https://www.jmir.org/issue/feedJournal of Medical Internet Research2023-01-03T13:00:05-05:00JMIR Publicationseditor@jmir.orgOpen Journal Systems The leading peer-reviewed journal for digital medicine and health and health care in the internet age. https://www.jmir.org/2024/1/e52150/ Tanzania’s and Germany’s Digital Health Strategies and Their Consistency With the World Health Organization’s Global Strategy on Digital Health 2020-2025: Comparative Policy Analysis2024-03-18T11:31:08-04:00Felix HollJennifer KircherAttila J HertelendyFelix SukumsWalter Swoboda<strong>Background:</strong> In recent years, the fast-paced adoption of digital health (DH) technologies has transformed health care delivery. However, this rapid evolution has also led to challenges such as uncoordinated development and information silos, impeding effective health care integration. Recognizing these challenges, nations have developed digital health strategies (DHSs), aligning with their national health priorities and guidance from global frameworks. The World Health Organization (WHO)’s Global Strategy on Digital Health 2020-2025 (GSDH) guides national DHSs. <strong>Objective:</strong> This study analyzes the DHSs of Tanzania and Germany as case studies and assesses their alignment with the GSDH and identifies strengths, shortcomings, and areas for improvement. <strong>Methods:</strong> A comparative policy analysis was conducted, focusing on the DHSs of Tanzania and Germany as case studies, selected for their contrasting health care systems and cooperative history. The analysis involved a three-step process: (1) assessing consistency with the GSDH, (2) comparing similarities and differences, and (3) evaluating the incorporation of emergent technologies. Primary data sources included national eHealth policy documents and related legislation. <strong>Results:</strong> Both Germany’s and Tanzania’s DHSs align significantly with the WHO’s GSDH, incorporating most of its 35 elements, but each missing 5 distinct elements. Specifically, Tanzania’s DHS lacks in areas such as knowledge management and capacity building for leaders, while Germany’s strategy falls short in engaging health care service providers and beneficiaries in development phases and promoting health equity. Both countries, however, excel in other aspects like collaboration, knowledge transfer, and advancing national DHSs, reflecting their commitment to enhancing DH infrastructures. The high ratings of both countries on the Global Digital Health Monitor underscore their substantial progress in DH, although challenges persist in adopting the rapidly advancing technologies and in the need for more inclusive and comprehensive strategies. <strong>Conclusions:</strong> This study reveals that both Tanzania and Germany have made significant strides in aligning their DHSs with the WHO’s GSDH. However, the rapid evolution of technologies like artificial intelligence and machine learning presents challenges in keeping strategies up-to-date. This study recommends the development of more comprehensive, inclusive strategies and regular revisions to align with emerging technologies and needs. The research underscores the importance of context-specific adaptations in DHSs and highlights the need for broader, strategic guidelines to direct the future development of the DH ecosystem. The WHO’s GSDH serves as a crucial blueprint for national DHSs. This comparative analysis demonstrates the value and challenges of aligning national strategies with global guidelines. Both Tanzania and Germany offer valuable insights into developing and implementing effective DHSs, highlighting the importance of continuous adaptation and context-specific considerations. Future policy assessments require in-depth knowledge of the country’s health care needs and structure, supplemented by stakeholder input for a comprehensive evaluation. 2024-03-18T11:31:08-04:00 https://www.jmir.org/2024/1/e50369/ Development and Validation of an Interpretable Conformal Predictor to Predict Sepsis Mortality Risk: Retrospective Cohort Study2024-03-18T11:00:05-04:00Meicheng YangHui ChenWenhan HuMassimo MischiCaifeng ShanJianqing LiXi LongChengyu Liu<strong>Background:</strong> Early and reliable identification of patients with sepsis who are at high risk of mortality is important to improve clinical outcomes. However, 3 major barriers to artificial intelligence (AI) models, including the lack of interpretability, the difficulty in generalizability, and the risk of automation bias, hinder the widespread adoption of AI models for use in clinical practice. <strong>Objective:</strong> This study aimed to develop and validate (internally