nonadherence to home exercises is still a serious problem as it leads to increased costs due to prolonged treatments. Objective: To improve adherence to home exercises, we propose, implement, and assess the novel coaching concept of hybrid ubiquitous coaching (HUC). In HUC, health care experts are complemented by a conversational agent (CA) that delivers psychoeducation and personalized motivational messages via a smartphone, as well as real-time exercise support, monitoring, and feedback in a hands-free augmented reality environment. Methods: We applied HUC to the field of physiotherapy and conducted 4 design-and-evaluate loops with an interdisciplinary team to assess how HUC is perceived by patients and physiotherapists and whether HUC leads to treatment adherence. A first version of HUC was evaluated by 35 physiotherapy patients in a lab setting to identify patients' perceptions of HUC. In addition, 11 physiotherapists were interviewed about HUC and assessed whether the CA could help them build up a working alliance with their patients. A second version was then tested by 15 patients in a within-subject experiment to identify the ability of HUC to address adherence and to build a working alliance between the patient and the CA. Finally, a 4-week n-of-1 trial was conducted with 1 patient to show one experience with HUC in depth and thereby potentially reveal real-world benefits and challenges. Results: Patients perceived HUC to be useful, easy to use, and enjoyable, preferred it to state-of-the-art approaches, and expressed their intentions to use it. Moreover, patients built a working alliance with the CA. Physiotherapists saw a relative advantage of HUC compared to current approaches but initially did not see the potential in terms of a working alliance, which changed after seeing the results of HUC in the field. Qualitative feedback from patients indicated that they enjoyed doing the exercise with an augmented reality--based CA and understood better how to do the exercise correctly with HUC. Moreover, physiotherapists highlighted that HUC would be helpful to use in the therapy process. The longitudinal field study resulted in an adherence rate of 92{\%} (11/12 sessions; 330/360 repetitions; 33/36 sets) and a substantial increase in exercise accuracy during the 4 weeks. Conclusions: The overall positive assessments from both patients and health care experts suggest that HUC is a promising tool to be applied in various disorders with a relevant set of home exercises. Future research, however, must implement a variety of exercises and test HUC with patients suffering from different disorders. ", doi="10.2196/23612", url="https://www.jmir.org/2021/2/e23612", url="https://doi.org/10.2196/23612", url="http://www.ncbi.nlm.nih.gov/pubmed/33461957" } @Article{info:doi/10.2196/25060, author="Kowatsch, Tobias and Schachner, Theresa and Harperink, Samira and Barata, Filipe and Dittler, Ullrich and Xiao, Grace and Stanger, Catherine and v Wangenheim, Florian and Fleisch, Elgar and Oswald, Helmut and M{\"o}ller, Alexander", title="Conversational Agents as Mediating Social Actors in Chronic Disease Management Involving Health Care Professionals, Patients, and Family Members: Multisite Single-Arm Feasibility Study", journal="J Med Internet Res", year="2021", month="Feb", day="17", volume="23", number="2", pages="e25060", keywords="digital health intervention; intervention design; mHealth; eHealth; chatbot; conversational agent; chronic diseases; asthma; feasibility study", abstract="Background: Successful management of chronic diseases requires a trustful collaboration between health care professionals, patients, and family members. Scalable conversational agents, designed to assist health care professionals, may play a significant role in supporting this collaboration in a scalable way by reaching out to the everyday lives of patients and their family members. However, to date, it remains unclear whether conversational agents, in such a role, would be accepted and whether they can support this multistakeholder collaboration. Objective: With asthma in children representing a relevant target of chronic disease management, this study had the following objectives: (1) to describe the design of MAX, a conversational agent--delivered asthma intervention that supports health care professionals targeting child-parent teams in their everyday lives; and (2) to assess the (a) reach of MAX, (b) conversational agent--patient working alliance, (c) acceptance of MAX, (d) intervention completion rate, (e) cognitive and behavioral outcomes, and (f) human effort and responsiveness of health care professionals in primary and secondary care settings. Methods: MAX was designed to increase cognitive skills (ie, knowledge about asthma) and behavioral skills (ie, inhalation technique) in 10-15-year-olds with asthma, and enables support by a health professional and a family member. To this end, three design goals guided the development: (1) to build a conversational agent--patient working alliance; (2) to offer hybrid (human- and conversational agent--supported) ubiquitous coaching; and (3) to provide an intervention with high experiential value. An interdisciplinary team of computer scientists, asthma experts, and young patients with their parents developed the intervention collaboratively. The conversational agent communicates with health care professionals via email, with patients via a mobile chat app, and with a family member via SMS text messaging. A single-arm feasibility study in primary and secondary care settings was performed to assess MAX. Results: Results indicated an overall positive evaluation of MAX with respect to its reach (49.5{\%}, 49/99 of recruited and eligible patient-family member teams participated), a strong patient-conversational agent working alliance, and high acceptance by all relevant stakeholders. Moreover, MAX led to improved cognitive and behavioral skills and an intervention completion rate of 75.5{\%}. Family members supported the patients in 269 out of 275 (97.8{\%}) coaching sessions. Most of the conversational turns (99.5{\%}) were conducted between patients and the conversational agent as opposed to between patients and health care professionals, thus indicating the scalability of MAX. In addition, it took health care professionals less than 4 minutes to assess the inhalation technique and 3 days to deliver related feedback to the patients. Several suggestions for improvement were made. Conclusions: This study provides the first evidence that conversational agents, designed as mediating social actors involving health care professionals, patients, and family members, are not only accepted in such a ``team player'' role but also show potential to improve health-relevant outcomes in chronic disease management. ", doi="10.2196/25060", url="http://www.jmir.org/2021/2/e25060/", url="https://doi.org/10.2196/25060", url="http://www.ncbi.nlm.nih.gov/pubmed/33484114" } @Article{info:doi/10.2196/25184, author="Sato, Ann and Haneda, Eri and Suganuma, Nobuyasu and Narimatsu, Hiroto", title="Preliminary Screening for Hereditary Breast and Ovarian Cancer Using a Chatbot Augmented Intelligence Genetic Counselor: Development and Feasibility Study", journal="JMIR Form Res", year="2021", month="Feb", day="5", volume="5", number="2", pages="e25184", keywords="artificial intelligence; augmented intelligence; hereditary cancer; familial cancer; IBM Watson; preliminary screening; cancer; genetics; chatbot; screening; feasibility", abstract="Background: Breast cancer is the most common form of cancer in Japan; genetic background and hereditary breast and ovarian cancer (HBOC) are implicated. The key to HBOC diagnosis involves screening to identify high-risk individuals. However, genetic medicine is still developing; thus, many patients who may potentially benefit from genetic medicine have not yet been identified. Objective: This study's objective is to develop a chatbot system that uses augmented intelligence for HBOC screening to determine whether patients meet the National Comprehensive Cancer Network (NCCN) BRCA1/2 testing criteria. Methods: The system was evaluated by a doctor specializing in genetic medicine and certified genetic counselors. We prepared 3 scenarios and created a conversation with the chatbot to reflect each one. Then we evaluated chatbot feasibility, the required time, the medical accuracy of conversations and family history, and the final result. Results: The times required for the conversation were 7 minutes for scenario 1, 15 minutes for scenario 2, and 16 minutes for scenario 3. Scenarios 1 and 2 met the BRCA1/2 testing criteria, but scenario 3 did not, and this result was consistent with the findings of 3 experts who retrospectively reviewed conversations with the chatbot according to the 3 scenarios. A family history comparison ascertained by the chatbot with the actual scenarios revealed that each result was consistent with each scenario. From a genetic medicine perspective, no errors were noted by the 3 experts. Conclusions: This study demonstrated that chatbot systems could be applied to preliminary genetic medicine screening for HBOC. ", doi="10.2196/25184", url="https://formative.jmir.org/2021/2/e25184", url="https://doi.org/10.2196/25184", url="http://www.ncbi.nlm.nih.gov/pubmed/33544084" } @Article{info:doi/10.2196/22919, author="Schachner, Theresa and Gross, Christoph and Hasl, Andrea and v Wangenheim, Florian and Kowatsch, Tobias", title="Deliberative and Paternalistic Interaction Styles for Conversational Agents in Digital Health: Procedure and Validation Through a Web-Based Experiment", journal="J Med Internet Res", year="2021", month="Jan", day="29", volume="23", number="1", pages="e22919", keywords="conversational agents; chatbots; human-computer interaction; physician-patient relationship; interaction styles, deliberative interaction; paternalistic interaction; digital health; chronic conditions; COPD", abstract="Background: Recent years have witnessed a constant increase in the number of people with chronic conditions requiring ongoing medical support in their everyday lives. However, global health systems are not adequately equipped for this extraordinarily time-consuming and cost-intensive development. Here, conversational agents (CAs) can offer easily scalable and ubiquitous support. Moreover, different aspects of CAs have not yet been sufficiently investigated to fully exploit their potential. One such trait is the interaction style between patients and CAs. In human-to-human settings, the interaction style is an imperative part of the interaction between patients and physicians. Patient-physician interaction is recognized as a critical success factor for patient satisfaction, treatment adherence, and subsequent treatment outcomes. However, so far, it remains effectively unknown how different interaction styles can be implemented into CA interactions and whether these styles are recognizable by users. Objective: The objective of this study was to develop an approach to reproducibly induce 2 specific interaction styles into CA-patient dialogs and subsequently test and validate them in a chronic health care context. Methods: On the basis of the Roter Interaction Analysis System and iterative evaluations by scientific experts and medical health care professionals, we identified 10 communication components that characterize the 2 developed interaction styles: deliberative and paternalistic interaction styles. These communication components were used to develop 2 CA variations, each representing one of the 2 interaction styles. We assessed them in a web-based between-subject experiment. The participants were asked to put themselves in the position of a patient with chronic obstructive pulmonary disease. These participants were randomly assigned to interact with one of the 2 CAs and subsequently asked to identify the respective interaction style. Chi-square test was used to assess the correct identification of the CA-patient interaction style. Results: A total of 88 individuals (42/88, 48{\%} female; mean age 31.5 years, SD 10.1 years) fulfilled the inclusion criteria and participated in the web-based experiment. The participants in both the paternalistic and deliberative conditions correctly identified the underlying interaction styles of the CAs in more than 80{\%} of the assessments (X21,88=38.2; P<.001; phi coefficient r$\phi$=0.68). The validation of the procedure was hence successful. Conclusions: We developed an approach that is tailored for a medical context to induce a paternalistic and deliberative interaction style into a written interaction between a patient and a CA. We successfully tested and validated the procedure in a web-based experiment involving 88 participants. Future research should implement and test this approach among actual patients with chronic diseases and compare the results in different medical conditions. This approach can further be used as a starting point to develop dynamic CAs that adapt their interaction styles to their users. ", doi="10.2196/22919", url="http://www.jmir.org/2021/1/e22919/", url="https://doi.org/10.2196/22919", url="http://www.ncbi.nlm.nih.gov/pubmed/33512328" } @Article{info:doi/10.2196/17828, author="Abd-Alrazaq, Alaa A and Alajlani, Mohannad and Ali, Nashva and Denecke, Kerstin and Bewick, Bridgette M and Househ, Mowafa", title="Perceptions and Opinions of Patients About Mental Health Chatbots: Scoping Review", journal="J Med Internet Res", year="2021", month="Jan", day="13", volume="23", number="1", pages="e17828", keywords="chatbots; conversational agents; mental health; mental disorders; perceptions; opinions; mobile phone", abstract="Background: Chatbots have been used in the last decade to improve access to mental health care services. Perceptions and opinions of patients influence the adoption of chatbots for health care. Many studies have been conducted to assess the perceptions and opinions of patients about mental health chatbots. To the best of our knowledge, there has been no review of the evidence surrounding perceptions and opinions of patients about mental health chatbots. Objective: This study aims to conduct a scoping review of the perceptions and opinions of patients about chatbots for mental health. Methods: The scoping review was carried out in line with the PRISMA (Preferred Reporting Items for Systematic reviews and Meta-Analyses) extension for scoping reviews guidelines. Studies were identified by searching 8 electronic databases (eg, MEDLINE and Embase) in addition to conducting backward and forward reference list checking of the included studies and relevant reviews. In total, 2 reviewers independently selected studies and extracted data from the included studies. Data were synthesized using thematic analysis. Results: Of 1072 citations retrieved, 37 unique studies were included in the review. The thematic analysis generated 10 themes from the findings of the studies: usefulness, ease of use, responsiveness, understandability, acceptability, attractiveness, trustworthiness, enjoyability, content, and comparisons. Conclusions: The results demonstrated overall positive perceptions and opinions of patients about chatbots for mental health. Important issues to be addressed in the future are the linguistic capabilities of the chatbots: they have to be able to deal adequately with unexpected user input, provide high-quality responses, and have to show high variability in responses. To be useful for clinical practice, we have to find ways to harmonize chatbot content with individual treatment recommendations, that is, a personalization of chatbot conversations is required. ", doi="10.2196/17828", url="http://www.jmir.org/2021/1/e17828/", url="https://doi.org/10.2196/17828", url="http://www.ncbi.nlm.nih.gov/pubmed/33439133" } @Article{info:doi/10.2196/21453, author="Leung, Yvonne W and Wouterloot, Elise and Adikari, Achini and Hirst, Graeme and de Silva, Daswin and Wong, Jiahui and Bender, Jacqueline L and Gancarz, Mathew and Gratzer, David and Alahakoon, Damminda and Esplen, Mary Jane", title="Natural Language Processing--Based Virtual Cofacilitator for Online Cancer Support Groups: Protocol for an Algorithm Development and Validation Study", journal="JMIR Res Protoc", year="2021", month="Jan", day="7", volume="10", number="1", pages="e21453", keywords="artificial intelligence; cancer; online support groups; emotional distress; natural language processing; participant engagement", abstract="Background: Cancer and its treatment can significantly impact the short- and long-term psychological well-being of patients and families. Emotional distress and depressive symptomatology are often associated with poor treatment adherence, reduced quality of life, and higher mortality. Cancer support groups, especially those led by health care professionals, provide a safe place for participants to discuss fear, normalize stress reactions, share solidarity, and learn about effective strategies to build resilience and enhance coping. However, in-person support groups may not always be accessible to individuals; geographic distance is one of the barriers for access, and compromised physical condition (eg, fatigue, pain) is another. Emerging evidence supports the effectiveness of online support groups in reducing access barriers. Text-based and professional-led online support groups have been offered by Cancer Chat Canada. Participants join the group discussion using text in real time. However, therapist leaders report some challenges leading text-based online support groups in the absence of visual cues, particularly in tracking participant distress. With multiple participants typing at the same time, the nuances of the text messages or red flags for distress can sometimes be missed. Recent advances in artificial intelligence such as deep learning--based natural language processing offer potential solutions. This technology can be used to analyze online support group text data to track participants' expressed emotional distress, including fear, sadness, and hopelessness. Artificial intelligence allows session activities to be monitored in real time and alerts the therapist to participant disengagement. Objective: We aim to develop and evaluate an artificial intelligence--based cofacilitator prototype to track and monitor online support group participants' distress through real-time analysis of text-based messages posted during synchronous sessions. Methods: An artificial intelligence--based cofacilitator will be developed to identify participants who are at-risk for increased emotional distress and track participant engagement and in-session group cohesion levels, providing real-time alerts for therapist to follow-up; generate postsession participant profiles that contain discussion content keywords and emotion profiles for each session; and automatically suggest tailored resources to participants according to their needs. The study is designed to be conducted in 4 phases consisting of (1) development based on a subset of data and an existing natural language processing framework, (2) performance evaluation using human scoring, (3) beta testing, and (4) user experience evaluation. Results: This study received ethics approval in August 2019. Phase 1, development of an artificial intelligence--based cofacilitator, was completed in January 2020. As of December 2020, phase 2 is underway. The study is expected to be completed by September 2021. Conclusions: An artificial intelligence--based cofacilitator offers a promising new mode of delivery of person-centered online support groups tailored to individual needs. International Registered Report Identifier (IRRID): DERR1-10.2196/21453 ", doi="10.2196/21453", url="https://www.researchprotocols.org/2021/1/e21453", url="https://doi.org/10.2196/21453", url="http://www.ncbi.nlm.nih.gov/pubmed/33410754" } @Article{info:doi/10.2196/19928, author="Fan, Xiangmin and Chao, Daren and Zhang, Zhan and Wang, Dakuo and Li, Xiaohua and Tian, Feng", title="Utilization of Self-Diagnosis Health Chatbots in Real-World Settings: Case Study", journal="J Med Internet Res", year="2021", month="Jan", day="6", volume="23", number="1", pages="e19928", keywords="self-diagnosis; chatbot; conversational agent; human--artificial intelligence interaction; artificial intelligence; diagnosis; case study; eHealth; real world; user experience", abstract="Background: Artificial intelligence (AI)-driven chatbots are increasingly being used in health care, but most chatbots are designed for a specific population and evaluated in controlled settings. There is little research documenting how health consumers (eg, patients and caregivers) use chatbots for self-diagnosis purposes in real-world scenarios. Objective: The aim of this research was to understand how health chatbots are used in a real-world context, what issues and barriers exist in their usage, and how the user experience of this novel technology can be improved. Methods: We employed a data-driven approach to analyze the system log of a widely deployed self-diagnosis chatbot in China. Our data set consisted of 47,684 consultation sessions initiated by 16,519 users over 6 months. The log data included a variety of information, including users' nonidentifiable demographic information, consultation details, diagnostic reports, and user feedback. We conducted both statistical analysis and content analysis on this heterogeneous data set. Results: The chatbot users spanned all age groups, including middle-aged and older adults. Users consulted the chatbot on a wide range of medical conditions, including those that often entail considerable privacy and social stigma issues. Furthermore, we distilled 2 prominent issues in the use of the chatbot: (1) a considerable number of users dropped out in the middle of their consultation sessions, and (2) some users pretended to have health concerns and used the chatbot for nontherapeutic purposes. Finally, we identified a set of user concerns regarding the use of the chatbot, including insufficient actionable information and perceived inaccurate diagnostic suggestions. Conclusions: Although health chatbots are considered to be convenient tools for enhancing patient-centered care, there are issues and barriers impeding the optimal use of this novel technology. Designers and developers should employ user-centered approaches to address the issues and user concerns to achieve the best uptake and utilization. We conclude the paper by discussing several design implications, including making the chatbots more informative, easy-to-use, and trustworthy, as well as improving the onboarding experience to enhance user engagement. ", doi="10.2196/19928", url="https://www.jmir.org/2021/1/e19928", url="https://doi.org/10.2196/19928", url="http://www.ncbi.nlm.nih.gov/pubmed/33404508" } @Article{info:doi/10.2196/22186, author="Kramer, Lean L and Mulder, Bob C and van Velsen, Lex and de Vet, Emely", title="Use and Effect of Web-Based Embodied Conversational Agents for Improving Eating Behavior and Decreasing Loneliness Among Community-Dwelling Older Adults: Protocol for a Randomized Controlled Trial", journal="JMIR Res Protoc", year="2021", month="Jan", day="6", volume="10", number="1", pages="e22186", keywords="embodied conversational agent; health behavior change; loneliness; eating behavior; older adults", abstract="Background: An unhealthy eating pattern and loneliness negatively influence quality of life in older age. Embodied conversational agents (ECAs) are a promising way to address these health behaviors in an engaging manner. Objective: We aim to (1) identify whether ECAs can persuade community-dwelling older adults to change their dietary behavior and whether ECA use can decrease loneliness, (2) test these pathways to effects, and (3) understand the use of an ECA. Methods: The web-based eHealth app PACO is a fully automated 8-week intervention in which 2 ECAs engage older adults in dialogue to motivate them to change their dietary behavior and decrease their loneliness. PACO was developed via a human-centered and stakeholder-inclusive design approach and incorporates Self-determination Theory and various behavior change techniques. For this study, an unblinded randomized controlled trial will be performed. There will be 2 cohorts, with 30 participants per cohort. Participants in the first cohort will immediately receive the PACO app for 8 weeks, while participants in the second cohort receive the PACO app after a waiting-list condition of 4 weeks. Participants will be recruited via social media, an online panel, flyers, and advertorials. To be eligible, participants must be at least 65 years of age, must not be in paid employment, and must live alone independently at home. Primary outcomes will be self-assessed via online questionnaires at intake, control, after 4 weeks, and after 8 weeks, and will include eating behavior and loneliness. In addition, the primary outcome---use---will be measured via data logs. Secondary outcomes will be measured at the same junctures, via either validated, self-assessed, online questionnaires or an optional interview. Results: As of July 2020, we have begun recruiting participants. Conclusions: By unraveling the mechanisms behind the use of a web-based intervention with ECAs, we hope to gain a fine-grained understanding of both the effectiveness and the use of ECAs in the health context. Trial Registration: ClinicalTrials.gov NCT04510883; https://clinicaltrials.gov/ct2/show/NCT04510883 International Registered Report Identifier (IRRID): PRR1-10.2196/22186 ", doi="10.2196/22186", url="https://www.researchprotocols.org/2021/1/e22186", url="https://doi.org/10.2196/22186", url="http://www.ncbi.nlm.nih.gov/pubmed/33404513" } @Article{info:doi/10.2196/19127, author="Safi, Zeineb and Abd-Alrazaq, Alaa and Khalifa, Mohamed and Househ, Mowafa", title="Technical Aspects of Developing Chatbots for Medical Applications: Scoping Review", journal="J Med Internet Res", year="2020", month="Dec", day="18", volume="22", number="12", pages="e19127", keywords="chatbots; conversational agents; medical applications; scoping review; technical aspects", abstract="Background: Chatbots are applications that can conduct natural language conversations with users. In the medical field, chatbots have been developed and used to serve different purposes. They provide patients with timely information that can be critical in some scenarios, such as access to mental health resources. Since the development of the first chatbot, ELIZA, in the late 1960s, much effort has followed to produce chatbots for various health purposes developed in different ways. Objective: This study aimed to explore the technical aspects and development methodologies associated with chatbots used in the medical field to explain the best methods of development and support chatbot development researchers on their future work. Methods: We searched for relevant articles in 8 literature databases (IEEE, ACM, Springer, ScienceDirect, Embase, MEDLINE, PsycINFO, and Google Scholar). We also performed forward and backward reference checking of the selected articles. Study selection was performed by one reviewer, and 50{\%} of the selected studies were randomly checked by a second reviewer. A narrative approach was used for result synthesis. Chatbots were classified based on the different technical aspects of their development. The main chatbot components were identified in addition to the different techniques for implementing each module. Results: The original search returned 2481 publications, of which we identified 45 studies that matched our inclusion and exclusion criteria. The most common language of communication between users and chatbots was English (n=23). We identified 4 main modules: text understanding module, dialog management module, database layer, and text generation module. The most common technique for developing text understanding and dialogue management is the pattern matching method (n=18 and n=25, respectively). The most common text generation is fixed output (n=36). Very few studies relied on generating original output. Most studies kept a medical knowledge base to be used by the chatbot for different purposes throughout the conversations. A few studies kept conversation scripts and collected user data and previous conversations. Conclusions: Many chatbots have been developed for medical use, at an increasing rate. There is a recent, apparent shift in adopting machine learning--based approaches for developing chatbot systems. Further research can be conducted to link clinical outcomes to different chatbot development techniques and technical characteristics. ", doi="10.2196/19127", url="http://www.jmir.org/2020/12/e19127/", url="https://doi.org/10.2196/19127", url="http://www.ncbi.nlm.nih.gov/pubmed/33337337" } @Article{info:doi/10.2196/20456, author="Kowalska, Ma{\l}gorzata and G{\l}ady{\'{s}}, Aleksandra and Kala{\'{n}}ska-{\L}ukasik, Barbara and Gruz-Kwapisz, Monika and Wojakowski, Wojciech and Jadczyk, Tomasz", title="Readiness for Voice Technology in Patients With Cardiovascular Diseases: Cross-Sectional Study", journal="J Med Internet Res", year="2020", month="Dec", day="17", volume="22", number="12", pages="e20456", keywords="voice technology; smart speaker; acceptance; telehealth; cardiovascular diseases; chatbot", abstract="Background: The clinical application of voice technology provides novel opportunities in the field of telehealth. However, patients' readiness for this solution has not been investigated among patients with cardiovascular diseases (CVD). Objective: This paper aims to evaluate patients' anticipated experiences regarding telemedicine, including voice conversational agents combined with provider-driven support delivered by phone. Methods: A cross-sectional study enrolled patients with chronic CVD who were surveyed using a validated investigator-designed questionnaire combining 19 questions (eg, demographic data, medical history, preferences for using telehealth services). Prior to the survey, respondents were educated on the telemedicine services presented in the questionnaire while being assisted by a medical doctor. Responses were then collected and analyzed, and multivariate logistic regression was used to identify predictors of willingness to use voice technology. Results: In total, 249 patients (mean age 65.3, SD 13.8 years; 158 [63.5{\%}] men) completed the questionnaire, which showed good repeatability in the validation procedure. Of the 249 total participants, 209 (83.9{\%}) reported high readiness to receive services allowing for remote contact with a cardiologist (176/249, 70.7{\%}) and telemonitoring of vital signs (168/249, 67.5{\%}). The voice conversational agents combined with provider-driven support delivered by phone were shown to be highly anticipated by patients with CVD. The readiness to use telehealth was statistically higher in people with previous difficulties accessing health care (OR 2.920, 95{\%} CI 1.377-6.192) and was most frequent in city residents and individuals reporting a higher education level. The age and sex of the respondents did not impact the intention to use voice technology (P=.20 and P=.50, respectively). Conclusions: Patients with cardiovascular diseases, including both younger and older individuals, declared high readiness for voice technology. ", doi="10.2196/20456", url="http://www.jmir.org/2020/12/e20456/", url="https://doi.org/10.2196/20456", url="http://www.ncbi.nlm.nih.gov/pubmed/33331824" } @Article{info:doi/10.2196/21982, author="te Pas, Mariska E and Rutten, Werner G M M and Bouwman, R Arthur and Buise, Marc P", title="User Experience of a Chatbot Questionnaire Versus a Regular Computer Questionnaire: Prospective Comparative Study", journal="JMIR Med Inform", year="2020", month="Dec", day="7", volume="8", number="12", pages="e21982", keywords="chatbot; user experience; questionnaires; response rates; value-based health care", abstract="Background: Respondent engagement of questionnaires in health care is fundamental to ensure adequate response rates for the evaluation of services and quality of care. Conventional survey designs are often perceived as dull and unengaging, resulting in negative respondent behavior. It is necessary to make completing a questionnaire attractive and motivating. Objective: The aim of this study is to compare the user experience of a chatbot questionnaire, which mimics intelligent conversation, with a regular computer questionnaire. Methods: The research took place at the preoperative outpatient clinic. Patients completed both the standard computer questionnaire and the new chatbot questionnaire. Afterward, patients gave their feedback on both questionnaires by the User Experience Questionnaire, which consists of 26 terms to score. Results: The mean age of the 40 included patients (25 [63{\%}] women) was 49 (SD 18-79) years; 46.73{\%} (486/1040) of all terms were scored positive for the chatbot. Patients preferred the computer for 7.98{\%} (83/1040) of the terms and for 47.88{\%} (498/1040) of the terms there were no differences. Completion (mean time) of the computer questionnaire took 9.00 minutes by men (SD 2.72) and 7.72 minutes by women (SD 2.60; P=.148). For the chatbot, completion by men took 8.33 minutes (SD 2.99) and by women 7.36 minutes (SD 2.61; P=.287). Conclusions: Patients preferred the chatbot questionnaire over the computer questionnaire. Time to completion of both questionnaires did not differ, though the chatbot questionnaire on a tablet felt more rapid compared to the computer questionnaire. This is an important finding because it could lead to higher response rates and to qualitatively better responses in future questionnaires. ", doi="10.2196/21982", url="http://medinform.jmir.org/2020/12/e21982/", url="https://doi.org/10.2196/21982", url="http://www.ncbi.nlm.nih.gov/pubmed/33284125" } @Article{info:doi/10.2196/20455, author="Ferr{\'e}, Fabrice and Boeschlin, Nicolas and Bastiani, Bruno and Castel, Adeline and Ferrier, Anne and Bosch, Laetitia and Muscari, Fabrice and Kurrek, Matt and Fourcade, Olivier and Piau, Antoine and Minville, Vincent", title="Improving Provision of Preanesthetic Information Through Use of the Digital Conversational Agent ``MyAnesth'': Prospective Observational Trial", journal="J Med Internet Res", year="2020", month="Dec", day="4", volume="22", number="12", pages="e20455", keywords="chatbot; digital conversational agent; preanesthetic consultation; Abric method; eHealth; digital health; anesthesia", abstract="Background: Due to time limitations, the preanesthetic consultation (PAC) is not the best time for patients to integrate information specific to their perioperative care pathway. Objective: The main objectives of this study were to evaluate the effectiveness of a digital companion on patients' knowledge of anesthesia and their satisfaction after real-life implementation. Methods: We conducted a prospective, monocentric, comparative study using a before-and-after design. In phase 1, a 9-item self-reported anesthesia knowledge test (Delphi method) was administered to patients before and after their PAC (control group: PAC group). In phase 2, the study was repeated immediately after the implementation of a digital conversational agent, MyAnesth (@+PAC group). Patients' satisfaction and their representations for anesthesia were also assessed using a Likert scale and the Abric method of hierarchized evocation. Results: A total of 600 tests were distributed; 205 patients and 98 patients were included in the PAC group and @+PAC group, respectively. Demographic characteristics and mean scores on the 9-point preinformation test (PAC group: 4.2 points, 95{\%} CI 3.9-4.4; @+PAC: 4.3 points, 95{\%} CI 4-4.7; P=.37) were similar in the two groups. The mean score after receiving information was better in the @+PAC group than in the PAC group (6.1 points, 95{\%} CI 5.8-6.4 points versus 5.2 points, 95{\%} CI 5.0-5.4 points, respectively; P<.001), with an added value of 0.7 points (95{\%} CI 0.3-1.1; P<.001). Among the respondents in the @+PAC group, 82{\%} found the information to be clear and appropriate, and 74{\%} found it easily accessible. Before receiving information, the central core of patients' representations for anesthesia was focused on the fear of being put to sleep and thereafter on caregiver skills and comfort. Conclusions: The implementation of our digital conversational agent in addition to the PAC improved patients' knowledge about their perioperative care pathway. This innovative audiovisual support seemed clear, adapted, easily accessible, and reassuring. Future studies should focus on adapting both the content and delivery of a digital conversational agent for the PAC in order to maximize its benefit to patients. ", doi="10.2196/20455", url="https://www.jmir.org/2020/12/e20455", url="https://doi.org/10.2196/20455", url="http://www.ncbi.nlm.nih.gov/pubmed/33275108" } @Article{info:doi/10.2196/20549, author="Morse, Keith E and Ostberg, Nicolai P and Jones, Veena G and Chan, Albert S", title="Use Characteristics and Triage Acuity of a Digital Symptom Checker in a Large Integrated Health System: Population-Based Descriptive Study", journal="J Med Internet Res", year="2020", month="Nov", day="30", volume="22", number="11", pages="e20549", keywords="symptom checker; chatbot; computer-assisted diagnosis; diagnostic self-evaluation; artificial intelligence; self-care; COVID-19", abstract="Background: Pressure on the US health care system has been increasing due to a combination of aging populations, rising health care expenditures, and most recently, the COVID-19 pandemic. Responses to this pressure are hindered in part by reliance on a limited supply of highly trained health care professionals, creating a need for scalable technological solutions. Digital symptom checkers are artificial intelligence--supported software tools that use a conversational ``chatbot'' format to support rapid diagnosis and consistent triage. The COVID-19 pandemic has brought new attention to these tools due to the need to avoid face-to-face contact and preserve urgent care capacity. However, evidence-based deployment of these chatbots requires an understanding of user demographics and associated triage recommendations generated by a large general population. Objective: In this study, we evaluate the user demographics and levels of triage acuity provided by a symptom checker chatbot deployed in partnership with a large integrated health system in the United States. Methods: This population-based descriptive study included all web-based symptom assessments completed on the website and patient portal of the Sutter Health system (24 hospitals in Northern California) from April 24, 2019, to February 1, 2020. User demographics were compared to relevant US Census population data. Results: A total of 26,646 symptom assessments were completed during the study period. Most assessments (17,816/26,646, 66.9{\%}) were completed by female users. The mean user age was 34.3 years (SD 14.4 years), compared to a median age of 37.3 years of the general population. The most common initial symptom was abdominal pain (2060/26,646, 7.7{\%}). A substantial number of assessments (12,357/26,646, 46.4{\%}) were completed outside of typical physician office hours. Most users were advised to seek medical care on the same day (7299/26,646, 27.4{\%}) or within 2-3 days (6301/26,646, 23.6{\%}). Over a quarter of the assessments indicated a high degree of urgency (7723/26,646, 29.0{\%}). Conclusions: Users of the symptom checker chatbot were broadly representative of our patient population, although they skewed toward younger and female users. The triage recommendations were comparable to those of nurse-staffed telephone triage lines. Although the emergence of COVID-19 has increased the interest in remote medical assessment tools, it is important to take an evidence-based approach to their deployment. ", doi="10.2196/20549", url="https://www.jmir.org/2020/11/e20549", url="https://doi.org/10.2196/20549", url="http://www.ncbi.nlm.nih.gov/pubmed/33170799" } @Article{info:doi/10.2196/17065, author="Dosovitsky, Gilly and Pineda, Blanca S and Jacobson, Nicholas C and Chang, Cyrus and Escoredo, Milagros and Bunge, Eduardo L", title="Artificial Intelligence Chatbot for Depression: Descriptive Study of Usage", journal="JMIR Form Res", year="2020", month="Nov", day="13", volume="4", number="11", pages="e17065", keywords="chatbot; artificial intelligence; depression; mobile health; telehealth", abstract="Background: Chatbots could be a scalable solution that provides an interactive means of engaging users in behavioral health interventions driven by artificial intelligence. Although some chatbots have shown promising early efficacy results, there is limited information about how people use these chatbots. Understanding the usage patterns of chatbots for depression represents a crucial step toward improving chatbot design and providing information about the strengths and limitations of the chatbots. Objective: This study aims to understand how users engage and are redirected through a chatbot for depression (Tess) to provide design recommendations. Methods: Interactions of 354 users with the Tess depression modules were analyzed to understand chatbot usage across and within modules. Descriptive statistics were used to analyze participant flow through each depression module, including characters per message, completion rate, and time spent per module. Slide plots were also used to analyze the flow across and within modules. Results: Users sent a total of 6220 messages, with a total of 86,298 characters, and, on average, they engaged with Tess depression modules for 46 days. There was large heterogeneity in user engagement across different modules, which appeared to be affected by the length, complexity, content, and style of questions within the modules and the routing between modules. Conclusions: Overall, participants engaged with Tess; however, there was a heterogeneous usage pattern because of varying module designs. Major implications for future chatbot design and evaluation are discussed in the paper. ", doi="10.2196/17065", url="http://formative.jmir.org/2020/11/e17065/", url="https://doi.org/10.2196/17065", url="http://www.ncbi.nlm.nih.gov/pubmed/33185563" } @Article{info:doi/10.2196/15185, author="Koman, Jason and Fauvelle, Khristina and Schuck, St{\'e}phane and Texier, Nathalie and Mebarki, Adel", title="Physicians' Perceptions of the Use of a Chatbot for Information Seeking: Qualitative Study", journal="J Med Internet Res", year="2020", month="Nov", day="10", volume="22", number="11", pages="e15185", keywords="health; digital health; innovation; conversational agent; decision support system; qualitative research; chatbot; bot; medical drugs; prescription; risk minimization measures", abstract="Background: Seeking medical information can be an issue for physicians. In the specific context of medical practice, chatbots are hypothesized to present additional value for providing information quickly, particularly as far as drug risk minimization measures are concerned. Objective: This qualitative study aimed to elicit physicians' perceptions of a pilot version of a chatbot used in the context of drug information and risk minimization measures. Methods: General practitioners and specialists were recruited across France to participate in individual semistructured interviews. Interviews were recorded, transcribed, and analyzed using a horizontal thematic analysis approach. Results: Eight general practitioners and 2 specialists participated. The tone and ergonomics of the pilot version were appreciated by physicians. However, all participants emphasized the importance of getting exhaustive, trustworthy answers when interacting with a chatbot. Conclusions: The chatbot was perceived as a useful and innovative tool that could easily be integrated into routine medical practice and could help health professionals when seeking information on drug and risk minimization measures. ", doi="10.2196/15185", url="http://www.jmir.org/2020/11/e15185/", url="https://doi.org/10.2196/15185", url="http://www.ncbi.nlm.nih.gov/pubmed/33170134" } @Article{info:doi/10.2196/20322, author="Gong, Enying and Baptista, Shaira and Russell, Anthony and Scuffham, Paul and Riddell, Michaela and Speight, Jane and Bird, Dominique and Williams, Emily and Lotfaliany, Mojtaba and Oldenburg, Brian", title="My Diabetes Coach, a Mobile App--Based Interactive Conversational Agent to Support Type 2 Diabetes Self-Management: Randomized Effectiveness-Implementation Trial", journal="J Med Internet Res", year="2020", month="Nov", day="5", volume="22", number="11", pages="e20322", keywords="type 2 diabetes mellitus; self-management; health-related quality of life; digital technology; coaching; mobile phone", abstract="Background: Delivering self-management support to people with type 2 diabetes mellitus is essential to reduce the health system burden and to empower people with the skills, knowledge, and confidence needed to take an active role in managing their own health. Objective: This study aims to evaluate the adoption, use, and effectiveness of the My Diabetes Coach (MDC) program, an app-based interactive embodied conversational agent, Laura, designed to support diabetes self-management in the home setting over 12 months. Methods: This randomized controlled trial evaluated both the implementation and effectiveness of the MDC program. Adults with type 2 diabetes in Australia were recruited and randomized to the intervention arm (MDC) or the control arm (usual care). Program use was tracked over 12 months. Coprimary outcomes included changes in glycated hemoglobin (HbA1c) and health-related quality of life (HRQoL). Data were assessed at baseline and at 6 and 12 months, and analyzed using linear mixed-effects regression models. Results: A total of 187 adults with type 2 diabetes (mean 57 years, SD 10 years; 41.7{\%} women) were recruited and randomly allocated to the intervention (n=93) and control (n=94) arms. MDC program users (92/93 participants) completed 1942 chats with Laura, averaging 243 min (SD 212) per person over 12 months. Compared with baseline, the mean estimated HbA1c decreased in both arms at 12 months (intervention: 0.33{\%} and control: 0.20{\%}), but the net differences between the two arms in change of HbA1c (−0.04{\%}, 95{\%} CI −0.45 to 0.36; P=.83) was not statistically significant. At 12 months, HRQoL utility scores improved in the intervention arm, compared with the control arm (between-arm difference: 0.04, 95{\%} CI 0.00 to 0.07; P=.04). Conclusions: The MDC program was successfully adopted and used by individuals with type 2 diabetes and significantly improved the users' HRQoL. These findings suggest the potential for wider implementation of technology-enabled conversation-based programs for supporting diabetes self-management. Future studies should focus on strategies to maintain program usage and HbA1c improvement. Trial Registration: Australia New Zealand Clinical Trials Registry (ACTRN) 12614001229662; https://anzctr.org.au/Trial/Registration/TrialReview.aspx?ACTRN=12614001229662 ", doi="10.2196/20322", url="https://www.jmir.org/2020/11/e20322", url="https://doi.org/10.2196/20322", url="http://www.ncbi.nlm.nih.gov/pubmed/33151154" } @Article{info:doi/10.2196/20251, author="Almusharraf, Fahad and Rose, Jonathan and Selby, Peter", title="Engaging Unmotivated Smokers to Move Toward Quitting: Design of Motivational Interviewing--Based Chatbot Through Iterative Interactions", journal="J Med Internet Res", year="2020", month="Nov", day="3", volume="22", number="11", pages="e20251", keywords="smoking cessation; motivational interviewing; chatbot; natural language processing", abstract="Background: At any given time, most smokers in a population are ambivalent with no motivation to quit. Motivational interviewing (MI) is an evidence-based technique that aims to elicit change in ambivalent smokers. MI practitioners are scarce and expensive, and smokers are difficult to reach. Smokers are potentially reachable through the web, and if an automated chatbot could emulate an MI conversation, it could form the basis of a low-cost and scalable intervention motivating smokers to quit. Objective: The primary goal of this study is to design, train, and test an automated MI-based chatbot capable of eliciting reflection in a conversation with cigarette smokers. This study describes the process of collecting training data to improve the chatbot's ability to generate MI-oriented responses, particularly reflections and summary statements. The secondary goal of this study is to observe the effects on participants through voluntary feedback given after completing a conversation with the chatbot. Methods: An interdisciplinary collaboration between an MI expert and experts in computer engineering and natural language processing (NLP) co-designed the conversation and algorithms underlying the chatbot. A sample of 121 adult cigarette smokers in 11 successive groups were recruited from a web-based platform for a single-arm prospective iterative design study. The chatbot was designed to stimulate reflections on the pros and cons of smoking using MI's running head start technique. Participants were also asked to confirm the chatbot's classification of their free-form responses to measure the classification accuracy of the underlying NLP models. Each group provided responses that were used to train the chatbot for the next group. Results: A total of 6568 responses from 121 participants in 11 successive groups over 14 weeks were received. From these responses, we were able to isolate 21 unique reasons for and against smoking and the relative frequency of each. The gradual collection of responses as inputs and smoking reasons as labels over the 11 iterations improved the F1 score of the classification within the chatbot from 0.63 in the first group to 0.82 in the final group. The mean time spent by each participant interacting with the chatbot was 21.3 (SD 14.0) min (minimum 6.4 and maximum 89.2). We also found that 34.7{\%} (42/121) of participants enjoyed the interaction with the chatbot, and 8.3{\%} (10/121) of participants noted explicit smoking cessation benefits from the conversation in voluntary feedback that did not solicit this explicitly. Conclusions: Recruiting ambivalent smokers through the web is a viable method to train a chatbot to increase accuracy in reflection and summary statements, the building blocks of MI. A new set of 21 smoking reasons (both for and against) has been identified. Initial feedback from smokers on the experience shows promise toward using it in an intervention. ", doi="10.2196/20251", url="https://www.jmir.org/2020/11/e20251", url="https://doi.org/10.2196/20251", url="http://www.ncbi.nlm.nih.gov/pubmed/33141095" } @Article{info:doi/10.2196/20346, author="Milne-Ives, Madison and de Cock, Caroline and Lim, Ernest and Shehadeh, Melissa Harper and de Pennington, Nick and Mole, Guy and Normando, Eduardo and Meinert, Edward", title="The Effectiveness of Artificial Intelligence Conversational Agents in Health Care: Systematic Review", journal="J Med Internet Res", year="2020", month="Oct", day="22", volume="22", number="10", pages="e20346", keywords="artificial intelligence; avatar; chatbot; conversational agent; digital health; intelligent assistant; speech recognition software; virtual assistant; virtual coach; virtual health care; virtual nursing; voice recognition software", abstract="Background: The high demand for health care services and the growing capability of artificial intelligence have led to the development of conversational agents designed to support a variety of health-related activities, including behavior change, treatment support, health monitoring, training, triage, and screening support. Automation of these tasks could free clinicians to focus on more complex work and increase the accessibility to health care services for the public. An overarching assessment of the acceptability, usability, and effectiveness of these agents in health care is needed to collate the evidence so that future development can target areas for improvement and potential for sustainable adoption. Objective: This systematic review aims to assess the effectiveness and usability of conversational agents in health care and identify the elements that users like and dislike to inform future research and development of these agents. Methods: PubMed, Medline (Ovid), EMBASE (Excerpta Medica dataBASE), CINAHL (Cumulative Index to Nursing and Allied Health Literature), Web of Science, and the Association for Computing Machinery Digital Library were systematically searched for articles published since 2008 that evaluated unconstrained natural language processing conversational agents used in health care. EndNote (version X9, Clarivate Analytics) reference management software was used for initial screening, and full-text screening was conducted by 1 reviewer. Data were extracted, and the risk of bias was assessed by one reviewer and validated by another. Results: A total of 31 studies were selected and included a variety of conversational agents, including 14 chatbots (2 of which were voice chatbots), 6 embodied conversational agents (3 of which were interactive voice response calls, virtual patients, and speech recognition screening systems), 1 contextual question-answering agent, and 1 voice recognition triage system. Overall, the evidence reported was mostly positive or mixed. Usability and satisfaction performed well (27/30 and 26/31), and positive or mixed effectiveness was found in three-quarters of the studies (23/30). However, there were several limitations of the agents highlighted in specific qualitative feedback. Conclusions: The studies generally reported positive or mixed evidence for the effectiveness, usability, and satisfactoriness of the conversational agents investigated, but qualitative user perceptions were more mixed. The quality of many of the studies was limited, and improved study design and reporting are necessary to more accurately evaluate the usefulness of the agents in health care and identify key areas for improvement. Further research should also analyze the cost-effectiveness, privacy, and security of the agents. International Registered Report Identifier (IRRID): RR2-10.2196/16934 ", doi="10.2196/20346", url="http://www.jmir.org/2020/10/e20346/", url="https://doi.org/10.2196/20346", url="http://www.ncbi.nlm.nih.gov/pubmed/33090118" } @Article{info:doi/10.2196/22845, author="Zhang, Jingwen and Oh, Yoo Jung and Lange, Patrick and Yu, Zhou and Fukuoka, Yoshimi", title="Artificial Intelligence Chatbot Behavior Change Model for Designing Artificial Intelligence Chatbots to Promote Physical Activity and a Healthy Diet: Viewpoint", journal="J Med Internet Res", year="2020", month="Sep", day="30", volume="22", number="9", pages="e22845", keywords="chatbot; conversational agent; artificial intelligence; physical activity; diet; intervention; behavior change; natural language processing; communication", abstract="Background: Chatbots empowered by artificial intelligence (AI) can increasingly engage in natural conversations and build relationships with users. Applying AI chatbots to lifestyle modification programs is one of the promising areas to develop cost-effective and feasible behavior interventions to promote physical activity and a healthy diet. Objective: The purposes of this perspective paper are to present a brief literature review of chatbot use in promoting physical activity and a healthy diet, describe the AI chatbot behavior change model our research team developed based on extensive interdisciplinary research, and discuss ethical principles and considerations. Methods: We conducted a preliminary search of studies reporting chatbots for improving physical activity and/or diet in four databases in July 2020. We summarized the characteristics of the chatbot studies and reviewed recent developments in human-AI communication research and innovations in natural language processing. Based on the identified gaps and opportunities, as well as our own clinical and research experience and findings, we propose an AI chatbot behavior change model. Results: Our review found a lack of understanding around theoretical guidance and practical recommendations on designing AI chatbots for lifestyle modification programs. The proposed AI chatbot behavior change model consists of the following four components to provide such guidance: (1) designing chatbot characteristics and understanding user background; (2) building relational capacity; (3) building persuasive conversational capacity; and (4) evaluating mechanisms and outcomes. The rationale and evidence supporting the design and evaluation choices for this model are presented in this paper. Conclusions: As AI chatbots become increasingly integrated into various digital communications, our proposed theoretical framework is the first step to conceptualize the scope of utilization in health behavior change domains and to synthesize all possible dimensions of chatbot features to inform intervention design and evaluation. There is a need for more interdisciplinary work to continue developing AI techniques to improve a chatbot's relational and persuasive capacities to change physical activity and diet behaviors with strong ethical principles. ", doi="10.2196/22845", url="https://www.jmir.org/2020/9/e22845", url="https://doi.org/10.2196/22845", url="http://www.ncbi.nlm.nih.gov/pubmed/32996892" } @Article{info:doi/10.2196/19897, author="Li, Juan and Maharjan, Bikesh and Xie, Bo and Tao, Cui", title="A Personalized Voice-Based Diet Assistant for Caregivers of Alzheimer Disease and Related Dementias: System Development and Validation", journal="J Med Internet Res", year="2020", month="Sep", day="21", volume="22", number="9", pages="e19897", keywords="Alzheimer disease; dementia; diet; knowledge; ontology; voice assistant", abstract="Background: The world's aging population is increasing, with an expected increase in the prevalence of Alzheimer disease and related dementias (ADRD). Proper nutrition and good eating behavior show promise for preventing and slowing the progression of ADRD and consequently improving patients with ADRD's health status and quality of life. Most ADRD care is provided by informal caregivers, so assisting caregivers to manage patients with ADRD's diet is important. Objective: This study aims to design, develop, and test an artificial intelligence--powered voice assistant to help informal caregivers manage the daily diet of patients with ADRD and learn food and nutrition-related knowledge. Methods: The voice assistant is being implemented in several steps: construction of a comprehensive knowledge base with ontologies that define ADRD diet care and user profiles, and is extended with external knowledge graphs; management of conversation between users and the voice assistant; personalized ADRD diet services provided through a semantics-based knowledge graph search and reasoning engine; and system evaluation in use cases with additional qualitative evaluations. Results: A prototype voice assistant was evaluated in the lab using various use cases. Preliminary qualitative test results demonstrate reasonable rates of dialogue success and recommendation correctness. Conclusions: The voice assistant provides a natural, interactive interface for users, and it does not require the user to have a technical background, which may facilitate senior caregivers' use in their daily care tasks. This study suggests the feasibility of using the intelligent voice assistant to help caregivers manage patients with ADRD's diet. ", doi="10.2196/19897", url="http://www.jmir.org/2020/9/e19897/", url="https://doi.org/10.2196/19897", url="http://www.ncbi.nlm.nih.gov/pubmed/32955452" } @Article{info:doi/10.2196/20701, author="Schachner, Theresa and Keller, Roman and v Wangenheim, Florian", title="Artificial Intelligence-Based Conversational Agents for Chronic Conditions: Systematic Literature Review", journal="J Med Internet Res", year="2020", month="Sep", day="14", volume="22", number="9", pages="e20701", keywords="artificial intelligence; conversational agents; chatbots; healthcare; chronic diseases; systematic literature review", abstract="Background: A rising number of conversational agents or chatbots are equipped with artificial intelligence (AI) architecture. They are increasingly prevalent in health care applications such as those providing education and support to patients with chronic diseases, one of the leading causes of death in the 21st century. AI-based chatbots enable more effective and frequent interactions with such patients. Objective: The goal of this systematic literature review is to review the characteristics, health care conditions, and AI architectures of AI-based conversational agents designed specifically for chronic diseases. Methods: We conducted a systematic literature review using PubMed MEDLINE, EMBASE, PyscInfo, CINAHL, ACM Digital Library, ScienceDirect, and Web of Science. We applied a predefined search strategy using the terms ``conversational agent,'' ``healthcare,'' ``artificial intelligence,'' and their synonyms. We updated the search results using Google alerts, and screened reference lists for other relevant articles. We included primary research studies that involved the prevention, treatment, or rehabilitation of chronic diseases, involved a conversational agent, and included any kind of AI architecture. Two independent reviewers conducted screening and data extraction, and Cohen kappa was used to measure interrater agreement.A narrative approach was applied for data synthesis. Results: The literature search found 2052 articles, out of which 10 papers met the inclusion criteria. The small number of identified studies together with the prevalence of quasi-experimental studies (n=7) and prevailing prototype nature of the chatbots (n=7) revealed the immaturity of the field. The reported chatbots addressed a broad variety of chronic diseases (n=6), showcasing a tendency to develop specialized conversational agents for individual chronic conditions. However, there lacks comparison of these chatbots within and between chronic diseases. In addition, the reported evaluation measures were not standardized, and the addressed health goals showed a large range. Together, these study characteristics complicated comparability and open room for future research. While natural language processing represented the most used AI technique (n=7) and the majority of conversational agents allowed for multimodal interaction (n=6), the identified studies demonstrated broad heterogeneity, lack of depth of reported AI techniques and systems, and inconsistent usage of taxonomy of the underlying AI software, further aggravating comparability and generalizability of study results. Conclusions: The literature on AI-based conversational agents for chronic conditions is scarce and mostly consists of quasi-experimental studies with chatbots in prototype stage that use natural language processing and allow for multimodal user interaction. Future research could profit from evidence-based evaluation of the AI-based conversational agents and comparison thereof within and between different chronic health conditions. Besides increased comparability, the quality of chatbots developed for specific chronic conditions and their subsequent impact on the target patients could be enhanced by more structured development and standardized evaluation processes. ", doi="10.2196/20701", url="http://www.jmir.org/2020/9/e20701/", url="https://doi.org/10.2196/20701", url="http://www.ncbi.nlm.nih.gov/pubmed/32924957" } @Article{info:doi/10.2196/19987, author="ter Stal, Silke and Broekhuis, Marijke and van Velsen, Lex and Hermens, Hermie and Tabak, Monique", title="Embodied Conversational Agent Appearance for Health Assessment of Older Adults: Explorative Study", journal="JMIR Hum Factors", year="2020", month="Sep", day="4", volume="7", number="3", pages="e19987", keywords="embodied conversational agent; appearance design; health status assessment; older adults; eHealth", abstract="Background: Embodied conversational agents (ECAs) have great potential for health apps but are rarely investigated as part of such apps. To promote the uptake of health apps, we need to understand how the design of ECAs can influence the preferences, motivation, and behavior of users. Objective: This is one of the first studies that investigates how the appearance of an ECA implemented within a health app affects users' likeliness of following agent advice, their perception of agent characteristics, and their feeling of rapport. In addition, we assessed usability and intention to use. Methods: The ECA was implemented within a frailty assessment app in which three health questionnaires were translated into agent dialogues. In a within-subject experiment, questionnaire dialogues were randomly offered by a young female agent or an older male agent. Participants were asked to think aloud during interaction. Afterward, they rated the likeliness of following the agent's advice, agent characteristics, rapport, usability, and intention to use and participated in a semistructured interview. Results: A total of 20 older adults (72.2 [SD 3.5] years) participated. The older male agent was perceived as more authoritative than the young female agent (P=.03), but no other differences were found. The app scored high on usability (median 6.1) and intention to use (median 6.0). Participants indicated they did not see an added value of the agent to the health app. Conclusions: Agent age and gender little influence users' impressions after short interaction but remain important at first glance to lower the threshold to interact with the agent. Thus, it is important to take the design of ECAs into account when implementing them into health apps. ", doi="10.2196/19987", url="https://humanfactors.jmir.org/2020/3/e19987", url="https://doi.org/10.2196/19987", url="http://www.ncbi.nlm.nih.gov/pubmed/32886068" } @Article{info:doi/10.2196/19706, author="Zhang, Melvyn and Smith, Helen Elizabeth", title="Digital Tools to Ameliorate Psychological Symptoms Associated With COVID-19: Scoping Review", journal="J Med Internet Res", year="2020", month="Aug", day="21", volume="22", number="8", pages="e19706", keywords="COVID-19; digital tool; psychiatry; mental health; digital health; psychology; distress; stress; anxiety; depression", abstract="Background: In the four months after the discovery of the index case of coronavirus disease (COVID-19), several studies highlighted the psychological impact of COVID-19 on frontline health care workers and on members of the general public. It is evident from these studies that individuals experienced elevated levels of anxiety and depression in the acute phase, when they first became aware of the pandemic, and that the psychological distress persisted into subsequent weeks. It is becoming apparent that technological tools such as SMS text messages, web-based interventions, mobile interventions, and conversational agents can help ameliorate psychological distress in the workplace and in society. To our knowledge, there are few publications describing how digital tools have been used to ameliorate psychological symptoms among individuals. Objective: The aim of this review was to identify existing SMS text message, web-based, mobile, and conversational agents that the general public can access to ameliorate the psychological symptoms they are experiencing during the COVID-19 pandemic. Methods: To identify digital tools that were published specifically for COVID-19, a search was performed in the PubMed and MEDLINE databases from the inception of the databases through June 17, 2020. The following search strings were used: ``NCOV OR 2019-nCoV OR SARS-CoV-2 OR Coronavirus OR COVID19 OR COVID'' and ``mHealth OR eHealth OR text''. Another search was conducted in PubMed and MEDLINE to identify existing digital tools for depression and anxiety disorders. A web-based search engine (Google) was used to identify if the cited web-based interventions could be accessed. A mobile app search engine, App Annie, was used to determine if the identified mobile apps were commercially available. Results: A total of 6 studies were identified. Of the 6 identified web-based interventions, 5 websites (83{\%}) could be accessed. Of the 32 identified mobile interventions, 7 apps (22{\%}) could be accessed. Of the 7 identified conversational agents, only 2 (29{\%}) could be accessed. Results: A total of 6 studies were identified. Of the 6 identified web-based interventions, 5 websites (83{\%}) could be accessed. Of the 32 identified mobile interventions, 7 apps (22{\%}) could be accessed. Of the 7 identified conversational agents, only 2 (29{\%}) could be accessed. Conclusions: The COVID-19 pandemic has caused significant psychological distress. Digital tools that are commercially available may be useful for at-risk individuals or individuals with pre-existing psychiatric symptoms. ", doi="10.2196/19706", url="http://www.jmir.org/2020/8/e19706/", url="https://doi.org/10.2196/19706", url="http://www.ncbi.nlm.nih.gov/pubmed/32721922" } @Article{info:doi/10.2196/17367, author="Bray, Lucy and Sharpe, Ashley and Gichuru, Phillip and Fortune, Peter-Marc and Blake, Lucy and Appleton, Victoria", title="The Acceptability and Impact of the Xploro Digital Therapeutic Platform to Inform and Prepare Children for Planned Procedures in a Hospital: Before and After Evaluation Study", journal="J Med Internet Res", year="2020", month="Aug", day="11", volume="22", number="8", pages="e17367", keywords="health literacy; augmented reality; children; procedure; health; artificial intelligence", abstract="Background: There is increasing interest in finding novel approaches to improve the preparation of children for hospital procedures such as surgery, x-rays, and blood tests. Well-prepared and informed children have better outcomes (less procedural anxiety and higher satisfaction). A digital therapeutic (DTx) platform (Xploro) was developed with children to provide health information through gamification, serious games, a chatbot, and an augmented reality avatar. Objective: This before and after evaluation study aims to assess the acceptability of the Xploro DTx and examine its impact on children and their parent's procedural knowledge, procedural anxiety, and reported experiences when attending a hospital for a planned procedure. Methods: We used a mixed methods design with quantitative measures and qualitative data collected sequentially from a group of children who received standard hospital information (before group) and a group of children who received the DTx intervention (after group). Participants were children aged between 8 and 14 years and their parents who attended a hospital for a planned clinical procedure at a children's hospital in North West England. Children and their parents completed self-report measures (perceived knowledge, procedural anxiety, procedural satisfaction, and procedural involvement) at baseline, preprocedure, and postprocedure. Results: A total of 80 children (n=40 standard care group and n=40 intervention group) and their parents participated in the study; the children were aged between 8 and 14 years (average 10.4, SD 2.27 years) and were attending a hospital for a range of procedures. The children in the intervention group reported significantly lower levels of procedural anxiety before the procedure than those in the standard group (two-tailed t63.64=2.740; P=.008). The children in the intervention group also felt more involved in their procedure than those in the standard group (t75=−2.238; P=.03). The children in the intervention group also reported significantly higher levels of perceived procedural knowledge preprocedure (t59.98=−4.892; P=.001) than those in the standard group. As for parents, those with access to the Xploro intervention reported significantly lower levels of procedural anxiety preprocedure than those who did not (t68.51=1.985; P=.05). During the semistructured write and tell interviews, children stated that they enjoyed using the intervention, it was fun and easy to use, and they felt that it had positively influenced their experiences of coming to the hospital for a procedure. Conclusions: This study has shown that the DTx platform, Xploro, has a positive impact on children attending a hospital for a procedure by reducing levels of procedural anxiety. The children and parents in the intervention group described Xploro as improving their experiences and being easy and fun to use. ", doi="10.2196/17367", url="http://www.jmir.org/2020/8/e17367/", url="https://doi.org/10.2196/17367", url="http://www.ncbi.nlm.nih.gov/pubmed/32780025" } @Article{info:doi/10.2196/17158, author="Tudor Car, Lorainne and Dhinagaran, Dhakshenya Ardhithy and Kyaw, Bhone Myint and Kowatsch, Tobias and Joty, Shafiq and Theng, Yin-Leng and Atun, Rifat", title="Conversational Agents in Health Care: Scoping Review and Conceptual Analysis", journal="J Med Internet Res", year="2020", month="Aug", day="7", volume="22", number="8", pages="e17158", keywords="conversational agents; chatbots; artificial intelligence; machine learning; mobile phone; health care; scoping review", abstract="Background: Conversational agents, also known as chatbots, are computer programs designed to simulate human text or verbal conversations. They are increasingly used in a range of fields, including health care. By enabling better accessibility, personalization, and efficiency, conversational agents have the potential to improve patient care. Objective: This study aimed to review the current applications, gaps, and challenges in the literature on conversational agents in health care and provide recommendations for their future research, design, and application. Methods: We performed a scoping review. A broad literature search was performed in MEDLINE (Medical Literature Analysis and Retrieval System Online; Ovid), EMBASE (Excerpta Medica database; Ovid), PubMed, Scopus, and Cochrane Central with the search terms ``conversational agents,'' ``conversational AI,'' ``chatbots,'' and associated synonyms. We also searched the gray literature using sources such as the OCLC (Online Computer Library Center) WorldCat database and ResearchGate in April 2019. Reference lists of relevant articles were checked for further articles. Screening and data extraction were performed in parallel by 2 reviewers. The included evidence was analyzed narratively by employing the principles of thematic analysis. Results: The literature search yielded 47 study reports (45 articles and 2 ongoing clinical trials) that matched the inclusion criteria. The identified conversational agents were largely delivered via smartphone apps (n=23) and used free text only as the main input (n=19) and output (n=30) modality. Case studies describing chatbot development (n=18) were the most prevalent, and only 11 randomized controlled trials were identified. The 3 most commonly reported conversational agent applications in the literature were treatment and monitoring, health care service support, and patient education. Conclusions: The literature on conversational agents in health care is largely descriptive and aimed at treatment and monitoring and health service support. It mostly reports on text-based, artificial intelligence--driven, and smartphone app--delivered conversational agents. There is an urgent need for a robust evaluation of diverse health care conversational agents' formats, focusing on their acceptability, safety, and effectiveness. ", doi="10.2196/17158", url="http://www.jmir.org/2020/8/e17158/", url="https://doi.org/10.2196/17158", url="http://www.ncbi.nlm.nih.gov/pubmed/32763886" } @Article{info:doi/10.2196/19018, author="Ferrand, John and Hockensmith, Ryli and Houghton, Rebecca Fagen and Walsh-Buhi, Eric R", title="Evaluating Smart Assistant Responses for Accuracy and Misinformation Regarding Human Papillomavirus Vaccination: Content Analysis Study", journal="J Med Internet Res", year="2020", month="Aug", day="3", volume="22", number="8", pages="e19018", keywords="digital health; human papillomavirus; smart assistants; chatbots; conversational agents; misinformation; infodemiology; vaccination", abstract="Background: Almost half (46{\%}) of Americans have used a smart assistant of some kind (eg, Apple Siri), and 25{\%} have used a stand-alone smart assistant (eg, Amazon Echo). This positions smart assistants as potentially useful modalities for retrieving health-related information; however, the accuracy of smart assistant responses lacks rigorous evaluation. Objective: This study aimed to evaluate the levels of accuracy, misinformation, and sentiment in smart assistant responses to human papillomavirus (HPV) vaccination--related questions. Methods: We systematically examined responses to questions about the HPV vaccine from the following four most popular smart assistants: Apple Siri, Google Assistant, Amazon Alexa, and Microsoft Cortana. One team member posed 10 questions to each smart assistant and recorded all queries and responses. Two raters independently coded all responses ($\kappa$=0.85). We then assessed differences among the smart assistants in terms of response accuracy, presence of misinformation, and sentiment regarding the HPV vaccine. Results: A total of 103 responses were obtained from the 10 questions posed across the smart assistants. Google Assistant data were excluded owing to nonresponse. Over half (n=63, 61{\%}) of the responses of the remaining three smart assistants were accurate. We found statistically significant differences across the smart assistants (N=103, $\chi$22=7.807, P=.02), with Cortana yielding the greatest proportion of misinformation. Siri yielded the greatest proportion of accurate responses (n=26, 72{\%}), whereas Cortana yielded the lowest proportion of accurate responses (n=33, 54{\%}). Most response sentiments across smart assistants were positive (n=65, 64{\%}) or neutral (n=18, 18{\%}), but Cortana's responses yielded the largest proportion of negative sentiment (n=7, 12{\%}). Conclusions: Smart assistants appear to be average-quality sources for HPV vaccination information, with Alexa responding most reliably. Cortana returned the largest proportion of inaccurate responses, the most misinformation, and the greatest proportion of results with negative sentiments. More collaboration between technology companies and public health entities is necessary to improve the retrieval of accurate health information via smart assistants. ", doi="10.2196/19018", url="https://www.jmir.org/2020/8/e19018", url="https://doi.org/10.2196/19018", url="http://www.ncbi.nlm.nih.gov/pubmed/32744508" } @Article{info:doi/10.2196/18839, author="Chattopadhyay, Debaleena and Ma, Tengteng and Sharifi, Hasti and Martyn-Nemeth, Pamela", title="Computer-Controlled Virtual Humans in Patient-Facing Systems: Systematic Review and Meta-Analysis", journal="J Med Internet Res", year="2020", month="Jul", day="30", volume="22", number="7", pages="e18839", keywords="virtual humans; avatars; patient-facing systems; meta-analysis; conversational agents; chatbot; digital interlocutors", abstract="Background: Virtual humans (VH) are computer-generated characters that appear humanlike and simulate face-to-face conversations using verbal and nonverbal cues. Unlike formless conversational agents, like smart speakers or chatbots, VH bring together the capabilities of both a conversational agent and an interactive avatar (computer-represented digital characters). Although their use in patient-facing systems has garnered substantial interest, it is unknown to what extent VH are effective in health applications. Objective: The purpose of this review was to examine the effectiveness of VH in patient-facing systems. The design and implementation characteristics of these systems were also examined. Methods: Electronic bibliographic databases were searched for peer-reviewed articles with relevant key terms. Studies were included in the systematic review if they designed or evaluated VH in patient-facing systems. Of the included studies, studies that used a randomized controlled trial to evaluate VH were included in the meta-analysis; they were then summarized using the PICOTS framework (population, intervention, comparison group, outcomes, time frame, setting). Summary effect sizes, using random-effects models, were calculated, and the risk of bias was assessed. Results: Among the 8,125 unique records identified, 53 articles describing 33 unique systems, were qualitatively, systematically reviewed. Two distinct design categories emerged --- simple VH and VH augmented with health sensors and trackers. Of the 53 articles, 16 (26 studies) with 44 primary and 22 secondary outcomes were included in the meta-analysis. Meta-analysis of the 44 primary outcome measures revealed a significant difference between intervention and control conditions, favoring the VH intervention (SMD = .166, 95{\%} CI .039-.292, P=.012), but with evidence of some heterogeneity, I2=49.3{\%}. There were more cross-sectional (k=15) than longitudinal studies (k=11). The intervention was delivered using a personal computer in most studies (k=18), followed by a tablet (k=4), mobile kiosk (k=2), head-mounted display (k=1), and a desktop computer in a community center (k=1). Conclusions: We offer evidence for the efficacy of VH in patient-facing systems. Considering that studies included different population and outcome types, more focused analysis is needed in the future. Future studies also need to identify what features of virtual human interventions contribute toward their effectiveness. ", doi="10.2196/18839", url="http://www.jmir.org/2020/7/e18839/", url="https://doi.org/10.2196/18839", url="http://www.ncbi.nlm.nih.gov/pubmed/32729837" } @Article{info:doi/10.2196/17750, author="Anthony, Chris A and Rojas, Edward Octavio and Keffala, Valerie and Glass, Natalie Ann and Shah, Apurva S and Miller, Benjamin J and Hogue, Matthew and Willey, Michael C and Karam, Matthew and Marsh, John Lawrence", title="Acceptance and Commitment Therapy Delivered via a Mobile Phone Messaging Robot to Decrease Postoperative Opioid Use in Patients With Orthopedic Trauma: Randomized Controlled Trial", journal="J Med Internet Res", year="2020", month="Jul", day="29", volume="22", number="7", pages="e17750", keywords="acceptance and commitment therapy; opioid crisis; patient-reported outcome measures; postoperative pain; orthopedics; text messaging; chatbot; conversational agents; mHealth", abstract="Background: Acceptance and commitment therapy (ACT) is a pragmatic approach to help individuals decrease avoidable pain. Objective: This study aims to evaluate the effects of ACT delivered via an automated mobile messaging robot on postoperative opioid use and patient-reported outcomes (PROs) in patients with orthopedic trauma who underwent operative intervention for their injuries. Methods: Adult patients presenting to a level 1 trauma center who underwent operative fixation of a traumatic upper or lower extremity fracture and who used mobile phone text messaging were eligible for the study. Patients were randomized in a 1:1 ratio to either the intervention group, who received twice-daily mobile phone messages communicating an ACT-based intervention for the first 2 weeks after surgery, or the control group, who received no messages. Baseline PROs were completed. Two weeks after the operative intervention, follow-up was performed in the form of an opioid medication pill count and postoperative administration of PROs. The mean number of opioid tablets used by patients was calculated and compared between groups. The mean PRO scores were also compared between the groups. Results: A total of 82 subjects were enrolled in the study. Of the 82 participants, 76 (38 ACT and 38 controls) completed the study. No differences between groups in demographic factors were identified. The intervention group used an average of 26.1 (SD 21.4) opioid tablets, whereas the control group used 41.1 (SD 22.0) tablets, resulting in 36.5{\%} ([41.1-26.1]/41.1) less tablets used by subjects receiving the mobile phone--based ACT intervention (P=.004). The intervention group subjects reported a lower postoperative Patient-Reported Outcome Measure Information System Pain Intensity score (mean 45.9, SD 7.2) than control group subjects (mean 49.7, SD 8.8; P=.04). Conclusions: In this study, the delivery of an ACT-based intervention via an automated mobile messaging robot in the acute postoperative period decreased opioid use in selected patients with orthopedic trauma. Participants receiving the ACT-based intervention also reported lower pain intensity after 2 weeks, although this may not represent a clinically important difference. Trial Registration: ClinicalTrials.gov NCT03991546; https://clinicaltrials.gov/ct2/show/NCT03991546 ", doi="10.2196/17750", url="https://www.jmir.org/2020/7/e17750", url="https://doi.org/10.2196/17750", url="http://www.ncbi.nlm.nih.gov/pubmed/32723723" } @Article{info:doi/10.2196/17038, author="Baptista, Shaira and Wadley, Greg and Bird, Dominique and Oldenburg, Brian and Speight, Jane", title="Acceptability of an Embodied Conversational Agent for Type 2 Diabetes Self-Management Education and Support via a Smartphone App: Mixed Methods Study", journal="JMIR Mhealth Uhealth", year="2020", month="Jul", day="22", volume="8", number="7", pages="e17038", keywords="embodied conversational agent; type 2 diabetes; mobile apps; mHealth; smartphone; self-management; mobile phone", abstract="Background: Embodied conversational agents (ECAs) are increasingly used in health care apps; however, their acceptability in type 2 diabetes (T2D) self-management apps has not yet been investigated. Objective: This study aimed to evaluate the acceptability of the ECA (Laura) used to deliver diabetes self-management education and support in the My Diabetes Coach (MDC) app. Methods: A sequential mixed methods design was applied. Adults with T2D allocated to the intervention arm of the MDC trial used the MDC app over a period of 12 months. At 6 months, they completed questions assessing their interaction with, and attitudes toward, the ECA. In-depth qualitative interviews were conducted with a subsample of the participants from the intervention arm to explore their experiences of using the ECA. The interview questions included the participants' perceptions of Laura, including their initial impression of her (and how this changed over time), her personality, and human character. The quantitative and qualitative data were interpreted using integrated synthesis. Results: Of the 93 intervention participants, 44 (47{\%}) were women; the mean (SD) age of the participants was 55 (SD 10) years and the baseline glycated hemoglobin A1c level was 7.3{\%} (SD 1.5{\%}). Overall, 66 of the 93 participants (71{\%}) provided survey responses. Of these, most described Laura as being helpful (57/66, 86{\%}), friendly (57/66, 86{\%}), competent (56/66, 85{\%}), trustworthy (48/66, 73{\%}), and likable (40/66, 61{\%}). Some described Laura as not real (18/66, 27{\%}), boring (26/66, 39{\%}), and annoying (20/66, 30{\%}). Participants reported that interacting with Laura made them feel more motivated (29/66, 44{\%}), comfortable (24/66, 36{\%}), confident (14/66, 21{\%}), happy (11/66, 17{\%}), and hopeful (8/66, 12{\%}). Furthermore, 20{\%} (13/66) of the participants were frustrated by their interaction with Laura, and 17{\%} (11/66) of the participants reported that interacting with Laura made them feel guilty. A total of 4 themes emerged from the qualitative data (N=19): (1) perceived role: a friendly coach rather than a health professional; (2) perceived support: emotional and motivational support; (3) embodiment preference acceptability of a human-like character; and (4) room for improvement: need for greater congruence between Laura's words and actions. Conclusions: These findings suggest that an ECA is an acceptable means to deliver T2D self-management education and support. A human-like character providing ongoing, friendly, nonjudgmental, emotional, and motivational support is well received. Nevertheless, the ECA can be improved by increasing congruence between its verbal and nonverbal communication and accommodating user preferences. Trial Registration: Australian New Zealand Clinical Trials Registry CTRN12614001229662; https://tinyurl.com/yxshn6pd ", doi="10.2196/17038", url="https://mhealth.jmir.org/2020/7/e17038", url="https://doi.org/10.2196/17038", url="http://www.ncbi.nlm.nih.gov/pubmed/32706734" } @Article{info:doi/10.2196/16021, author="Abd-Alrazaq, Alaa Ali and Rababeh, Asma and Alajlani, Mohannad and Bewick, Bridgette M and Househ, Mowafa", title="Effectiveness and Safety of Using Chatbots to Improve Mental Health: Systematic Review and Meta-Analysis", journal="J Med Internet Res", year="2020", month="Jul", day="13", volume="22", number="7", pages="e16021", keywords="chatbots; conversational agents; mental health; mental disorders; depression; anxiety; effectiveness; safety", abstract="Background: The global shortage of mental health workers has prompted the utilization of technological advancements, such as chatbots, to meet the needs of people with mental health conditions. Chatbots are systems that are able to converse and interact with human users using spoken, written, and visual language. While numerous studies have assessed the effectiveness and safety of using chatbots in mental health, no reviews have pooled the results of those studies. Objective: This study aimed to assess the effectiveness and safety of using chatbots to improve mental health through summarizing and pooling the results of previous studies. Methods: A systematic review was carried out to achieve this objective. The search sources were 7 bibliographic databases (eg, MEDLINE, EMBASE, PsycINFO), the search engine ``Google Scholar,'' and backward and forward reference list checking of the included studies and relevant reviews. Two reviewers independently selected the studies, extracted data from the included studies, and assessed the risk of bias. Data extracted from studies were synthesized using narrative and statistical methods, as appropriate. Results: Of 1048 citations retrieved, we identified 12 studies examining the effect of using chatbots on 8 outcomes. Weak evidence demonstrated that chatbots were effective in improving depression, distress, stress, and acrophobia. In contrast, according to similar evidence, there was no statistically significant effect of using chatbots on subjective psychological wellbeing. Results were conflicting regarding the effect of chatbots on the severity of anxiety and positive and negative affect. Only two studies assessed the safety of chatbots and concluded that they are safe in mental health, as no adverse events or harms were reported. Conclusions: Chatbots have the potential to improve mental health. However, the evidence in this review was not sufficient to definitely conclude this due to lack of evidence that their effect is clinically important, a lack of studies assessing each outcome, high risk of bias in those studies, and conflicting results for some outcomes. Further studies are required to draw solid conclusions about the effectiveness and safety of chatbots. Trial Registration: PROSPERO International Prospective Register of Systematic Reviews CRD42019141219; https://www.crd.york.ac.uk/prospero/display{\_}record.php?ID=CRD42019141219 ", doi="10.2196/16021", url="http://www.jmir.org/2020/7/e16021/", url="https://doi.org/10.2196/16021", url="http://www.ncbi.nlm.nih.gov/pubmed/32673216" } @Article{info:doi/10.2196/18890, author="Linden, Brooke and Tam-Seto, Linna and Stuart, Heather", title="Adherence of the {\#}Here4U App -- Military Version to Criteria for the Development of Rigorous Mental Health Apps", journal="JMIR Form Res", year="2020", month="Jun", day="17", volume="4", number="6", pages="e18890", keywords="mental health services; telemedicine; mHealth; chatbot; e-solutions; Canadian Armed Forces; military health; mobile phone", abstract="Background: Over the past several years, the emergence of mobile mental health apps has increased as a potential solution for populations who may face logistical and social barriers to traditional service delivery, including individuals connected to the military. Objective: The goal of the {\#}Here4U App -- Military Version is to provide evidence-informed mental health support to members of Canada's military community, leveraging artificial intelligence in the form of IBM Canada's Watson Assistant to carry on unique text-based conversations with users, identify presenting mental health concerns, and refer users to self-help resources or recommend professional health care where appropriate. Methods: As the availability and use of mental health apps has increased, so too has the list of recommendations and guidelines for efficacious development. We describe the development and testing conducted between 2018 and 2020 and assess the quality of the {\#}Here4U App against 16 criteria for rigorous mental health app development, as identified by Bakker and colleagues in 2016. Results: The {\#}Here4U App -- Military Version met the majority of Bakker and colleagues' criteria, with those unmet considered not applicable to this particular product or out of scope for research conducted to date. Notably, a formal evaluation of the efficacy of the app is a major priority moving forward. Conclusions: The {\#}Here4U App -- Military Version is a promising new mental health e-solution for members of the Canadian Armed Forces community, filling many of the gaps left by traditional service delivery. ", doi="10.2196/18890", url="https://formative.jmir.org/2020/6/e18890", url="https://doi.org/10.2196/18890", url="http://www.ncbi.nlm.nih.gov/pubmed/32554374" } @Article{info:doi/10.2196/18301, author="Abd-Alrazaq, Alaa and Safi, Zeineb and Alajlani, Mohannad and Warren, Jim and Househ, Mowafa and Denecke, Kerstin", title="Technical Metrics Used to Evaluate Health Care Chatbots: Scoping Review", journal="J Med Internet Res", year="2020", month="Jun", day="5", volume="22", number="6", pages="e18301", keywords="chatbots; conversational agents; health care; evaluation; metrics", abstract="Background: Dialog agents (chatbots) have a long history of application in health care, where they have been used for tasks such as supporting patient self-management and providing counseling. Their use is expected to grow with increasing demands on health systems and improving artificial intelligence (AI) capability. Approaches to the evaluation of health care chatbots, however, appear to be diverse and haphazard, resulting in a potential barrier to the advancement of the field. Objective: This study aims to identify the technical (nonclinical) metrics used by previous studies to evaluate health care chatbots. Methods: Studies were identified by searching 7 bibliographic databases (eg, MEDLINE and PsycINFO) in addition to conducting backward and forward reference list checking of the included studies and relevant reviews. The studies were independently selected by two reviewers who then extracted data from the included studies. Extracted data were synthesized narratively by grouping the identified metrics into categories based on the aspect of chatbots that the metrics evaluated. Results: Of the 1498 citations retrieved, 65 studies were included in this review. Chatbots were evaluated using 27 technical metrics, which were related to chatbots as a whole (eg, usability, classifier performance, speed), response generation (eg, comprehensibility, realism, repetitiveness), response understanding (eg, chatbot understanding as assessed by users, word error rate, concept error rate), and esthetics (eg, appearance of the virtual agent, background color, and content). Conclusions: The technical metrics of health chatbot studies were diverse, with survey designs and global usability metrics dominating. The lack of standardization and paucity of objective measures make it difficult to compare the performance of health chatbots and could inhibit advancement of the field. We suggest that researchers more frequently include metrics computed from conversation logs. In addition, we recommend the development of a framework of technical metrics with recommendations for specific circumstances for their inclusion in chatbot studies. ", doi="10.2196/18301", url="http://www.jmir.org/2020/6/e18301/", url="https://doi.org/10.2196/18301", url="http://www.ncbi.nlm.nih.gov/pubmed/32442157" } @Article{info:doi/10.2196/18677, author="Fu, Weifeng", title="Application of an Isolated Word Speech Recognition System in the Field of Mental Health Consultation: Development and Usability Study", journal="JMIR Med Inform", year="2020", month="Jun", day="3", volume="8", number="6", pages="e18677", keywords="speech recognition; isolated words; mental health; small vocabulary; HMM; hidden Markov model; programming", abstract="Background: Speech recognition is a technology that enables machines to understand human language. Objective: In this study, speech recognition of isolated words from a small vocabulary was applied to the field of mental health counseling. Methods: A software platform was used to establish a human-machine chat for psychological counselling. The software uses voice recognition technology to decode the user's voice information. The software system analyzes and processes the user's voice information according to many internal related databases, and then gives the user accurate feedback. For users who need psychological treatment, the system provides them with psychological education. Results: The speech recognition system included features such as speech extraction, endpoint detection, feature value extraction, training data, and speech recognition. Conclusions: The Hidden Markov Model was adopted, based on multithread programming under a VC2005 compilation environment, to realize the parallel operation of the algorithm and improve the efficiency of speech recognition. After the design was completed, simulation debugging was performed in the laboratory. The experimental results showed that the designed program met the basic requirements of a speech recognition system. ", doi="10.2196/18677", url="https://medinform.jmir.org/2020/6/e18677", url="https://doi.org/10.2196/18677", url="http://www.ncbi.nlm.nih.gov/pubmed/32384054" } @Article{info:doi/10.2196/14827, author="Chen, Jessica and Lyell, David and Laranjo, Liliana and Magrabi, Farah", title="Effect of Speech Recognition on Problem Solving and Recall in Consumer Digital Health Tasks: Controlled Laboratory Experiment", journal="J Med Internet Res", year="2020", month="Jun", day="1", volume="22", number="6", pages="e14827", keywords="speech recognition software; consumer health informatics; ergonomics", abstract="Background: Recent advances in natural language processing and artificial intelligence have led to widespread adoption of speech recognition technologies. In consumer health applications, speech recognition is usually applied to support interactions with conversational agents for data collection, decision support, and patient monitoring. However, little is known about the use of speech recognition in consumer health applications and few studies have evaluated the efficacy of conversational agents in the hands of consumers. In other consumer-facing tools, cognitive load has been observed to be an important factor affecting the use of speech recognition technologies in tasks involving problem solving and recall. Users find it more difficult to think and speak at the same time when compared to typing, pointing, and clicking. However, the effects of speech recognition on cognitive load when performing health tasks has not yet been explored. Objective: The aim of this study was to evaluate the use of speech recognition for documentation in consumer digital health tasks involving problem solving and recall. Methods: Fifty university staff and students were recruited to undertake four documentation tasks with a simulated conversational agent in a computer laboratory. The tasks varied in complexity determined by the amount of problem solving and recall required (simple and complex) and the input modality (speech recognition vs keyboard and mouse). Cognitive load, task completion time, error rate, and usability were measured. Results: Compared to using a keyboard and mouse, speech recognition significantly increased the cognitive load for complex tasks (Z=--4.08, P<.001) and simple tasks (Z=--2.24, P=.03). Complex tasks took significantly longer to complete (Z=--2.52, P=.01) and speech recognition was found to be overall less usable than a keyboard and mouse (Z=--3.30, P=.001). However, there was no effect on errors. Conclusions: Use of a keyboard and mouse was preferable to speech recognition for complex tasks involving problem solving and recall. Further studies using a broader variety of consumer digital health tasks of varying complexity are needed to investigate the contexts in which use of speech recognition is most appropriate. The effects of cognitive load on task performance and its significance also need to be investigated. ", doi="10.2196/14827", url="https://www.jmir.org/2020/6/e14827", url="https://doi.org/10.2196/14827", url="http://www.ncbi.nlm.nih.gov/pubmed/32442129" } @Article{info:doi/10.2196/16794, author="Bennion, Matthew Russell and Hardy, Gillian E and Moore, Roger K and Kellett, Stephen and Millings, Abigail", title="Usability, Acceptability, and Effectiveness of Web-Based Conversational Agents to Facilitate Problem Solving in Older Adults: Controlled Study", journal="J Med Internet Res", year="2020", month="May", day="27", volume="22", number="5", pages="e16794", keywords="transdiagnostic; method of levels; system usability; acceptability; effectiveness; mental health; conversational agents; older adults; chatbots; web-based", abstract="Background: The usability and effectiveness of conversational agents (chatbots) that deliver psychological therapies is under-researched. Objective: This study aimed to compare the system usability, acceptability, and effectiveness in older adults of 2 Web-based conversational agents that differ in theoretical orientation and approach. Methods: In a randomized study, 112 older adults were allocated to 1 of the following 2 fully automated interventions: Manage Your Life Online (MYLO; ie, a chatbot that mimics a therapist using a method of levels approach) and ELIZA (a chatbot that mimics a therapist using a humanistic counseling approach). The primary outcome was problem distress and resolution, with secondary outcome measures of system usability and clinical outcome. Results: MYLO participants spent significantly longer interacting with the conversational agent. Posthoc tests indicated that MYLO participants had significantly lower problem distress at follow-up. There were no differences between MYLO and ELIZA in terms of problem resolution. MYLO was rated as significantly more helpful and likely to be used again. System usability of both the conversational agents was associated with helpfulness of the agents and the willingness of the participants to reuse. Adherence was high. A total of 12{\%} (7/59) of the MYLO group did not carry out their conversation with the chatbot. Conclusions: Controlled studies of chatbots need to be conducted in clinical populations across different age groups. The potential integration of chatbots into psychological care in routine services is discussed. ", doi="10.2196/16794", url="http://www.jmir.org/2020/5/e16794/", url="https://doi.org/10.2196/16794", url="http://www.ncbi.nlm.nih.gov/pubmed/32384055" } @Article{info:doi/10.2196/15589, author="Zand, Aria and Sharma, Arjun and Stokes, Zack and Reynolds, Courtney and Montilla, Alberto and Sauk, Jenny and Hommes, Daniel", title="An Exploration Into the Use of a Chatbot for Patients With Inflammatory Bowel Diseases: Retrospective Cohort Study", journal="J Med Internet Res", year="2020", month="May", day="26", volume="22", number="5", pages="e15589", keywords="chatbots; inflammatory bowel diseases; eHealth; artificial intelligence; telehealth; natural language processing", abstract="Background: The emergence of chatbots in health care is fast approaching. Data on the feasibility of chatbots for chronic disease management are scarce. Objective: This study aimed to explore the feasibility of utilizing natural language processing (NLP) for the categorization of electronic dialog data of patients with inflammatory bowel diseases (IBD) for use in the development of a chatbot. Methods: Electronic dialog data collected between 2013 and 2018 from a care management platform (UCLA eIBD) at a tertiary referral center for IBD at the University of California, Los Angeles, were used. Part of the data was manually reviewed, and an algorithm for categorization was created. The algorithm categorized all relevant dialogs into a set number of categories using NLP. In addition, 3 independent physicians evaluated the appropriateness of the categorization. Results: A total of 16,453 lines of dialog were collected and analyzed. We categorized 8324 messages from 424 patients into seven categories. As there was an overlap in these categories, their frequencies were measured independently as symptoms (2033/6193, 32.83{\%}), medications (2397/6193, 38.70{\%}), appointments (1518/6193, 24.51{\%}), laboratory investigations (2106/6193, 34.01{\%}), finance or insurance (447/6193, 7.22{\%}), communications (2161/6193, 34.89{\%}), procedures (617/6193, 9.96{\%}), and miscellaneous (624/6193, 10.08{\%}). Furthermore, in 95.0{\%} (285/300) of cases, there were minor or no differences in categorization between the algorithm and the three independent physicians. Conclusions: With increased adaptation of electronic health technologies, chatbots could have great potential in interacting with patients, collecting data, and increasing efficiency. Our categorization showcases the feasibility of using NLP in large amounts of electronic dialog for the development of a chatbot algorithm. Chatbots could allow for the monitoring of patients beyond consultations and potentially empower and educate patients and improve clinical outcomes. ", doi="10.2196/15589", url="http://www.jmir.org/2020/5/e15589/", url="https://doi.org/10.2196/15589", url="http://www.ncbi.nlm.nih.gov/pubmed/32452808" } @Article{info:doi/10.2196/15859, author="Arem, Hannah and Scott, Remle and Greenberg, Daniel and Kaltman, Rebecca and Lieberman, Daniel and Lewin, Daniel", title="Assessing Breast Cancer Survivors' Perceptions of Using Voice-Activated Technology to Address Insomnia: Feasibility Study Featuring Focus Groups and In-Depth Interviews", journal="JMIR Cancer", year="2020", month="May", day="26", volume="6", number="1", pages="e15859", keywords="artificial intelligence; breast neoplasms; survivors; insomnia; cognitive behavioral therapy; mobile phones", abstract="Background: Breast cancer survivors (BCSs) are a growing population with a higher prevalence of insomnia than women of the same age without a history of cancer. Cognitive behavioral therapy for insomnia (CBT-I) has been shown to be effective in this population, but it is not widely available to those who need it. Objective: This study aimed to better understand BCSs' experiences with insomnia and to explore the feasibility and acceptability of delivering CBT-I using a virtual assistant (Amazon Alexa). Methods: We first conducted a formative phase with 2 focus groups and 3 in-depth interviews to understand BCSs' perceptions of insomnia as well as their interest in and comfort with using a virtual assistant to learn about CBT-I. We then developed a prototype incorporating participant preferences and CBT-I components and demonstrated it in group and individual settings to BCSs to evaluate acceptability, interest, perceived feasibility, educational potential, and usability of the prototype. We also collected open-ended feedback on the content and used frequencies to describe the quantitative data. Results: We recruited 11 BCSs with insomnia in the formative phase and 14 BCSs in the prototype demonstration. In formative work, anxiety, fear, and hot flashes were identified as causes of insomnia. After prototype demonstration, nearly 79{\%} (11/14) of participants reported an interest in and perceived feasibility of using the virtual assistant to record sleep patterns. Approximately two-thirds of the participants thought lifestyle modification (9/14, 64{\%}) and sleep restriction (9/14, 64{\%}) would be feasible and were interested in this feature of the program (10/14, 71{\%} and 9/14, 64{\%}, respectively). Relaxation exercises were rated as interesting and feasible using the virtual assistant by 71{\%} (10/14) of the participants. Usability was rated as better than average, and all women reported that they would recommend the program to friends and family. Conclusions: This virtual assistant prototype delivering CBT-I components by using a smart speaker was rated as feasible and acceptable, suggesting that this prototype should be fully developed and tested for efficacy in the BCS population. If efficacy is shown in this population, the prototype should also be adapted for other high-risk populations. ", doi="10.2196/15859", url="http://cancer.jmir.org/2020/1/e15859/", url="https://doi.org/10.2196/15859", url="http://www.ncbi.nlm.nih.gov/pubmed/32348274" } @Article{info:doi/10.2196/15085, author="Piao, Meihua and Ryu, Hyeongju and Lee, Hyeongsuk and Kim, Jeongeun", title="Use of the Healthy Lifestyle Coaching Chatbot App to Promote Stair-Climbing Habits Among Office Workers: Exploratory Randomized Controlled Trial", journal="JMIR Mhealth Uhealth", year="2020", month="May", day="19", volume="8", number="5", pages="e15085", keywords="exercise; habits; reward; health behavior; healthy lifestyle", abstract="Background: Lack of time for exercise is common among office workers given their busy lives. Because of occupational restrictions and difficulty in taking time off, it is necessary to suggest effective ways for workers to exercise regularly. Sustaining lifestyle habits that increase nonexercise activity in daily life can solve the issue of lack of exercise time. Healthy Lifestyle Coaching Chatbot is a messenger app based on the habit formation model that can be used as a tool to provide a health behavior intervention that emphasizes the importance of sustainability and involvement. Objective: This study aimed to assess the efficacy of the Healthy Lifestyle Coaching Chatbot intervention presented via a messenger app aimed at stair-climbing habit formation for office workers. Methods: From February 1, 2018, to April 30, 2018, a total of 106 people participated in the trial after online recruitment. Participants were randomly assigned to the intervention group (n=57) or the control group (n=49). The intervention group received cues and intrinsic and extrinsic rewards for the entire 12 weeks. However, the control group did not receive intrinsic rewards for the first 4 weeks and only received all rewards as in the intervention group from the fifth to twelfth week. The Self-Report Habit Index (SRHI) of participants was evaluated every week, and the level of physical activity was measured at the beginning and end of the trial. SPSS Statistics version 21 (IBM Corp) was used for statistical analysis. Results: After 4 weeks of intervention without providing the intrinsic rewards in the control group, the change in SRHI scores was 13.54 (SD 14.99) in the intervention group and 6.42 (SD 9.42) in the control group, indicating a significant difference between the groups (P=.04). When all rewards were given to both groups, from the fifth to twelfth week, the change in SRHI scores of the intervention and control groups was comparable at 12.08 (SD 10.87) and 15.88 (SD 13.29), respectively (P=.21). However, the level of physical activity showed a significant difference between the groups after 12 weeks of intervention (P=.045). Conclusions: This study provides evidence that intrinsic rewards are important to enhance the sustainability and effectiveness of an intervention. The Healthy Lifestyle Coaching Chatbot program can be a cost-effective method for healthy habit formation. Trial Registration: Clinical Research Information Service KCT0004009; https://tinyurl.com/w4oo7md ", doi="10.2196/15085", url="https://mhealth.jmir.org/2020/5/e15085", url="https://doi.org/10.2196/15085", url="http://www.ncbi.nlm.nih.gov/pubmed/32427114" } @Article{info:doi/10.2196/18808, author="Espinoza, Juan and Crown, Kelly and Kulkarni, Omkar", title="A Guide to Chatbots for COVID-19 Screening at Pediatric Health Care Facilities", journal="JMIR Public Health Surveill", year="2020", month="Apr", day="30", volume="6", number="2", pages="e18808", keywords="chatbots; COVID-19: pediatrics; digital health; screening", doi="10.2196/18808", url="http://publichealth.jmir.org/2020/2/e18808/", url="https://doi.org/10.2196/18808", url="http://www.ncbi.nlm.nih.gov/pubmed/32325425" } @Article{info:doi/10.2196/15806, author="Hauser-Ulrich, Sandra and K{\"u}nzli, Hansj{\"o}rg and Meier-Peterhans, Danielle and Kowatsch, Tobias", title="A Smartphone-Based Health Care Chatbot to Promote Self-Management of Chronic Pain (SELMA): Pilot Randomized Controlled Trial", journal="JMIR Mhealth Uhealth", year="2020", month="Apr", day="3", volume="8", number="4", pages="e15806", keywords="conversational agent; chatbot; digital health; pain self-management; cognitive behavior therapy; smartphone; psychoeducation; text-based; health care; chronic pain", abstract="Background: Ongoing pain is one of the most common diseases and has major physical, psychological, social, and economic impacts. A mobile health intervention utilizing a fully automated text-based health care chatbot (TBHC) may offer an innovative way not only to deliver coping strategies and psychoeducation for pain management but also to build a working alliance between a participant and the TBHC. Objective: The objectives of this study are twofold: (1) to describe the design and implementation to promote the chatbot painSELfMAnagement (SELMA), a 2-month smartphone-based cognitive behavior therapy (CBT) TBHC intervention for pain self-management in patients with ongoing or cyclic pain, and (2) to present findings from a pilot randomized controlled trial, in which effectiveness, influence of intention to change behavior, pain duration, working alliance, acceptance, and adherence were evaluated. Methods: Participants were recruited online and in collaboration with pain experts, and were randomized to interact with SELMA for 8 weeks either every day or every other day concerning CBT-based pain management (n=59), or weekly concerning content not related to pain management (n=43). Pain-related impairment (primary outcome), general well-being, pain intensity, and the bond scale of working alliance were measured at baseline and postintervention. Intention to change behavior and pain duration were measured at baseline only, and acceptance postintervention was assessed via self-reporting instruments. Adherence was assessed via usage data. Results: From May 2018 to August 2018, 311 adults downloaded the SELMA app, 102 of whom consented to participate and met the inclusion criteria. The average age of the women (88/102, 86.4{\%}) and men (14/102, 13.6{\%}) participating was 43.7 (SD 12.7) years. Baseline group comparison did not differ with respect to any demographic or clinical variable. The intervention group reported no significant change in pain-related impairment (P=.68) compared to the control group postintervention. The intention to change behavior was positively related to pain-related impairment (P=.01) and pain intensity (P=.01). Working alliance with the TBHC SELMA was comparable to that obtained in guided internet therapies with human coaches. Participants enjoyed using the app, perceiving it as useful and easy to use. Participants of the intervention group replied with an average answer ratio of 0.71 (SD 0.20) to 200 (SD 58.45) conversations initiated by SELMA. Participants' comments revealed an appreciation of the empathic and responsible interaction with the TBHC SELMA. A main criticism was that there was no option to enter free text for the patients' own comments. Conclusions: SELMA is feasible, as revealed mainly by positive feedback and valuable suggestions for future revisions. For example, the participants' intention to change behavior or a more homogenous sample (eg, with a specific type of chronic pain) should be considered in further tailoring of SELMA. Trial Registration: German Clinical Trials Register DRKS00017147; https://tinyurl.com/vx6n6sx, Swiss National Clinical Trial Portal: SNCTP000002712; https://www.kofam.ch/de/studienportal/suche/70582/studie/46326. ", doi="10.2196/15806", url="http://mhealth.jmir.org/2020/4/e15806/", url="https://doi.org/10.2196/15806", url="http://www.ncbi.nlm.nih.gov/pubmed/32242820" } @Article{info:doi/10.2196/16641, author="Hurmuz, Marian Z M and Jansen-Kosterink, Stephanie M and op den Akker, Harm and Hermens, Hermie J", title="User Experience and Potential Health Effects of a Conversational Agent-Based Electronic Health Intervention: Protocol for an Observational Cohort Study", journal="JMIR Res Protoc", year="2020", month="Apr", day="3", volume="9", number="4", pages="e16641", keywords="virtual coaching; effectiveness; user experience; evaluation protocol; older adults; adults; type 2 diabetes mellitus; chronic pain; healthy lifestyle", abstract="Background: While the average human life expectancy has increased remarkably, the length of life with chronic conditions has also increased. To limit the occurrence of chronic conditions and comorbidities, it is important to adopt a healthy lifestyle. Within the European project ``Council of Coaches,'' a personalized coaching platform was developed that supports developing and maintaining a healthy lifestyle. Objective: The primary aim of this study is to assess the user experience with and the use and potential health effects of a fully working Council of Coaches system implemented in a real-world setting among the target population, specifically older adults or adults with type 2 diabetes mellitus or chronic pain. Methods: An observational cohort study with a pretest-posttest design will be conducted. The study population will be a dynamic cohort consisting of older adults, aged ≥55 years, as well as adults aged ≥18 years with type 2 diabetes mellitus or chronic pain. Each participant will interact in a fully automated manner with Council of Coaches for 5 to 9 weeks. The primary outcomes are user experience, use of the program, and potential effects (health-related factors). Secondary outcomes include demographics, applicability of the virtual coaches, and user interaction with the virtual coaches. Results: Recruitment started in December 2019 and is conducted through mass mailing, snowball sampling, and advertisements in newspapers and social media. This study is expected to conclude in August 2020. Conclusions: The results of this study will either confirm or reject the hypothesis that a group of virtual embodied conversational coaches can keep users engaged over several weeks of interaction and contribute to positive health outcomes. Trial Registration: The Netherlands Trial Register: NL7911; https://www.trialregister.nl/trial/7911 International Registered Report Identifier (IRRID): PRR1-10.2196/16641 ", doi="10.2196/16641", url="https://www.researchprotocols.org/2020/4/e16641", url="https://doi.org/10.2196/16641", url="http://www.ncbi.nlm.nih.gov/pubmed/32242517" } @Article{info:doi/10.2196/16235, author="Ta, Vivian and Griffith, Caroline and Boatfield, Carolynn and Wang, Xinyu and Civitello, Maria and Bader, Haley and DeCero, Esther and Loggarakis, Alexia", title="User Experiences of Social Support From Companion Chatbots in Everyday Contexts: Thematic Analysis", journal="J Med Internet Res", year="2020", month="Mar", day="6", volume="22", number="3", pages="e16235", keywords="artificial intelligence; social support; artificial agents; chatbots; interpersonal relations", abstract="Background: Previous research suggests that artificial agents may be a promising source of social support for humans. However, the bulk of this research has been conducted in the context of social support interventions that specifically address stressful situations or health improvements. Little research has examined social support received from artificial agents in everyday contexts. Objective: Considering that social support manifests in not only crises but also everyday situations and that everyday social support forms the basis of support received during more stressful events, we aimed to investigate the types of everyday social support that can be received from artificial agents. Methods: In Study 1, we examined publicly available user reviews (N=1854) of Replika, a popular companion chatbot. In Study 2, a sample (n=66) of Replika users provided detailed open-ended responses regarding their experiences of using Replika. We conducted thematic analysis on both datasets to gain insight into the kind of everyday social support that users receive through interactions with Replika. Results: Replika provides some level of companionship that can help curtail loneliness, provide a ``safe space'' in which users can discuss any topic without the fear of judgment or retaliation, increase positive affect through uplifting and nurturing messages, and provide helpful information/advice when normal sources of informational support are not available. Conclusions: Artificial agents may be a promising source of everyday social support, particularly companionship, emotional, informational, and appraisal support, but not as tangible support. Future studies are needed to determine who might benefit from these types of everyday social support the most and why. These results could potentially be used to help address global health issues or other crises early on in everyday situations before they potentially manifest into larger issues. ", doi="10.2196/16235", url="http://www.jmir.org/2020/2/e16235/", url="https://doi.org/10.2196/16235", url="http://www.ncbi.nlm.nih.gov/pubmed/32141837" } @Article{info:doi/10.2196/15349, author="Garc{\'i}a-Carbajal, Santiago and Pipa-Muniz, Mar{\'i}a and M{\'u}gica, Jose Luis", title="Using String Metrics to Improve the Design of Virtual Conversational Characters: Behavior Simulator Development Study", journal="JMIR Serious Games", year="2020", month="Feb", day="27", volume="8", number="1", pages="e15349", keywords="spoken interaction; string metrics; virtual conversational characters; serious games; e-learning", abstract="Background: An emergency waiting room is a place where conflicts often arise. Nervous relatives in a hostile, unknown environment force security and medical staff to be ready to deal with some awkward situations. Additionally, it has been said that the medical interview is the first diagnostic and therapeutic tool, involving both intellectual and emotional skills on the part of the doctor. At the same time, it seems that there is something mysterious about interviewing that cannot be formalized or taught. In this context, virtual conversational characters (VCCs) are progressively present in most e-learning environments. Objective: In this study, we propose and develop a modular architecture for a VCC-based behavior simulator to be used as a tool for conflict avoidance training. Our behavior simulators are now being used in hospital environments, where training exercises must be easily designed and tested. Methods: We define training exercises as labeled, directed graphs that help an instructor in the design of complex training situations. In order to increase the perception of talking to a real person, the simulator must deal with a huge number of sentences that a VCC must understand and react to. These sentences are grouped into sets identified with a common label. Labels are then used to trigger changes in the active node of the graph that encodes the current state of the training exercise. As a consequence, we need to be able to map every sentence said by the human user into the set it belongs to, in a fast and robust way. In this work, we discuss two different existing string metrics, and compare them to one that we use to assess a designed exercise. Results: Based on the similarities found between different sets, the proposed metric provided valuable information about ill-defined exercises. We also described the environment in which our programs are being used and illustrated it with an example. Conclusions: Initially designed as a tool for training emergency room staff, our software could be of use in many other areas within the same environment. We are currently exploring the possibility of using it in speech therapy situations. ", doi="10.2196/15349", url="http://games.jmir.org/2020/1/e15349/", url="https://doi.org/10.2196/15349", url="http://www.ncbi.nlm.nih.gov/pubmed/32130121" } @Article{info:doi/10.2196/16762, author="Gabrielli, Silvia and Rizzi, Silvia and Carbone, Sara and Donisi, Valeria", title="A Chatbot-Based Coaching Intervention for Adolescents to Promote Life Skills: Pilot Study", journal="JMIR Hum Factors", year="2020", month="Feb", day="14", volume="7", number="1", pages="e16762", keywords="life skills; chatbots; conversational agents; mental health; participatory design; adolescence; bullying; cyberbullying; well-being intervention", abstract="Background: Adolescence is a challenging period, where youth face rapid changes as well as increasing socioemotional demands and threats, such as bullying and cyberbullying. Adolescent mental health and well-being can be best supported by providing effective coaching on life skills, such as coping strategies and protective factors. Interventions that take advantage of online coaching by means of chatbots, deployed on Web or mobile technology, may be a novel and more appealing way to support positive mental health for adolescents. Objective: In this pilot study, we co-designed and conducted a formative evaluation of an online, life skills coaching, chatbot intervention, inspired by the positive technology approach, to promote mental well-being in adolescence. Methods: We co-designed the first life skills coaching session of the CRI (for girls) and CRIS (for boys) chatbot with 20 secondary school students in a participatory design workshop. We then conducted a formative evaluation of the entire intervention---eight sessions---with a convenience sample of 21 adolescents of both genders (mean age 14.52 years). Participants engaged with the chatbot sessions over 4 weeks and filled in an anonymous user experience questionnaire at the end of each session; responses were based on a 5-point Likert scale. Results: A majority of the adolescents found the intervention useful (16/21, 76{\%}), easy to use (19/21, 90{\%}), and innovative (17/21, 81{\%}). Most of the participants (15/21, 71{\%}) liked, in particular, the video cartoons provided by the chatbot in the coaching sessions. They also thought that a session should last only 5-10 minutes (14/21, 66{\%}) and said they would recommend the intervention to a friend (20/21, 95{\%}). Conclusions: We have presented a novel and scalable self-help intervention to deliver life skills coaching to adolescents online that is appealing to this population. This intervention can support the promotion of coping skills and mental well-being among youth. ", doi="10.2196/16762", url="http://humanfactors.jmir.org/2020/1/e16762/", url="https://doi.org/10.2196/16762", url="http://www.ncbi.nlm.nih.gov/pubmed/32130128" } @Article{info:doi/10.2196/15823, author="Kocaballi, Ahmet Baki and Quiroz, Juan C and Rezazadegan, Dana and Berkovsky, Shlomo and Magrabi, Farah and Coiera, Enrico and Laranjo, Liliana", title="Responses of Conversational Agents to Health and Lifestyle Prompts: Investigation of Appropriateness and Presentation Structures", journal="J Med Internet Res", year="2020", month="Feb", day="10", volume="22", number="2", pages="e15823", keywords="conversational agents; chatbots; patient safety; health literacy; public health; design principles; evaluation", abstract="Background: Conversational agents (CAs) are systems that mimic human conversations using text or spoken language. Their widely used examples include voice-activated systems such as Apple Siri, Google Assistant, Amazon Alexa, and Microsoft Cortana. The use of CAs in health care has been on the rise, but concerns about their potential safety risks often remain understudied. Objective: This study aimed to analyze how commonly available, general-purpose CAs on smartphones and smart speakers respond to health and lifestyle prompts (questions and open-ended statements) by examining their responses in terms of content and structure alike. Methods: We followed a piloted script to present health- and lifestyle-related prompts to 8 CAs. The CAs' responses were assessed for their appropriateness on the basis of the prompt type: responses to safety-critical prompts were deemed appropriate if they included a referral to a health professional or service, whereas responses to lifestyle prompts were deemed appropriate if they provided relevant information to address the problem prompted. The response structure was also examined according to information sources (Web search--based or precoded), response content style (informative and/or directive), confirmation of prompt recognition, and empathy. Results: The 8 studied CAs provided in total 240 responses to 30 prompts. They collectively responded appropriately to 41{\%} (46/112) of the safety-critical and 39{\%} (37/96) of the lifestyle prompts. The ratio of appropriate responses deteriorated when safety-critical prompts were rephrased or when the agent used a voice-only interface. The appropriate responses included mostly directive content and empathy statements for the safety-critical prompts and a mix of informative and directive content for the lifestyle prompts. Conclusions: Our results suggest that the commonly available, general-purpose CAs on smartphones and smart speakers with unconstrained natural language interfaces are limited in their ability to advise on both the safety-critical health prompts and lifestyle prompts. Our study also identified some response structures the CAs employed to present their appropriate responses. Further investigation is needed to establish guidelines for designing suitable response structures for different prompt types. ", doi="10.2196/15823", url="https://www.jmir.org/2020/2/e15823", url="https://doi.org/10.2196/15823" } @Article{info:doi/10.2196/14058, author="Kramer, Lean L and ter Stal, Silke and Mulder, Bob C and de Vet, Emely and van Velsen, Lex", title="Developing Embodied Conversational Agents for Coaching People in a Healthy Lifestyle: Scoping Review", journal="J Med Internet Res", year="2020", month="Feb", day="5", volume="22", number="2", pages="e14058", keywords="embodied conversational agent; virtual agent; lifestyle; health behavior; eHealth; chatbots", abstract="Background: Embodied conversational agents (ECAs) are animated computer characters that simulate face-to-face counseling. Owing to their capacity to establish and maintain an empathic relationship, they are deemed to be a promising tool for starting and maintaining a healthy lifestyle. Objective: This review aimed to identify the current practices in designing and evaluating ECAs for coaching people in a healthy lifestyle and provide an overview of their efficacy (on behavioral, knowledge, and motivational parameters) and use (on usability, usage, and user satisfaction parameters). Methods: We used the Arksey and O'Malley framework to conduct a scoping review. PsycINFO, Medical Literature Analysis and Retrieval System Online, and Scopus were searched with a combination of terms related to ECA and lifestyle. Initially, 1789 unique studies were identified; 20 studies were included. Results: Most often, ECAs targeted physical activity (n=16) and had the appearance of a middle-aged African American woman (n=13). Multiple behavior change techniques (median=3) and theories or principles (median=3) were applied, but their interpretation and application were usually not reported. ECAs seemed to be designed for the end user rather than with the end user. Stakeholders were usually not involved. A total of 7 out of 15 studies reported better efficacy outcomes for the intervention group, and 5 out of 8 studies reported better use-related outcomes, as compared with the control group. Conclusions: ECAs are a promising tool for persuasive communication in the health domain. This review provided valuable insights into the current developmental processes, and it recommends the use of human-centered, stakeholder-inclusive design approaches, along with reporting on the design activities in a systematic and comprehensive manner. The gaps in knowledge were identified on the working mechanisms of intervention components and the right timing and frequency of coaching. ", doi="10.2196/14058", url="https://www.jmir.org/2020/2/e14058", url="https://doi.org/10.2196/14058" } @Article{info:doi/10.2196/13244, author="Holdener, Marianne and Gut, Alain and Angerer, Alfred", title="Applicability of the User Engagement Scale to Mobile Health: A Survey-Based Quantitative Study", journal="JMIR Mhealth Uhealth", year="2020", month="Jan", day="3", volume="8", number="1", pages="e13244", keywords="mobile health; mhealth; mobile apps; user engagement; measurement; user engagement scale; chatbot", abstract="Background: There has recently been exponential growth in the development and use of health apps on mobile phones. As with most mobile apps, however, the majority of users abandon them quickly and after minimal use. One of the most critical factors for the success of a health app is how to support users' commitment to their health. Despite increased interest from researchers in mobile health, few studies have examined the measurement of user engagement with health apps. Objective: User engagement is a multidimensional, complex phenomenon. The aim of this study was to understand the concept of user engagement and, in particular, to demonstrate the applicability of a user engagement scale (UES) to mobile health apps. Methods: To determine the measurability of user engagement in a mobile health context, a UES was employed, which is a psychometric tool to measure user engagement with a digital system. This was adapted to Ada, developed by Ada Health, an artificial intelligence--powered personalized health guide that helps people understand their health. A principal component analysis (PCA) with varimax rotation was conducted on 30 items. In addition, sum scores as means of each subscale were calculated. Results: Survey data from 73 Ada users were analyzed. PCA was determined to be suitable, as verified by the sampling adequacy of Kaiser-Meyer-Olkin=0.858, a significant Bartlett test of sphericity ($\chi$2300=1127.1; P<.001), and communalities mostly within the 0.7 range. Although 5 items had to be removed because of low factor loadings, the results of the remaining 25 items revealed 4 attributes: perceived usability, aesthetic appeal, reward, and focused attention. Ada users showed the highest engagement level with perceived usability, with a value of 294, followed by aesthetic appeal, reward, and focused attention. Conclusions: Although the UES was deployed in German and adapted to another digital domain, PCA yielded consistent subscales and a 4-factor structure. This indicates that user engagement with health apps can be assessed with the German version of the UES. These results can benefit related mobile health app engagement research and may be of importance to marketers and app developers. ", doi="10.2196/13244", url="https://mhealth.jmir.org/2020/1/e13244", url="https://doi.org/10.2196/13244", url="http://www.ncbi.nlm.nih.gov/pubmed/31899454" } @Article{info:doi/10.2196/15381, author="Martin-Hammond, Aqueasha and Vemireddy, Sravani and Rao, Kartik", title="Exploring Older Adults' Beliefs About the Use of Intelligent Assistants for Consumer Health Information Management: A Participatory Design Study", journal="JMIR Aging", year="2019", month="Dec", day="11", volume="2", number="2", pages="e15381", keywords="intelligent assistants; artificial intelligence; chatbots; conversational agents; digital health; elderly; aging in place; participatory design; co-design; health information seeking", abstract="Background: Intelligent assistants (IAs), also known as intelligent agents, use artificial intelligence to help users achieve a goal or complete a task. IAs represent a potential solution for providing older adults with individualized assistance at home, for example, to reduce social isolation, serve as memory aids, or help with disease management. However, to design IAs for health that are beneficial and accepted by older adults, it is important to understand their beliefs about IAs, how they would like to interact with IAs for consumer health, and how they desire to integrate IAs into their homes. Objective: We explore older adults' mental models and beliefs about IAs, the tasks they want IAs to support, and how they would like to interact with IAs for consumer health. For the purpose of this study, we focus on IAs in the context of consumer health information management and search. Methods: We present findings from an exploratory, qualitative study that investigated older adults' perspectives of IAs that aid with consumer health information search and management tasks. Eighteen older adults participated in a multiphase, participatory design workshop in which we engaged them in discussion, brainstorming, and design activities that helped us identify their current challenges managing and finding health information at home. We also explored their beliefs and ideas for an IA to assist them with consumer health tasks. We used participatory design activities to identify areas in which they felt IAs might be useful, but also to uncover the reasoning behind the ideas they presented. Discussions were audio-recorded and later transcribed. We compiled design artifacts collected during the study to supplement researcher transcripts and notes. Thematic analysis was used to analyze data. Results: We found that participants saw IAs as potentially useful for providing recommendations, facilitating collaboration between themselves and other caregivers, and for alerts of serious illness. However, they also desired familiar and natural interactions with IAs (eg, using voice) that could, if need be, provide fluid and unconstrained interactions, reason about their symptoms, and provide information or advice. Other participants discussed the need for flexible IAs that could be used by those with low technical resources or skills. Conclusions: From our findings, we present a discussion of three key components of participants' mental models, including the people, behaviors, and interactions they described that were important for IAs for consumer health information management and seeking. We then discuss the role of access, transparency, caregivers, and autonomy in design for addressing participants' concerns about privacy and trust as well as its role in assisting others that may interact with an IA on the older adults' behalf. International Registered Report Identifier (IRRID): RR2-10.1145/3240925.3240972 ", doi="10.2196/15381", url="http://aging.jmir.org/2019/2/e15381/", url="https://doi.org/10.2196/15381", url="http://www.ncbi.nlm.nih.gov/pubmed/31825322" } @Article{info:doi/10.2196/15787, author="Bibault, Jean-Emmanuel and Chaix, Benjamin and Guillemass{\'e}, Arthur and Cousin, Sophie and Escande, Alexandre and Perrin, Morgane and Pienkowski, Arthur and Delamon, Guillaume and Nectoux, Pierre and Brouard, Beno{\^i}t", title="A Chatbot Versus Physicians to Provide Information for Patients With Breast Cancer: Blind, Randomized Controlled Noninferiority Trial", journal="J Med Internet Res", year="2019", month="Nov", day="27", volume="21", number="11", pages="e15787", keywords="chatbot; clinical trial; cancer", abstract="Background: The data regarding the use of conversational agents in oncology are scarce. Objective: The aim of this study was to verify whether an artificial conversational agent was able to provide answers to patients with breast cancer with a level of satisfaction similar to the answers given by a group of physicians. Methods: This study is a blind, noninferiority randomized controlled trial that compared the information given by the chatbot, Vik, with that given by a multidisciplinary group of physicians to patients with breast cancer. Patients were women with breast cancer in treatment or in remission. The European Organisation for Research and Treatment of Cancer Quality of Life Group information questionnaire (EORTC QLQ-INFO25) was adapted and used to compare the quality of the information provided to patients by the physician or the chatbot. The primary outcome was to show that the answers given by the Vik chatbot to common questions asked by patients with breast cancer about their therapy management are at least as satisfying as answers given by a multidisciplinary medical committee by comparing the success rate in each group (defined by a score above 3). The secondary objective was to compare the average scores obtained by the chatbot and physicians for each INFO25 item. Results: A total of 142 patients were included and randomized into two groups of 71. They were all female with a mean age of 42 years (SD 19). The success rates (as defined by a score >3) was 69{\%} (49/71) in the chatbot group versus 64{\%} (46/71) in the physicians group. The binomial test showed the noninferiority (P<.001) of the chatbot's answers. Conclusions: This is the first study that assessed an artificial conversational agent used to inform patients with cancer. The EORTC INFO25 scores from the chatbot were found to be noninferior to the scores of the physicians. Artificial conversational agents may save patients with minor health concerns from a visit to the doctor. This could allow clinicians to spend more time to treat patients who need a consultation the most. Trial Registration: Clinicaltrials.gov NCT03556813, https://tinyurl.com/rgtlehq ", doi="10.2196/15787", url="http://www.jmir.org/2019/11/e15787/", url="https://doi.org/10.2196/15787", url="http://www.ncbi.nlm.nih.gov/pubmed/31774408" } @Article{info:doi/10.2196/15771, author="Brar Prayaga, Rena and Agrawal, Ridhika and Nguyen, Benjamin and Jeong, Erwin W and Noble, Harmony K and Paster, Andrew and Prayaga, Ram S", title="Impact of Social Determinants of Health and Demographics on Refill Requests by Medicare Patients Using a Conversational Artificial Intelligence Text Messaging Solution: Cross-Sectional Study", journal="JMIR Mhealth Uhealth", year="2019", month="Nov", day="18", volume="7", number="11", pages="e15771", keywords="text messaging; SMS; refill adherence; medication adherence; Medicare patients; conversational AI; social determinants of health; predictive modeling; machine learning; health disparities", abstract="Background: Nonadherence among patients with chronic disease continues to be a significant concern, and the use of text message refill reminders has been effective in improving adherence. However, questions remain about how differences in patient characteristics and demographics might influence the likelihood of refill using this channel. Objective: The aim of this study was to evaluate the efficacy of an SMS-based refill reminder solution using conversational artificial intelligence (AI; an automated system that mimics human conversations) with a large Medicare patient population and to explore the association and impact of patient demographics (age, gender, race/ethnicity, language) and social determinants of health on successful engagement with the solution to improve refill adherence. Methods: The study targeted 99,217 patients with chronic disease, median age of 71 years, for medication refill using the mPulse Mobile interactive SMS text messaging solution from December 2016 to February 2019. All patients were partially adherent or nonadherent Medicare Part D members of Kaiser Permanente, Southern California, a large integrated health plan. Patients received SMS reminders in English or Spanish and used simple numeric or text responses to validate their identity, view their medication, and complete a refill request. The refill requests were processed by Kaiser Permanente pharmacists and support staff, and refills were picked up at the pharmacy or mailed to patients. Descriptive statistics and predictive analytics were used to examine the patient population and their refill behavior. Qualitative text analysis was used to evaluate quality of conversational AI. Results: Over the course of the study, 273,356 refill reminders requests were sent to 99,217 patients, resulting in 47,552 refill requests (17.40{\%}). This was consistent with earlier pilot study findings. Of those who requested a refill, 54.81{\%} (26,062/47,552) did so within 2 hours of the reminder. There was a strong inverse relationship (r10=−0.93) between social determinants of health and refill requests. Spanish speakers (5149/48,156, 10.69{\%}) had significantly lower refill request rates compared with English speakers (42,389/225,060, 18.83{\%}; X21 [n=273,216]=1829.2; P<.001). There were also significantly different rates of refill requests by age band (X26 [n=268,793]=1460.3; P<.001), with younger patients requesting refills at a higher rate. Finally, the vast majority (284,598/307,484, 92.23{\%}) of patient responses were handled using conversational AI. Conclusions: Multiple factors impacted refill request rates, including a strong association between social determinants of health and refill rates. The findings suggest that higher refill requests are linked to language, race/ethnicity, age, and social determinants of health, and that English speakers, whites, those younger than 75 years, and those with lower social determinants of health barriers are significantly more likely to request a refill via SMS. A neural network--based predictive model with an accuracy level of 78{\%} was used to identify patients who might benefit from additional outreach to narrow identified gaps based on demographic and socioeconomic factors. ", doi="10.2196/15771", url="http://mhealth.jmir.org/2019/11/e15771/", url="https://doi.org/10.2196/15771", url="http://www.ncbi.nlm.nih.gov/pubmed/31738170" } @Article{info:doi/10.2196/14672, author="Xing, Zhaopeng and Yu, Fei and Du, Jian and Walker, Jennifer S and Paulson, Claire B and Mani, Nandita S and Song, Lixin", title="Conversational Interfaces for Health: Bibliometric Analysis of Grants, Publications, and Patents", journal="J Med Internet Res", year="2019", month="Nov", day="18", volume="21", number="11", pages="e14672", keywords="conversational interfaces; conversational agents; chatbots; artifical intelligence; healthcare; bibliometrics; social network; grants; publications; patents", abstract="Background: Conversational interfaces (CIs) in different modalities have been developed for health purposes, such as health behavioral intervention, patient self-management, and clinical decision support. Despite growing research evidence supporting CIs' potential, CI-related research is still in its infancy. There is a lack of systematic investigation that goes beyond publication review and presents the state of the art from perspectives of funding agencies, academia, and industry by incorporating CI-related public funding and patent activities. Objective: This study aimed to use data systematically extracted from multiple sources (ie, grant, publication, and patent databases) to investigate the development, research, and fund application of health-related CIs and associated stakeholders (ie, countries, organizations, and collaborators). Methods: A multifaceted search query was executed to retrieve records from 9 databases. Bibliometric analysis, social network analysis, and term co-occurrence analysis were conducted on the screened records. Results: This review included 42 funded projects, 428 research publications, and 162 patents. The total dollar amount of grants awarded was US {\$}30,297,932, of which US {\$}13,513,473 was awarded by US funding agencies and US {\$}16,784,459 was funded by the Europe Commission. The top 3 funding agencies in the United States were the National Science Foundation, National Institutes of Health, and Agency for Healthcare Research and Quality. Boston Medical Center was awarded the largest combined grant size (US {\$}2,246,437) for 4 projects. The authors of the publications were from 58 countries and 566 organizations; the top 3 most productive organizations were Northeastern University (United States), Universiti Teknologi MARA (Malaysia), and the French National Center for Scientific Research (CNRS; France). US researchers produced 114 publications. Although 82.0{\%} (464/566) of the organizations engaged in interorganizational collaboration, 2 organizational research-collaboration clusters were observed with Northeastern University and CNRS as the central nodes. About 112 organizations from the United States and China filed 87.7{\%} patents. IBM filed most patents (N=17). Only 5 patents were co-owned by different organizations, and there was no across-country collaboration on patenting activity. The terms patient, child, elderly, and robot were frequently discussed in the 3 record types. The terms related to mental and chronic issues were discussed mainly in grants and publications. The terms regarding multimodal interactions were widely mentioned as users' communication modes with CIs in the identified records. Conclusions: Our findings provided an overview of the countries, organizations, and topic terms in funded projects, as well as the authorship, collaboration, content, and related information of research publications and patents. There is a lack of broad cross-sector partnerships among grant agencies, academia, and industry, particularly in the United States. Our results suggest a need to improve collaboration among public and private sectors and health care organizations in research and patent activities. ", doi="10.2196/14672", url="http://www.jmir.org/2019/11/e14672/", url="https://doi.org/10.2196/14672", url="http://www.ncbi.nlm.nih.gov/pubmed/31738171" } @Article{info:doi/10.2196/15360, author="Kocaballi, Ahmet Baki and Berkovsky, Shlomo and Quiroz, Juan C and Laranjo, Liliana and Tong, Huong Ly and Rezazadegan, Dana and Briatore, Agustina and Coiera, Enrico", title="The Personalization of Conversational Agents in Health Care: Systematic Review", journal="J Med Internet Res", year="2019", month="Nov", day="7", volume="21", number="11", pages="e15360", keywords="conversational interfaces; conversational agents; dialogue systems; personalization; customization; adaptive systems; health care", abstract="Background: The personalization of conversational agents with natural language user interfaces is seeing increasing use in health care applications, shaping the content, structure, or purpose of the dialogue between humans and conversational agents. Objective: The goal of this systematic review was to understand the ways in which personalization has been used with conversational agents in health care and characterize the methods of its implementation. Methods: We searched on PubMed, Embase, CINAHL, PsycInfo, and ACM Digital Library using a predefined search strategy. The studies were included if they: (1) were primary research studies that focused on consumers, caregivers, or health care professionals; (2) involved a conversational agent with an unconstrained natural language interface; (3) tested the system with human subjects; and (4) implemented personalization features. Results: The search found 1958 publications. After abstract and full-text screening, 13 studies were included in the review. Common examples of personalized content included feedback, daily health reports, alerts, warnings, and recommendations. The personalization features were implemented without a theoretical framework of customization and with limited evaluation of its impact. While conversational agents with personalization features were reported to improve user satisfaction, user engagement and dialogue quality, the role of personalization in improving health outcomes was not assessed directly. Conclusions: Most of the studies in our review implemented the personalization features without theoretical or evidence-based support for them and did not leverage the recent developments in other domains of personalization. Future research could incorporate personalization as a distinct design factor with a more careful consideration of its impact on health outcomes and its implications on patient safety, privacy, and decision-making. ", doi="10.2196/15360", url="https://www.jmir.org/2019/11/e15360", url="https://doi.org/10.2196/15360", url="http://www.ncbi.nlm.nih.gov/pubmed/31697237" } @Article{info:doi/10.2196/15018, author="Greer, Stephanie and Ramo, Danielle and Chang, Yin-Juei and Fu, Michael and Moskowitz, Judith and Haritatos, Jana", title="Use of the Chatbot ``Vivibot'' to Deliver Positive Psychology Skills and Promote Well-Being Among Young People After Cancer Treatment: Randomized Controlled Feasibility Trial", journal="JMIR Mhealth Uhealth", year="2019", month="Oct", day="31", volume="7", number="10", pages="e15018", keywords="chatbot; positive psychology; young adult; cancer", abstract="Background: Positive psychology interventions show promise for reducing psychosocial distress associated with health adversity and have the potential to be widely disseminated to young adults through technology. Objective: This pilot randomized controlled trial examined the feasibility of delivering positive psychology skills via the Vivibot chatbot and its effects on key psychosocial well-being outcomes in young adults treated for cancer. Methods: Young adults (age 18-29 years) were recruited within 5 years of completing active cancer treatment by using the Vivibot chatbot on Facebook messenger. Participants were randomized to either immediate access to Vivibot content (experimental group) or access to only daily emotion ratings and access to full chatbot content after 4 weeks (control). Created using a human-centered design process with young adults treated for cancer, Vivibot content includes 4 weeks of positive psychology skills, daily emotion ratings, video, and other material produced by survivors, and periodic feedback check-ins. All participants were assessed for psychosocial well-being via online surveys at baseline and weeks 2, 4, and 8. Analyses examined chatbot engagement and open-ended feedback on likability and perceived helpfulness and compared experimental and control groups with regard to anxiety and depression symptoms and positive and negative emotion changes between baseline and 4 weeks. To verify the main effects, follow-up analyses compared changes in the main outcomes between 4 and 8 weeks in the control group once participants had access to all chatbot content. Results: Data from 45 young adults (36 women; mean age: 25 [SD 2.9]; experimental group: n=25; control group: n=20) were analyzed. Participants in the experimental group spent an average of 74 minutes across an average of 12 active sessions chatting with Vivibot and rated their experience as helpful (mean 2.0/3, SD 0.72) and would recommend it to a friend (mean 6.9/10; SD 2.6). Open-ended feedback noted its nonjudgmental nature as a particular benefit of the chatbot. After 4 weeks, participants in the experimental group reported an average reduction in anxiety of 2.58 standardized t-score units, while the control group reported an increase in anxiety of 0.7 units. A mixed-effects models revealed a trend-level (P=.09) interaction between group and time, with an effect size of 0.41. Those in the experimental group also experienced greater reductions in anxiety when they engaged in more sessions (z=--1.9, P=.06). There were no significant (or trend level) effects by group on changes in depression, positive emotion, or negative emotion. Conclusions: The chatbot format provides a useful and acceptable way of delivering positive psychology skills to young adults who have undergone cancer treatment and supports anxiety reduction. Further analysis with a larger sample size is required to confirm this pattern. ", doi="10.2196/15018", url="http://mhealth.jmir.org/2019/10/e15018/", url="https://doi.org/10.2196/15018", url="http://www.ncbi.nlm.nih.gov/pubmed/31674920" } @Article{info:doi/10.2196/13863, author="Jungmann, Stefanie Maria and Klan, Timo and Kuhn, Sebastian and Jungmann, Florian", title="Accuracy of a Chatbot (Ada) in the Diagnosis of Mental Disorders: Comparative Case Study With Lay and Expert Users", journal="JMIR Form Res", year="2019", month="Oct", day="29", volume="3", number="4", pages="e13863", keywords="artificial intelligence; eHealth; mental disorders; mHealth; screening; (mobile) app; diagnostic", abstract="Background: Health apps for the screening and diagnosis of mental disorders have emerged in recent years on various levels (eg, patients, practitioners, and public health system). However, the diagnostic quality of these apps has not been (sufficiently) tested so far. Objective: The objective of this pilot study was to investigate the diagnostic quality of a health app for a broad spectrum of mental disorders and its dependency on expert knowledge. Methods: Two psychotherapists, two psychology students, and two laypersons each read 20 case vignettes with a broad spectrum of mental disorders. They used a health app (Ada---Your Health Guide) to get a diagnosis by entering the symptoms. Interrater reliabilities were computed between the diagnoses of the case vignettes and the results of the app for each user group. Results: Overall, there was a moderate diagnostic agreement (kappa=0.64) between the results of the app and the case vignettes for mental disorders in adulthood and a low diagnostic agreement (kappa=0.40) for mental disorders in childhood and adolescence. When psychotherapists applied the app, there was a good diagnostic agreement (kappa=0.78) regarding mental disorders in adulthood. The diagnostic agreement was moderate (kappa=0.55/0.60) for students and laypersons. For mental disorders in childhood and adolescence, a moderate diagnostic quality was found when psychotherapists (kappa=0.53) and students (kappa=0.41) used the app, whereas the quality was low for laypersons (kappa=0.29). On average, the app required 34 questions to be answered and 7 min to complete. Conclusions: The health app investigated here can represent an efficient diagnostic screening or help function for mental disorders in adulthood and has the potential to support especially diagnosticians in their work in various ways. The results of this pilot study provide a first indication that the diagnostic accuracy is user dependent and improvements in the app are needed especially for mental disorders in childhood and adolescence. ", doi="10.2196/13863", url="http://formative.jmir.org/2019/4/e13863/", url="https://doi.org/10.2196/13863", url="http://www.ncbi.nlm.nih.gov/pubmed/31663858" } @Article{info:doi/10.2196/16222, author="Powell, John", title="Trust Me, I'm a Chatbot: How Artificial Intelligence in Health Care Fails the Turing Test", journal="J Med Internet Res", year="2019", month="Oct", day="28", volume="21", number="10", pages="e16222", keywords="artificial intelligence; machine learning; medical informatics; digital health; ehealth; chatbots; conversational agents", doi="10.2196/16222", url="http://www.jmir.org/2019/10/e16222/", url="https://doi.org/10.2196/16222", url="http://www.ncbi.nlm.nih.gov/pubmed/31661083" } @Article{info:doi/10.2196/14166, author="Gaffney, Hannah and Mansell, Warren and Tai, Sara", title="Conversational Agents in the Treatment of Mental Health Problems: Mixed-Method Systematic Review", journal="JMIR Ment Health", year="2019", month="Oct", day="18", volume="6", number="10", pages="e14166", keywords="artificial intelligence; mental health; stress, pychological; psychiatry; therapy, computer-assisted; conversational agent; chatbot; digital health", abstract="Background: The use of conversational agent interventions (including chatbots and robots) in mental health is growing at a fast pace. Recent existing reviews have focused exclusively on a subset of embodied conversational agent interventions despite other modalities aiming to achieve the common goal of improved mental health. Objective: This study aimed to review the use of conversational agent interventions in the treatment of mental health problems. Methods: We performed a systematic search using relevant databases (MEDLINE, EMBASE, PsycINFO, Web of Science, and Cochrane library). Studies that reported on an autonomous conversational agent that simulated conversation and reported on a mental health outcome were included. Results: A total of 13 studies were included in the review. Among them, 4 full-scale randomized controlled trials (RCTs) were included. The rest were feasibility, pilot RCTs and quasi-experimental studies. Interventions were diverse in design and targeted a range of mental health problems using a wide variety of therapeutic orientations. All included studies reported reductions in psychological distress postintervention. Furthermore, 5 controlled studies demonstrated significant reductions in psychological distress compared with inactive control groups. In addition, 3 controlled studies comparing interventions with active control groups failed to demonstrate superior effects. Broader utility in promoting well-being in nonclinical populations was unclear. Conclusions: The efficacy and acceptability of conversational agent interventions for mental health problems are promising. However, a more robust experimental design is required to demonstrate efficacy and efficiency. A focus on streamlining interventions, demonstrating equivalence to other treatment modalities, and elucidating mechanisms of action has the potential to increase acceptance by users and clinicians and maximize reach. ", doi="10.2196/14166", url="https://mental.jmir.org/2019/10/e14166", url="https://doi.org/10.2196/14166", url="http://www.ncbi.nlm.nih.gov/pubmed/31628789" } @Article{info:doi/10.2196/13440, author="Bott, Nicholas and Wexler, Sharon and Drury, Lin and Pollak, Chava and Wang, Victor and Scher, Kathleen and Narducci, Sharon", title="A Protocol-Driven, Bedside Digital Conversational Agent to Support Nurse Teams and Mitigate Risks of Hospitalization in Older Adults: Case Control Pre-Post Study", journal="J Med Internet Res", year="2019", month="Oct", day="17", volume="21", number="10", pages="e13440", keywords="digital health; older adults; loneliness; delirium; falls; embodied conversational agent; chatbot; relational agent; information and communication technology", abstract="Background: Hospitalized older adults often experience isolation and disorientation while receiving care, placing them at risk for many inpatient complications, including loneliness, depression, delirium, and falls. Embodied conversational agents (ECAs) are technological entities that can interact with people through spoken conversation. Some ECAs are also relational agents, which build and maintain socioemotional relationships with people across multiple interactions. This study utilized a novel form of relational ECA, provided by Care Coach (care.coach, inc): an animated animal avatar on a tablet device, monitored and controlled by live health advocates. The ECA implemented algorithm-based clinical protocols for hospitalized older adults, such as reorienting patients to mitigate delirium risk, eliciting toileting needs to prevent falls, and engaging patients in social interaction to facilitate social engagement. Previous pilot studies of the Care Coach avatar have demonstrated the ECA's usability and efficacy in home-dwelling older adults. Further study among hospitalized older adults in a larger experimental trial is needed to demonstrate its effectiveness. Objective: The aim of the study was to examine the effect of a human-in-the-loop, protocol-driven relational ECA on loneliness, depression, delirium, and falls among diverse hospitalized older adults. Methods: This was a clinical trial of 95 adults over the age of 65 years, hospitalized at an inner-city community hospital. Intervention participants received an avatar for the duration of their hospital stay; participants on a control unit received a daily 15-min visit from a nursing student. Measures of loneliness (3-item University of California, Los Angeles Loneliness Scale), depression (15-item Geriatric Depression Scale), and delirium (confusion assessment method) were administered upon study enrollment and before discharge. Results: Participants who received the avatar during hospitalization had lower frequency of delirium at discharge (P<.001), reported fewer symptoms of loneliness (P=.01), and experienced fewer falls than control participants. There were no significant differences in self-reported depressive symptoms. Conclusions: The study findings validate the use of human-in-the-loop, relational ECAs among diverse hospitalized older adults. ", doi="10.2196/13440", url="http://www.jmir.org/2019/10/e13440/", url="https://doi.org/10.2196/13440", url="http://www.ncbi.nlm.nih.gov/pubmed/31625949" } @Article{info:doi/10.2196/12529, author="Tanana, Michael J and Soma, Christina S and Srikumar, Vivek and Atkins, David C and Imel, Zac E", title="Development and Evaluation of ClientBot: Patient-Like Conversational Agent to Train Basic Counseling Skills", journal="J Med Internet Res", year="2019", month="Jul", day="15", volume="21", number="7", pages="e12529", keywords="psychotherapy training; interactive learning; conversational agents; deep learning", abstract="Background: Training therapists is both expensive and time-consuming. Degree--based training can require tens of thousands of dollars and hundreds of hours of expert instruction. Counseling skills practice often involves role-plays, standardized patients, or practice with real clients. Performance--based feedback is critical for skill development and expertise, but trainee therapists often receive minimal and subjective feedback, which is distal to their skill practice. Objective: In this study, we developed and evaluated a patient-like neural conversational agent, which provides real-time feedback to trainees via chat--based interaction. Methods: The text--based conversational agent was trained on an archive of 2354 psychotherapy transcripts and provided specific feedback on the use of basic interviewing and counseling skills (ie, open questions and reflections---summary statements of what a client has said). A total of 151 nontherapists were randomized to either (1) immediate feedback on their use of open questions and reflections during practice session with ClientBot or (2) initial education and encouragement on the skills. Results: Participants in the ClientBot condition used 91{\%} (21.4/11.2) more reflections during practice with feedback (P<.001) and 76{\%} (14.1/8) more reflections after feedback was removed (P<.001) relative to the control group. The treatment group used more open questions during training but not after feedback was removed, suggesting that certain skills may not improve with performance--based feedback. Finally, after feedback was removed, the ClientBot group used 31{\%} (32.5/24.7) more listening skills overall (P<.001). Conclusions: This proof-of-concept study demonstrates that practice and feedback can improve trainee use of basic counseling skills. ", doi="10.2196/12529", url="https://www.jmir.org/2019/7/e12529/", url="https://doi.org/10.2196/12529", url="http://www.ncbi.nlm.nih.gov/pubmed/31309929" } @Article{info:doi/10.2196/13664, author="Loveys, Kate and Fricchione, Gregory and Kolappa, Kavitha and Sagar, Mark and Broadbent, Elizabeth", title="Reducing Patient Loneliness With Artificial Agents: Design Insights From Evolutionary Neuropsychiatry", journal="J Med Internet Res", year="2019", month="Jul", day="08", volume="21", number="7", pages="e13664", keywords="loneliness; neuropsychiatry; biological evolution; psychological bonding; interpersonal relations; artificial intelligence; social support; eHealth", doi="10.2196/13664", url="https://www.jmir.org/2019/7/e13664/", url="https://doi.org/10.2196/13664", url="http://www.ncbi.nlm.nih.gov/pubmed/31287067" } @Article{info:doi/10.2196/12996, author="Easton, Katherine and Potter, Stephen and Bec, Remi and Bennion, Matthew and Christensen, Heidi and Grindell, Cheryl and Mirheidari, Bahman and Weich, Scott and de Witte, Luc and Wolstenholme, Daniel and Hawley, Mark S", title="A Virtual Agent to Support Individuals Living With Physical and Mental Comorbidities: Co-Design and Acceptability Testing", journal="J Med Internet Res", year="2019", month="May", day="30", volume="21", number="5", pages="e12996", keywords="COPD; chronic obstructive pulmonary disease; mental health; comorbidity; chronic illness; self-management; artificial intelligence; virtual systems; computer-assisted therapy; chatbot; conversational agent", abstract="Background: Individuals living with long-term physical health conditions frequently experience co-occurring mental health problems. This comorbidity has a significant impact on an individual's levels of emotional distress, health outcomes, and associated health care utilization. As health care services struggle to meet demand and care increasingly moves to the community, digital tools are being promoted to support patients to self-manage their health. One such technology is the autonomous virtual agent (chatbot, conversational agent), which uses artificial intelligence (AI) to process the user's written or spoken natural language and then to select or construct the corresponding appropriate responses. Objective: This study aimed to co-design the content, functionality, and interface modalities of an autonomous virtual agent to support self-management for patients with an exemplar long-term condition (LTC; chronic pulmonary obstructive disease [COPD]) and then to assess the acceptability and system content. Methods: We conducted 2 co-design workshops and a proof-of-concept implementation of an autonomous virtual agent with natural language processing capabilities. This implementation formed the basis for video-based scenario testing of acceptability with adults with a diagnosis of COPD and health professionals involved in their care. Results: Adults (n=6) with a diagnosis of COPD and health professionals (n=5) specified 4 priority self-management scenarios for which they would like to receive support: at the time of diagnosis (information provision), during acute exacerbations (crisis support), during periods of low mood (emotional support), and for general self-management (motivation). From the scenario testing, 12 additional adults with COPD felt the system to be both acceptable and engaging, particularly with regard to internet-of-things capabilities. They felt the system would be particularly useful for individuals living alone. Conclusions: Patients did not explicitly separate mental and physical health needs, although the content they developed for the virtual agent had a clear psychological approach. Supported self-management delivered via an autonomous virtual agent was acceptable to the participants. A co-design process has allowed the research team to identify key design principles, content, and functionality to underpin an autonomous agent for delivering self-management support to older adults living with COPD and potentially other LTCs. ", doi="10.2196/12996", url="http://www.jmir.org/2019/5/e12996/", url="https://doi.org/10.2196/12996", url="http://www.ncbi.nlm.nih.gov/pubmed/31148545" } @Article{info:doi/10.2196/13203, author="Robinson, Nicole Lee and Cottier, Timothy Vaughan and Kavanagh, David John", title="Psychosocial Health Interventions by Social Robots: Systematic Review of Randomized Controlled Trials", journal="J Med Internet Res", year="2019", month="May", day="10", volume="21", number="5", pages="e13203", keywords="social robot; healthcare; treatment; therapy; autism spectrum disorder; dementia", abstract="Background: Social robots that can communicate and interact with people offer exciting opportunities for improved health care access and outcomes. However, evidence from randomized controlled trials (RCTs) on health or well-being outcomes has not yet been clearly synthesized across all health domains where social robots have been tested. Objective: This study aimed to undertake a systematic review examining current evidence from RCTs on the effects of psychosocial interventions by social robots on health or well-being. Methods: Medline, PsycInfo, ScienceDirect, Scopus, and Engineering Village searches across all years in the English language were conducted and supplemented by forward and backward searches. The included papers reported RCTs that assessed changes in health or well-being from interactions with a social robot across at least 2 measurement occasions. Results: Out of 408 extracted records, 27 trials met the inclusion criteria: 6 in child health or well-being, 9 in children with autism spectrum disorder, and 12 with older adults. No trials on adolescents, young adults, or other problem areas were identified, and no studies had interventions where robots spontaneously modified verbal responses based on speech by participants. Most trials were small (total N=5 to 415; median=34), only 6 (22{\%}) reported any follow-up outcomes (2 to 12 weeks; median=3.5) and a single-blind assessment was reported in 8 (31{\%}). More recent trials tended to have greater methodological quality. All papers reported some positive outcomes from robotic interventions, although most trials had some measures that showed no difference or favored alternate treatments. Conclusions: Controlled research on social robots is at an early stage, as is the current range of their applications to health care. Research on social robot interventions in clinical and health settings needs to transition from exploratory investigations to include large-scale controlled trials with sophisticated methodology, to increase confidence in their efficacy. ", doi="10.2196/13203", url="http://www.jmir.org/2019/5/e13203/", url="https://doi.org/10.2196/13203", url="http://www.ncbi.nlm.nih.gov/pubmed/31094357" } @Article{info:doi/10.2196/12856, author="Chaix, Benjamin and Bibault, Jean-Emmanuel and Pienkowski, Arthur and Delamon, Guillaume and Guillemass{\'e}, Arthur and Nectoux, Pierre and Brouard, Beno{\^i}t", title="When Chatbots Meet Patients: One-Year Prospective Study of Conversations Between Patients With Breast Cancer and a Chatbot", journal="JMIR Cancer", year="2019", month="May", day="02", volume="5", number="1", pages="e12856", keywords="artificial intelligence; breast cancer; mobile phone; patient-reported outcomes; symptom management; chatbot; conversational agent", abstract="Background: A chatbot is a software that interacts with users by simulating a human conversation through text or voice via smartphones or computers. It could be a solution to follow up with patients during their disease while saving time for health care providers. Objective: The aim of this study was to evaluate one year of conversations between patients with breast cancer and a chatbot. Methods: Wefight Inc designed a chatbot (Vik) to empower patients with breast cancer and their relatives. Vik responds to the fears and concerns of patients with breast cancer using personalized insights through text messages. We conducted a prospective study by analyzing the users' and patients' data, their usage duration, their interest in the various educational contents proposed, and their level of interactivity. Patients were women with breast cancer or under remission. Results: A total of 4737 patients were included. Results showed that an average of 132,970 messages exchanged per month was observed between patients and the chatbot, Vik. Thus, we calculated the average medication adherence rate over 4 weeks by using a prescription reminder function, and we showed that the more the patients used the chatbot, the more adherent they were. Patients regularly left positive comments and recommended Vik to their friends. The overall satisfaction was 93.95{\%} (900/958). When asked what Vik meant to them and what Vik brought them, 88.00{\%} (943/958) said that Vik provided them with support and helped them track their treatment effectively. Conclusions: We demonstrated that it is possible to obtain support through a chatbot since Vik improved the medication adherence rate of patients with breast cancer. ", doi="10.2196/12856", url="http://cancer.jmir.org/2019/1/e12856/", url="https://doi.org/10.2196/12856", url="http://www.ncbi.nlm.nih.gov/pubmed/31045505" } @Article{info:doi/10.2196/11800, author="Green, Eric P and Pearson, Nicholas and Rajasekharan, Sathyanath and Rauws, Michiel and Joerin, Angela and Kwobah, Edith and Musyimi, Christine and Bhat, Chaya and Jones, Rachel M and Lai, Yihuan", title="Expanding Access to Depression Treatment in Kenya Through Automated Psychological Support: Protocol for a Single-Case Experimental Design Pilot Study", journal="JMIR Res Protoc", year="2019", month="Apr", day="29", volume="8", number="4", pages="e11800", keywords="telemedicine; mental health; depression; artificial intelligence; Kenya; text messaging; chatbot; conversational agent", abstract="Background: Depression during pregnancy and in the postpartum period is associated with a number of poor outcomes for women and their children. Although effective interventions exist for common mental disorders that occur during pregnancy and the postpartum period, most cases in low- and middle-income countries go untreated because of a lack of trained professionals. Task-sharing models such as the Thinking Healthy Program have shown great potential in feasibility and efficacy trials as a strategy for expanding access to treatment in low-resource settings, but there are significant barriers to scale-up. We are addressing this gap by adapting Thinking Healthy for automated delivery via a mobile phone. This new intervention, Healthy Moms, uses an existing artificial intelligence system called Tess (Zuri in Kenya) to drive conversations with users. Objective: The objective of this pilot study is to test the Healthy Moms perinatal depression intervention using a single-case experimental design with pregnant women and new mothers recruited from public hospitals outside of Nairobi, Kenya. Methods: We will invite patients to complete a brief, automated screening delivered via text messages to determine their eligibility. Enrolled participants will be randomized to a 1- or 2-week baseline period and then invited to begin using Zuri. Participants will be prompted to rate their mood via short message service every 3 days during the baseline and intervention periods. We will review system logs and conduct in-depth interviews with participants to study engagement with the intervention, feasibility, and acceptability. We will use visual inspection, in-depth interviews, and Bayesian estimation to generate preliminary data about the potential response to treatment. Results: Our team adapted the intervention content in April and May 2018 and completed an initial prepilot round of formative testing with 10 women from a private maternity hospital in May and June. In preparation for this pilot study, we used feedback from these users to revise the structure and content of the intervention. Recruitment for this protocol began in early 2019. Results are expected toward the end of 2019. Conclusions: The main limitation of this pilot study is that we will recruit women who live in urban and periurban centers in one part of Kenya. The results of this study may not generalize to the broader population of Kenyan women, but that is not an objective of this phase of work. Our primary objective is to gather preliminary data to know how to build and test a more robust service. We are working toward a larger study with a more diverse population. International Registered Report Identifier (IRRID): DERR1-10.2196/11800 ", doi="10.2196/11800", url="http://www.researchprotocols.org/2019/4/e11800/", url="https://doi.org/10.2196/11800", url="http://www.ncbi.nlm.nih.gov/pubmed/31033448" } @Article{info:doi/10.2196/12231, author="Park, SoHyun and Choi, Jeewon and Lee, Sungwoo and Oh, Changhoon and Kim, Changdai and La, Soohyun and Lee, Joonhwan and Suh, Bongwon", title="Designing a Chatbot for a Brief Motivational Interview on Stress Management: Qualitative Case Study", journal="J Med Internet Res", year="2019", month="Apr", day="16", volume="21", number="4", pages="e12231", keywords="motivational interviewing; mental health; conversational agents; stress management", abstract="Background: In addition to addiction and substance abuse, motivational interviewing (MI) is increasingly being integrated in treating other clinical issues such as mental health problems. Most of the many technological adaptations of MI, however, have focused on delivering the action-oriented treatment, leaving its relational component unexplored or vaguely described. This study intended to design a conversational sequence that considers both technical and relational components of MI for a mental health concern. Objective: This case study aimed to design a conversational sequence for a brief motivational interview to be delivered by a Web-based text messaging application (chatbot) and to investigate its conversational experience with graduate students in their coping with stress. Methods: A brief conversational sequence was designed with varied combinations of MI skills to follow the 4 processes of MI. A Web-based text messaging application, Bonobot, was built as a research prototype to deliver the sequence in a conversation. A total of 30 full-time graduate students who self-reported stress with regard to their school life were recruited for a survey of demographic information and perceived stress and a semistructured interview. Interviews were transcribed verbatim and analyzed by Braun and Clarke's thematic method. The themes that reflect the process of, impact of, and needs for the conversational experience are reported. Results: Participants had a high level of perceived stress (mean 22.5 [SD 5.0]). Our findings included the following themes: Evocative Questions and Clich{\'e}d Feedback; Self-Reflection and Potential Consolation; and Need for Information and Contextualized Feedback. Participants particularly favored the relay of evocative questions but were less satisfied with the agent-generated reflective and affirming feedback that filled in-between. Discussing the idea of change was a good means of reflecting on themselves, and some of Bonobot's encouragements related to graduate school life were appreciated. Participants suggested the conversation provide informational support, as well as more contextualized feedback. Conclusions: A conversational sequence for a brief motivational interview was presented in this case study. Participant feedback suggests sequencing questions and MI-adherent statements can facilitate a conversation for stress management, which may encourage a chance of self-reflection. More diversified sequences, along with more contextualized feedback, should follow to offer a better conversational experience and to confirm any empirical effect. ", doi="10.2196/12231", url="https://www.jmir.org/2019/4/e12231/", url="https://doi.org/10.2196/12231", url="http://www.ncbi.nlm.nih.gov/pubmed/30990463" } @Article{info:doi/10.2196/12887, author="Palanica, Adam and Flaschner, Peter and Thommandram, Anirudh and Li, Michael and Fossat, Yan", title="Physicians' Perceptions of Chatbots in Health Care: Cross-Sectional Web-Based Survey", journal="J Med Internet Res", year="2019", month="Apr", day="05", volume="21", number="4", pages="e12887", keywords="physician satisfaction; health care; telemedicine; mobile health; health surveys", abstract="Background: Many potential benefits for the uses of chatbots within the context of health care have been theorized, such as improved patient education and treatment compliance. However, little is known about the perspectives of practicing medical physicians on the use of chatbots in health care, even though these individuals are the traditional benchmark of proper patient care. Objective: This study aimed to investigate the perceptions of physicians regarding the use of health care chatbots, including their benefits, challenges, and risks to patients. Methods: A total of 100 practicing physicians across the United States completed a Web-based, self-report survey to examine their opinions of chatbot technology in health care. Descriptive statistics and frequencies were used to examine the characteristics of participants. Results: A wide variety of positive and negative perspectives were reported on the use of health care chatbots, including the importance to patients for managing their own health and the benefits on physical, psychological, and behavioral health outcomes. More consistent agreement occurred with regard to administrative benefits associated with chatbots; many physicians believed that chatbots would be most beneficial for scheduling doctor appointments (78{\%}, 78/100), locating health clinics (76{\%}, 76/100), or providing medication information (71{\%}, 71/100). Conversely, many physicians believed that chatbots cannot effectively care for all of the patients' needs (76{\%}, 76/100), cannot display human emotion (72{\%}, 72/100), and cannot provide detailed diagnosis and treatment because of not knowing all of the personal factors associated with the patient (71{\%}, 71/100). Many physicians also stated that health care chatbots could be a risk to patients if they self-diagnose too often (714{\%}, 74/100) and do not accurately understand the diagnoses (74{\%}, 74/100). Conclusions: Physicians believed in both costs and benefits associated with chatbots, depending on the logistics and specific roles of the technology. Chatbots may have a beneficial role to play in health care to support, motivate, and coach patients as well as for streamlining organizational tasks; in essence, chatbots could become a surrogate for nonmedical caregivers. However, concerns remain on the inability of chatbots to comprehend the emotional state of humans as well as in areas where expert medical knowledge and intelligence is required. ", doi="10.2196/12887", url="https://www.jmir.org/2019/4/e12887/", url="https://doi.org/10.2196/12887", url="http://www.ncbi.nlm.nih.gov/pubmed/30950796" } @Article{info:doi/10.2196/jmir.9240, author="Tielman, Myrthe L and Neerincx, Mark A and Brinkman, Willem-Paul", title="Design and Evaluation of Personalized Motivational Messages by a Virtual Agent that Assists in Post-Traumatic Stress Disorder Therapy", journal="J Med Internet Res", year="2019", month="Mar", day="27", volume="21", number="3", pages="e9240", keywords="mental health; motivation; trust; user-computer interface; PTSD; computer assisted therapy", abstract="Background: Systems incorporating virtual agents can play a major role in electronic-mental (e-mental) health care, as barriers to care still prevent some patients from receiving the help they need. To properly assist the users of these systems, a virtual agent needs to promote motivation. This can be done by offering motivational messages. Objective: The objective of this study was two-fold. The first was to build a motivational message system for a virtual agent assisting in post-traumatic stress disorder (PTSD) therapy based on domain knowledge from experts. The second was to test the hypotheses that (1) computer-generated motivating messages influence users' motivation to continue with therapy, trust in a good therapy outcome, and the feeling of being heard by the agent and (2) personalized messages outperform generic messages on these factors. Methods: A system capable of generating motivational messages was built by analyzing expert (N=13) knowledge on what types of motivational statements to use in what situation. To test the 2 hypotheses, a Web-based study was performed (N=207). Participants were asked to imagine they were in a certain situation, specified by the progression of their symptoms and initial trust in a good therapy outcome. After this, they received a message from a virtual agent containing either personalized motivation as generated by the system, general motivation, or no motivational content. They were asked how this message changed their motivation to continue and trust in a good outcome as well as how much they felt they were being heard by the agent. Results: Overall, findings confirmed the first hypothesis, as well as the second hypothesis for the measure feeling of being heard by the agent. Personalization of the messages was also shown to be important in those situations where the symptoms were getting worse. In these situations, personalized messages outperformed general messages both in terms of motivation to continue and trust in a good therapy outcome. Conclusions: Expert input can successfully be used to develop a personalized motivational message system. Messages generated by such a system seem to improve people's motivation and trust in PTSD therapy as well as the user's feeling of being heard by a virtual agent. Given the importance of motivation, trust, and therapeutic alliance for successful therapy, we anticipate that the proposed system can improve adherence in e-mental therapy for PTSD and that it can provide a blueprint for the development of an adaptive system for persuasive messages based on expert input. ", doi="10.2196/jmir.9240", url="http://www.jmir.org/2019/3/e9240/", url="https://doi.org/10.2196/jmir.9240", url="http://www.ncbi.nlm.nih.gov/pubmed/30916660" } @Article{info:doi/10.2196/11954, author="Luk, Tzu Tsun and Wong, Sze Wing and Lee, Jung Jae and Chan, Sophia Siu-Chee and Lam, Tai Hing and Wang, Man Ping", title="Exploring Community Smokers' Perspectives for Developing a Chat-Based Smoking Cessation Intervention Delivered Through Mobile Instant Messaging: Qualitative Study", journal="JMIR Mhealth Uhealth", year="2019", month="Jan", day="31", volume="7", number="1", pages="e11954", keywords="chat intervention; instant messaging; mHealth; mobile phone; social media; smoking cessation; tobacco dependence; WhatsApp", abstract="Background: Advances in mobile communication technologies provide a promising avenue for the delivery of tobacco dependence treatment. Although mobile instant messaging (IM) apps (eg, WhatsApp, Facebook messenger, and WeChat) are an inexpensive and widely used communication tool, evidence on its use for promoting health behavior, including smoking cessation, is scarce. Objective: This study aims to explore the perception of using mobile IM as a modality to deliver a proposed chat intervention for smoking cessation in community smokers in Hong Kong, where the proportion of smartphone use is among the highest in the world. Methods: We conducted 5 focus group, semistructured qualitative interviews on a purposive sample of 15 male and 6 female current cigarette smokers (age 23-68 years) recruited from the community in Hong Kong. All interviews were audiotaped and transcribed. Two investigators independently analyzed the transcripts using thematic analyses. Results: Participants considered mobile IM as a feasible and acceptable platform for the delivery of a supportive smoking cessation intervention. The ability to provide more personalized and adaptive behavioral support was regarded as the most valued utility of the IM--based intervention. Other perceived utilities included improved perceived psychosocial support and identification of motivator to quit. In addition, participants provided suggestions on the content and design of the intervention, which may improve the acceptability and usability of the IM--based intervention. These include avoiding health warning information, positive messaging, using former smokers as counselors, and adjusting the language style (spoken vs written) according to the recipients' preference. Conclusions: This qualitative study provides the first evidence that mobile IM may be an alternative mobile health platform for the delivery of a smoking cessation intervention. Furthermore, the findings inform the development of a chat-based, IM smoking cessation program being evaluated in a community trial. ", doi="10.2196/11954", url="https://mhealth.jmir.org/2019/1/e11954/", url="https://doi.org/10.2196/11954", url="http://www.ncbi.nlm.nih.gov/pubmed/30702431" } @Article{info:doi/10.2196/11540, author="Kramer, Jan-Niklas and K{\"u}nzler, Florian and Mishra, Varun and Presset, Bastien and Kotz, David and Smith, Shawna and Scholz, Urte and Kowatsch, Tobias", title="Investigating Intervention Components and Exploring States of Receptivity for a Smartphone App to Promote Physical Activity: Protocol of a Microrandomized Trial", journal="JMIR Res Protoc", year="2019", month="Jan", day="31", volume="8", number="1", pages="e11540", keywords="physical activity; mHealth; walking; smartphone; incentives; self-regulation", abstract="Background: Smartphones enable the implementation of just-in-time adaptive interventions (JITAIs) that tailor the delivery of health interventions over time to user- and time-varying context characteristics. Ideally, JITAIs include effective intervention components, and delivery tailoring is based on effective moderators of intervention effects. Using machine learning techniques to infer each user's context from smartphone sensor data is a promising approach to further enhance tailoring. Objective: The primary objective of this study is to quantify main effects, interactions, and moderators of 3 intervention components of a smartphone-based intervention for physical activity. The secondary objective is the exploration of participants' states of receptivity, that is, situations in which participants are more likely to react to intervention notifications through collection of smartphone sensor data. Methods: In 2017, we developed the Assistant to Lift your Level of activitY (Ally), a chatbot-based mobile health intervention for increasing physical activity that utilizes incentives, planning, and self-monitoring prompts to help participants meet personalized step goals. We used a microrandomized trial design to meet the study objectives. Insurees of a large Swiss insurance company were invited to use the Ally app over a 12-day baseline and a 6-week intervention period. Upon enrollment, participants were randomly allocated to either a financial incentive, a charity incentive, or a no incentive condition. Over the course of the intervention period, participants were repeatedly randomized on a daily basis to either receive prompts that support self-monitoring or not and on a weekly basis to receive 1 of 2 planning interventions or no planning. Participants completed a Web-based questionnaire at baseline and postintervention follow-up. Results: Data collection was completed in January 2018. In total, 274 insurees (mean age 41.73 years; 57.7{\%} [158/274] female) enrolled in the study and installed the Ally app on their smartphones. Main reasons for declining participation were having an incompatible smartphone (37/191, 19.4{\%}) and collection of sensor data (35/191, 18.3{\%}). Step data are available for 227 (82.8{\%}, 227/274) participants, and smartphone sensor data are available for 247 (90.1{\%}, 247/274) participants. Conclusions: This study describes the evidence-based development of a JITAI for increasing physical activity. If components prove to be efficacious, they will be included in a revised version of the app that offers scalable promotion of physical activity at low cost. Trial Registration: ClinicalTrials.gov NCT03384550; https://clinicaltrials.gov/ct2/show/NCT03384550 (Archived by WebCite at http://www.webcitation.org/74IgCiK3d) International Registered Report Identifier (IRRID): DERR1-10.2196/11540 ", doi="10.2196/11540", url="http://www.researchprotocols.org/2019/1/e11540/", url="https://doi.org/10.2196/11540", url="http://www.ncbi.nlm.nih.gov/pubmed/30702430" } @Article{info:doi/10.2196/mental.9782, author="Fulmer, Russell and Joerin, Angela and Gentile, Breanna and Lakerink, Lysanne and Rauws, Michiel", title="Using Psychological Artificial Intelligence (Tess) to Relieve Symptoms of Depression and Anxiety: Randomized Controlled Trial", journal="JMIR Ment Health", year="2018", month="Dec", day="13", volume="5", number="4", pages="e64", keywords="artificial intelligence; mental health services; depression; anxiety; students", abstract="Background: Students in need of mental health care face many barriers including cost, location, availability, and stigma. Studies show that computer-assisted therapy and 1 conversational chatbot delivering cognitive behavioral therapy (CBT) offer a less-intensive and more cost-effective alternative for treating depression and anxiety. Although CBT is one of the most effective treatment methods, applying an integrative approach has been linked to equally effective posttreatment improvement. Integrative psychological artificial intelligence (AI) offers a scalable solution as the demand for affordable, convenient, lasting, and secure support grows. Objective: This study aimed to assess the feasibility and efficacy of using an integrative psychological AI, Tess, to reduce self-identified symptoms of depression and anxiety in college students. Methods: In this randomized controlled trial, 75 participants were recruited from 15 universities across the United States. All participants completed Web-based surveys, including the Patient Health Questionnaire (PHQ-9), Generalized Anxiety Disorder Scale (GAD-7), and Positive and Negative Affect Scale (PANAS) at baseline and 2 to 4 weeks later (T2). The 2 test groups consisted of 50 participants in total and were randomized to receive unlimited access to Tess for either 2 weeks (n=24) or 4 weeks (n=26). The information-only control group participants (n=24) received an electronic link to the National Institute of Mental Health's (NIMH) eBook on depression among college students and were only granted access to Tess after completion of the study. Results: A sample of 74 participants completed this study with 0{\%} attrition from the test group and less than 1{\%} attrition from the control group (1/24). The average age of participants was 22.9 years, with 70{\%} of participants being female (52/74), mostly Asian (37/74, 51{\%}), and white (32/74, 41{\%}). Group 1 received unlimited access to Tess, with daily check-ins for 2 weeks. Group 2 received unlimited access to Tess with biweekly check-ins for 4 weeks. The information-only control group was provided with an electronic link to the NIMH's eBook. Multivariate analysis of covariance was conducted. We used an alpha level of .05 for all statistical tests. Results revealed a statistically significant difference between the control group and group 1, such that group 1 reported a significant reduction in symptoms of depression as measured by the PHQ-9 (P=.03), whereas those in the control group did not. A statistically significant difference was found between the control group and both test groups 1 and 2 for symptoms of anxiety as measured by the GAD-7. Group 1 (P=.045) and group 2 (P=.02) reported a significant reduction in symptoms of anxiety, whereas the control group did not. A statistically significant difference was found on the PANAS between the control group and group 1 (P=.03) and suggests that Tess did impact scores. Conclusions: This study offers evidence that AI can serve as a cost-effective and accessible therapeutic agent. Although not designed to appropriate the role of a trained therapist, integrative psychological AI emerges as a feasible option for delivering support. Trial Registration: International Standard Randomized Controlled Trial Number: ISRCTN61214172; https://doi.org/10.1186/ISRCTN61214172. ", doi="10.2196/mental.9782", url="http://mental.jmir.org/2018/4/e64/", url="https://doi.org/10.2196/mental.9782", url="http://www.ncbi.nlm.nih.gov/pubmed/30545815" } @Article{info:doi/10.2196/12106, author="Inkster, Becky and Sarda, Shubhankar and Subramanian, Vinod", title="An Empathy-Driven, Conversational Artificial Intelligence Agent (Wysa) for Digital Mental Well-Being: Real-World Data Evaluation Mixed-Methods Study", journal="JMIR Mhealth Uhealth", year="2018", month="Nov", day="23", volume="6", number="11", pages="e12106", keywords="mental health; conversational agents; artificial intelligence; chatbots; coping skills; resilience, psychological; depression; mHealth; emotions; empathy", abstract="Background: A World Health Organization 2017 report stated that major depression affects almost 5{\%} of the human population. Major depression is associated with impaired psychosocial functioning and reduced quality of life. Challenges such as shortage of mental health personnel, long waiting times, perceived stigma, and lower government spends pose barriers to the alleviation of mental health problems. Face-to-face psychotherapy alone provides only point-in-time support and cannot scale quickly enough to address this growing global public health challenge. Artificial intelligence (AI)-enabled, empathetic, and evidence-driven conversational mobile app technologies could play an active role in filling this gap by increasing adoption and enabling reach. Although such a technology can help manage these barriers, they should never replace time with a health care professional for more severe mental health problems. However, app technologies could act as a supplementary or intermediate support system. Mobile mental well-being apps need to uphold privacy and foster both short- and long-term positive outcomes. Objective: This study aimed to present a preliminary real-world data evaluation of the effectiveness and engagement levels of an AI-enabled, empathetic, text-based conversational mobile mental well-being app, Wysa, on users with self-reported symptoms of depression. Methods: In the study, a group of anonymous global users were observed who voluntarily installed the Wysa app, engaged in text-based messaging, and self-reported symptoms of depression using the Patient Health Questionnaire-9. On the basis of the extent of app usage on and between 2 consecutive screening time points, 2 distinct groups of users (high users and low users) emerged. The study used mixed-methods approach to evaluate the impact and engagement levels among these users. The quantitative analysis measured the app impact by comparing the average improvement in symptoms of depression between high and low users. The qualitative analysis measured the app engagement and experience by analyzing in-app user feedback and evaluated the performance of a machine learning classifier to detect user objections during conversations. Results: The average mood improvement (ie, difference in pre- and post-self-reported depression scores) between the groups (ie, high vs low users; n=108 and n=21, respectively) revealed that the high users group had significantly higher average improvement (mean 5.84 [SD 6.66]) compared with the low users group (mean 3.52 [SD 6.15]); Mann-Whitney P=.03 and with a moderate effect size of 0.63. Moreover, 67.7{\%} of user-provided feedback responses found the app experience helpful and encouraging. Conclusions: The real-world data evaluation findings on the effectiveness and engagement levels of Wysa app on users with self-reported symptoms of depression show promise. However, further work is required to validate these initial findings in much larger samples and across longer periods. ", doi="10.2196/12106", url="http://mhealth.jmir.org/2018/11/e12106/", url="https://doi.org/10.2196/12106", url="http://www.ncbi.nlm.nih.gov/pubmed/30470676" } @Article{info:doi/10.2196/11510, author="Bickmore, Timothy W and Trinh, Ha and Olafsson, Stefan and O'Leary, Teresa K and Asadi, Reza and Rickles, Nathaniel M and Cruz, Ricardo", title="Patient and Consumer Safety Risks When Using Conversational Assistants for Medical Information: An Observational Study of Siri, Alexa, and Google Assistant", journal="J Med Internet Res", year="2018", month="Sep", day="04", volume="20", number="9", pages="e11510", keywords="conversational assistant; conversational interface; dialogue system; medical error; patient safety", abstract="Background: Conversational assistants, such as Siri, Alexa, and Google Assistant, are ubiquitous and are beginning to be used as portals for medical services. However, the potential safety issues of using conversational assistants for medical information by patients and consumers are not understood. Objective: To determine the prevalence and nature of the harm that could result from patients or consumers using conversational assistants for medical information. Methods: Participants were given medical problems to pose to Siri, Alexa, or Google Assistant, and asked to determine an action to take based on information from the system. Assignment of tasks and systems were randomized across participants, and participants queried the conversational assistants in their own words, making as many attempts as needed until they either reported an action to take or gave up. Participant-reported actions for each medical task were rated for patient harm using an Agency for Healthcare Research and Quality harm scale. Results: Fifty-four subjects completed the study with a mean age of 42 years (SD 18). Twenty-nine (54{\%}) were female, 31 (57{\%}) Caucasian, and 26 (50{\%}) were college educated. Only 8 (15{\%}) reported using a conversational assistant regularly, while 22 (41{\%}) had never used one, and 24 (44{\%}) had tried one ``a few times.`` Forty-four (82{\%}) used computers regularly. Subjects were only able to complete 168 (43{\%}) of their 394 tasks. Of these, 49 (29{\%}) reported actions that could have resulted in some degree of patient harm, including 27 (16{\%}) that could have resulted in death. Conclusions: Reliance on conversational assistants for actionable medical information represents a safety risk for patients and consumers. Patients should be cautioned to not use these technologies for answers to medical questions they intend to act on without further consultation from a health care provider. ", doi="10.2196/11510", url="http://www.jmir.org/2018/9/e11510/", url="https://doi.org/10.2196/11510", url="http://www.ncbi.nlm.nih.gov/pubmed/30181110" } @Article{info:doi/10.2196/10454, author="Suganuma, Shinichiro and Sakamoto, Daisuke and Shimoyama, Haruhiko", title="An Embodied Conversational Agent for Unguided Internet-Based Cognitive Behavior Therapy in Preventative Mental Health: Feasibility and Acceptability Pilot Trial", journal="JMIR Ment Health", year="2018", month="Jul", day="31", volume="5", number="3", pages="e10454", keywords="embodied conversational agent; cognitive behavioral therapy; psychological distress; mental well‐being; artificial intelligence technology", abstract="Background: Recent years have seen an increase in the use of internet-based cognitive behavioral therapy in the area of mental health. Although lower effectiveness and higher dropout rates of unguided than those of guided internet-based cognitive behavioral therapy remain critical issues, not incurring ongoing human clinical resources makes it highly advantageous. Objective: Current research in psychotherapy, which acknowledges the importance of therapeutic alliance, aims to evaluate the feasibility and acceptability, in terms of mental health, of an application that is embodied with a conversational agent. This application was enabled for use as an internet-based cognitive behavioral therapy preventative mental health measure. Methods: Analysis of the data from the 191 participants of the experimental group with a mean age of 38.07 (SD 10.75) years and the 263 participants of the control group with a mean age of 38.05 (SD 13.45) years using a 2-way factorial analysis of variance (group {\texttimes} time) was performed. Results: There was a significant main effect (P=.02) and interaction for time on the variable of positive mental health (P=.02), and for the treatment group, a significant simple main effect was also found (P=.002). In addition, there was a significant main effect (P=.02) and interaction for time on the variable of negative mental health (P=.005), and for the treatment group, a significant simple main effect was also found (P=.001). Conclusions: This research can be seen to represent a certain level of evidence for the mental health application developed herein, indicating empirically that internet-based cognitive behavioral therapy with the embodied conversational agent can be used in mental health care. In the pilot trial, given the issues related to feasibility and acceptability, it is necessary to pursue higher quality evidence while continuing to further improve the application, based on the findings of the current research. ", doi="10.2196/10454", url="http://mental.jmir.org/2018/3/e10454/", url="https://doi.org/10.2196/10454", url="http://www.ncbi.nlm.nih.gov/pubmed/30064969" } @Article{info:doi/10.2196/10148, author="Morris, Robert R and Kouddous, Kareem and Kshirsagar, Rohan and Schueller, Stephen M", title="Towards an Artificially Empathic Conversational Agent for Mental Health Applications: System Design and User Perceptions", journal="J Med Internet Res", year="2018", month="Jun", day="26", volume="20", number="6", pages="e10148", keywords="conversational agents; mental health; empathy; crowdsourcing; peer support", abstract="Background: Conversational agents cannot yet express empathy in nuanced ways that account for the unique circumstances of the user. Agents that possess this faculty could be used to enhance digital mental health interventions. Objective: We sought to design a conversational agent that could express empathic support in ways that might approach, or even match, human capabilities. Another aim was to assess how users might appraise such a system. Methods: Our system used a corpus-based approach to simulate expressed empathy. Responses from an existing pool of online peer support data were repurposed by the agent and presented to the user. Information retrieval techniques and word embeddings were used to select historical responses that best matched a user's concerns. We collected ratings from 37,169 users to evaluate the system. Additionally, we conducted a controlled experiment (N=1284) to test whether the alleged source of a response (human or machine) might change user perceptions. Results: The majority of responses created by the agent (2986/3770, 79.20{\%}) were deemed acceptable by users. However, users significantly preferred the efforts of their peers (P<.001). This effect was maintained in a controlled study (P=.02), even when the only difference in responses was whether they were framed as coming from a human or a machine. Conclusions: Our system illustrates a novel way for machines to construct nuanced and personalized empathic utterances. However, the design had significant limitations and further research is needed to make this approach viable. Our controlled study suggests that even in ideal conditions, nonhuman agents may struggle to express empathy as well as humans. The ethical implications of empathic agents, as well as their potential iatrogenic effects, are also discussed. ", doi="10.2196/10148", url="http://www.jmir.org/2018/6/e10148/", url="https://doi.org/10.2196/10148", url="http://www.ncbi.nlm.nih.gov/pubmed/29945856" } @Article{info:doi/10.2196/mental.9423, author="Martinez-Martin, Nicole and Kreitmair, Karola", title="Ethical Issues for Direct-to-Consumer Digital Psychotherapy Apps: Addressing Accountability, Data Protection, and Consent", journal="JMIR Ment Health", year="2018", month="Apr", day="23", volume="5", number="2", pages="e32", keywords="ethics; ethical issues; mental health; technology; telemedicine; mHealth; psychotherapy", doi="10.2196/mental.9423", url="http://mental.jmir.org/2018/2/e32/", url="https://doi.org/10.2196/mental.9423", url="http://www.ncbi.nlm.nih.gov/pubmed/29685865" } @Article{info:doi/10.2196/iproc.8585, author="Howe, Esther and Pedrelli, Paola and Morris, Robert and Nyer, Maren and Mischoulon, David and Picard, Rosalind", title="Feasibility of an Automated System Counselor for Survivors of Sexual Assault", journal="iproc", year="2017", month="Sep", day="22", volume="3", number="1", pages="e37", keywords="CBT; web chat", abstract="Background: Sexual assault (SA) is common and costly to individuals and society, and increases risk of mental health disorders. Stigma and cost of care discourage survivors from seeking help. Norms profiling survivors as heterosexual, cisgendered women dissuade LGBTQIA+ individuals and men from accessing care. Because individuals prefer disclosing sensitive information online rather than in-person, online systems---like instant messaging and chatbots---for counseling may bypass concerns about stigma. These systems' anonymity may increase disclosure and decrease impression management, the process by which individuals attempt to influence others' perceptions. Their low cost may expand reach of care. There are no known evidence-based chat platforms for SA survivors. Objective: To examine feasibility of a chat platform with peer and automated system (chatbot) counseling interfaces to provide cognitive reappraisals (a cognitive behavioral therapy technique) to survivors. Methods: Participants are English-speaking, US-based survivors, 18+ years old. Participants are told they will be randomized to chat with a peer or automated system counselor 5 times over 2 weeks. In reality, all participants chat with a peer counselor. Chats employ a modified-for-context evidence-based cognitive reappraisal script developed by Koko, a company offering support services for emotional distress via social networks. At baseline, participants indicate counselor type preference and complete a basic demographic form, the Brief Fear of Negative Evaluation Scale, and self-disclosure items from the International Personality Item Pool. After 5 chats, participants complete questions from the Client Satisfaction Questionnaire (CSQ), Self-Reported Attitudes Toward Agent, and the Working Alliance Inventory. Hypotheses: 1) Online chatting and automated systems will be acceptable and feasible means of delivering cognitive reappraisals to survivors. 2) High impression management (IM≥25) and low self-disclosure (SD≤45) will be associated with preference for an automated system. 3) IM and SD will separately moderate the relationship between counselor assignment and participant satisfaction. Results: Ten participants have completed the study. Recruitment is ongoing. We will enroll 50+ participants by 10/2017 and outline findings at the Connected Health Conference. To date, 70{\%} of participants completed all chats within 24 hours of enrollment, and 60{\%} indicated a pre-chat preference for an automated system, suggesting acceptability of the concept. The post-chat CSQ mean total score of 3.98 on a 5-point Likert scale (1=Poor; 5=Excellent) suggests platform acceptability. Of the 50{\%} reporting high IM, 60{\%} indicated preference for an automated system. Of the 30{\%} reporting low SD, 33{\%} reported preference for an automated system. At recruitment completion, ANOVA analyses will elucidate relationships between IM, SD, and counselor assignment. Correlation and linear regression analyses will show any moderating effect of IM and SD on the relationship between counselor assignment and participant satisfaction. Conclusions: Preliminary results suggest acceptability and feasibility of cognitive reappraisals via chat for survivors, and of the automated system counselor concept. Final results will explore relationships between SD, IM, counselor type, and participant satisfaction to inform the development of new platforms for survivors. ", doi="10.2196/iproc.8585", url="http://www.iproc.org/2017/1/e37/", url="https://doi.org/10.2196/iproc.8585" } @Article{info:doi/10.2196/jmir.7023, author="Hoermann, Simon and McCabe, Kathryn L and Milne, David N and Calvo, Rafael A", title="Application of Synchronous Text-Based Dialogue Systems in Mental Health Interventions: Systematic Review", journal="J Med Internet Res", year="2017", month="Jul", day="21", volume="19", number="8", pages="e267", keywords="chat; dialog system; remote psychotherapy", abstract="Background: Synchronous written conversations (or ``chats'') are becoming increasingly popular as Web-based mental health interventions. Therefore, it is of utmost importance to evaluate and summarize the quality of these interventions. Objective: The aim of this study was to review the current evidence for the feasibility and effectiveness of online one-on-one mental health interventions that use text-based synchronous chat. Methods: A systematic search was conducted of the databases relevant to this area of research (Medical Literature Analysis and Retrieval System Online [MEDLINE], PsycINFO, Central, Scopus, EMBASE, Web of Science, IEEE, and ACM). There were no specific selection criteria relating to the participant group. Studies were included if they reported interventions with individual text-based synchronous conversations (ie, chat or text messaging) and a psychological outcome measure. Results: A total of 24 articles were included in this review. Interventions included a wide range of mental health targets (eg, anxiety, distress, depression, eating disorders, and addiction) and intervention design. Overall, compared with the waitlist (WL) condition, studies showed significant and sustained improvements in mental health outcomes following synchronous text-based intervention, and post treatment improvement equivalent but not superior to treatment as usual (TAU) (eg, face-to-face and telephone counseling). Conclusions: Feasibility studies indicate substantial innovation in this area of mental health intervention with studies utilizing trained volunteers and chatbot technologies to deliver interventions. While studies of efficacy show positive post-intervention gains, further research is needed to determine whether time requirements for this mode of intervention are feasible in clinical practice. ", doi="10.2196/jmir.7023", url="http://www.jmir.org/2017/8/e267/", url="https://doi.org/10.2196/jmir.7023", url="http://www.ncbi.nlm.nih.gov/pubmed/28784594" } @Article{info:doi/10.2196/mental.7785, author="Fitzpatrick, Kathleen Kara and Darcy, Alison and Vierhile, Molly", title="Delivering Cognitive Behavior Therapy to Young Adults With Symptoms of Depression and Anxiety Using a Fully Automated Conversational Agent (Woebot): A Randomized Controlled Trial", journal="JMIR Ment Health", year="2017", month="Jun", day="06", volume="4", number="2", pages="e19", keywords="conversational agents; mobile mental health; mental health; chatbots; depression; anxiety; college students; digital health", abstract="Background: Web-based cognitive-behavioral therapeutic (CBT) apps have demonstrated efficacy but are characterized by poor adherence. Conversational agents may offer a convenient, engaging way of getting support at any time. Objective: The objective of the study was to determine the feasibility, acceptability, and preliminary efficacy of a fully automated conversational agent to deliver a self-help program for college students who self-identify as having symptoms of anxiety and depression. Methods: In an unblinded trial, 70 individuals age 18-28 years were recruited online from a university community social media site and were randomized to receive either 2 weeks (up to 20 sessions) of self-help content derived from CBT principles in a conversational format with a text-based conversational agent (Woebot) (n=34) or were directed to the National Institute of Mental Health ebook, ``Depression in College Students,'' as an information-only control group (n=36). All participants completed Web-based versions of the 9-item Patient Health Questionnaire (PHQ-9), the 7-item Generalized Anxiety Disorder scale (GAD-7), and the Positive and Negative Affect Scale at baseline and 2-3 weeks later (T2). Results: Participants were on average 22.2 years old (SD 2.33), 67{\%} female (47/70), mostly non-Hispanic (93{\%}, 54/58), and Caucasian (79{\%}, 46/58). Participants in the Woebot group engaged with the conversational agent an average of 12.14 (SD 2.23) times over the study period. No significant differences existed between the groups at baseline, and 83{\%} (58/70) of participants provided data at T2 (17{\%} attrition). Intent-to-treat univariate analysis of covariance revealed a significant group difference on depression such that those in the Woebot group significantly reduced their symptoms of depression over the study period as measured by the PHQ-9 (F=6.47; P=.01) while those in the information control group did not. In an analysis of completers, participants in both groups significantly reduced anxiety as measured by the GAD-7 (F1,54= 9.24; P=.004). Participants' comments suggest that process factors were more influential on their acceptability of the program than content factors mirroring traditional therapy. Conclusions: Conversational agents appear to be a feasible, engaging, and effective way to deliver CBT. ", doi="10.2196/mental.7785", url="http://mental.jmir.org/2017/2/e19/", url="https://doi.org/10.2196/mental.7785", url="http://www.ncbi.nlm.nih.gov/pubmed/28588005" } @Article{info:doi/10.2196/jmir.6553, author="Provoost, Simon and Lau, Ho Ming and Ruwaard, Jeroen and Riper, Heleen", title="Embodied Conversational Agents in Clinical Psychology: A Scoping Review", journal="J Med Internet Res", year="2017", month="May", day="09", volume="19", number="5", pages="e151", keywords="eHealth; review; embodied conversational agent; human computer interaction; clinical psychology; mental disorders; intelligent agent; health behavior", abstract="Background: Embodied conversational agents (ECAs) are computer-generated characters that simulate key properties of human face-to-face conversation, such as verbal and nonverbal behavior. In Internet-based eHealth interventions, ECAs may be used for the delivery of automated human support factors. Objective: We aim to provide an overview of the technological and clinical possibilities, as well as the evidence base for ECA applications in clinical psychology, to inform health professionals about the activity in this field of research. Methods: Given the large variety of applied methodologies, types of applications, and scientific disciplines involved in ECA research, we conducted a systematic scoping review. Scoping reviews aim to map key concepts and types of evidence underlying an area of research, and answer less-specific questions than traditional systematic reviews. Systematic searches for ECA applications in the treatment of mood, anxiety, psychotic, autism spectrum, and substance use disorders were conducted in databases in the fields of psychology and computer science, as well as in interdisciplinary databases. Studies were included if they conveyed primary research findings on an ECA application that targeted one of the disorders. We mapped each study's background information, how the different disorders were addressed, how ECAs and users could interact with one another, methodological aspects, and the study's aims and outcomes. Results: This study included N=54 publications (N=49 studies). More than half of the studies (n=26) focused on autism treatment, and ECAs were used most often for social skills training (n=23). Applications ranged from simple reinforcement of social behaviors through emotional expressions to sophisticated multimodal conversational systems. Most applications (n=43) were still in the development and piloting phase, that is, not yet ready for routine practice evaluation or application. Few studies conducted controlled research into clinical effects of ECAs, such as a reduction in symptom severity. Conclusions: ECAs for mental disorders are emerging. State-of-the-art techniques, involving, for example, communication through natural language or nonverbal behavior, are increasingly being considered and adopted for psychotherapeutic interventions in ECA research with promising results. However, evidence on their clinical application remains scarce. At present, their value to clinical practice lies mostly in the experimental determination of critical human support factors. In the context of using ECAs as an adjunct to existing interventions with the aim of supporting users, important questions remain with regard to the personalization of ECAs' interaction with users, and the optimal timing and manner of providing support. To increase the evidence base with regard to Internet interventions, we propose an additional focus on low-tech ECA solutions that can be rapidly developed, tested, and applied in routine practice. ", doi="10.2196/jmir.6553", url="http://www.jmir.org/2017/5/e151/", url="https://doi.org/10.2196/jmir.6553", url="http://www.ncbi.nlm.nih.gov/pubmed/28487267" } @Article{info:doi/10.2196/iproc.6099, author="Gardiner, Paula and Negash, N Lily and Shamekhi, Ameneh and Bickmore, Timothy and Gergen-Barnett, Katherine and Lestoquoy, Anna Sophia and Stillman, Sarah", title="Utilization of an Embodied Conversational Agent in an Integrative Medical Group Visit for Patients with Chronic Pain and Depression", journal="iproc", year="2016", month="Dec", day="09", volume="2", number="1", pages="e6", keywords="integrative medicine; embodied conversational agent; group visits", abstract="Background: This abstract will report on the feasibility of introducing an innovative eHealth technology called an Embodied Conversational Agent (ECA) into a diverse patient population with chronic pain and depression. Objective: The Integrative Medical Group Visit (IMGV) is a 9-week curriculum designed for patients with chronic pain and depression. The IMGV consists of 9 weekly group medical visits during which patients learn self-management for chronic pain and depression. Tablet computers with an ECA are given to each participant to reinforce the curriculum and self-care practices. The ECA reviews material covered in IMGV sessions and allows for participants to set healthy nutritional, exercise, and mindfulness goals. This clinical trial is ongoing across 3 sites in Boston, MA. Methods: Patients were recruited from Boston Medical Center, Codman Square Community Health Center, and DotHouse Health. Demographic characteristics collected include age, gender, race, ethnicity, and sexual orientation. Patients in the intervention were given a Dell tablet with an ECA for the duration of the study and were encouraged to interact with the ECA on a regular basis. The ECA reviewed material covered during group medical visits and served as a tool for participants to practice self-management and stress reduction techniques. Usage data were collected from the tablets at 9-weeks and at 21-weeks post enrollment. Results: In total, 75 patients were enrolled in the intervention. The majority of patients were female (83{\%}), 60{\%} identified as black/African American, and nearly 90{\%} identified as non-Hispanic. The mean age in this sample was 50 years old. Approximately half of patients reported regular computer use prior to the study (56{\%}). For this abstract, usage data and pain and depression outcomes are reported on. Patterns of utilization will be assessed from tablet usage data. This data will be used to assess potential associations between demographic data, amount of time spent using ECA, and content delivered by ECA. Conclusions: ECAs may represent one strategy to encourage patient use of self-management for pain and depression. ClinicalTrial: Clinicaltrials.gov NCT02262377; https://clinicaltrials.gov/ct2/show/NCT02262377 (Archived by WebCite at http://www.webcitation.org/6maRgLIT7). ", doi="10.2196/iproc.6099", url="http://www.iproc.org/2016/1/e6/", url="https://doi.org/10.2196/iproc.6099" }