and externally) a conformal predictor of sepsis mortality risk in patients who are critically ill, leveraging AI-assisted prediction modeling. The proposed approach enables explaining the model output and assessing its confidence level. <strong>Methods:</strong> We retrospectively extracted data on adult patients with sepsis from a database collected in a teaching hospital at Beth Israel Deaconess Medical Center for model training and internal validation. A large multicenter critical care database from the Philips eICU Research Institute was used for external validation. A total of 103 clinical features were extracted from the first day after admission. We developed an AI model using gradient-boosting machines to predict the mortality risk of sepsis and used Mondrian conformal prediction to estimate the prediction uncertainty. The Shapley additive explanation method was used to explain the model. <strong>Results:</strong> A total of 16,746 (80%) patients from Beth Israel Deaconess Medical Center were used to train the model. When tested on the internal validation population of 4187 (20%) patients, the model achieved an area under the receiver operating characteristic curve of 0.858 (95% CI 0.845-0.871), which was reduced to 0.800 (95% CI 0.789-0.811) when externally validated on 10,362 patients from the Philips eICU database. At a specified confidence level of 90% for the internal validation cohort the percentage of error predictions (n=438) out of all predictions (n=4187) was 10.5%, with 1229 (29.4%) predictions requiring clinician review. In contrast, the AI model without conformal prediction made 1449 (34.6%) errors. When externally validated, more predictions (n=4004, 38.6%) were flagged for clinician review due to interdatabase heterogeneity. Nevertheless, the model still produced significantly lower error rates compared to the point predictions by AI (n=1221, 11.8% vs n=4540, 43.8%). The most important predictors identified in this predictive model were Acute Physiology Score III, age, urine output, vasopressors, and pulmonary infection. Clinically relevant risk factors contributing to a single patient were also examined to show how the risk arose. <strong>Conclusions:</strong> By combining model explanation and conformal prediction, AI-based systems can be better translated into medical practice for clinical decision-making. 2024-03-18T11:00:05-04:00 https://www.jmir.org/2024/1/e45070/ Outcomes and Costs of the Transition From a Paper-Based Immunization System to a Digital Immunization System in Vietnam: Mixed Methods Study2024-03-18T10:45:04-04:00Thi Thanh Huyen DangEmily CarnahanLinh NguyenMercy MvunduraSang DaoThi Hong DuongTrung NguyenDoan NguyenTu NguyenLaurie WernerTove K RymanNga Nguyen<strong>Background:</strong> The electronic National Immunization Information System (NIIS) was introduced nationwide in Vietnam in 2017. Health workers were expected to use the NIIS alongside the legacy paper-based system. Starting in 2018, Hanoi and Son La provinces transitioned to paperless reporting. Interventions to support this transition included data guidelines and training, internet-based data review meetings, and additional supportive supervision visits. <strong>Objective:</strong> This study aims to assess (1) changes in NIIS data quality and use, (2) changes in immunization program outcomes, and (3) the economic costs of using the NIIS versus the traditional paper system. <strong>Methods:</strong> This mixed methods study took place in Hanoi and Son La provinces. It aimed to analyses pre- and postintervention data from various sources including the NIIS; household and health facility surveys; and interviews to measure NIIS data quality, data use, and immunization program outcomes. Financial data were collected at the national, provincial, district, and health facility levels through record review and interviews. An activity-based costing approach was conducted from a health system perspective. <strong>Results:</strong> NIIS data timeliness significantly improved from pre- to postintervention in both provinces. For example, the mean number of days from birth date to NIIS registration before and after intervention dropped from 18.6 (SD 65.5) to 5.7 (SD 31.4) days in Hanoi (<i>P</i><.001) and from 36.1 (SD 94.2) to 11.7 (40.1) days in Son La (<i>P</i><.001). Data from Son La showed that the completeness and accuracy improved, while Hanoi exhibited mixed results, possibly influenced by the COVID-19 pandemic. Data use improved; at postintervention, 100% (667/667) of facilities in both provinces used NIIS data for activities beyond monthly reporting compared with 34.8% (202/580) in Hanoi and 29.4% (55/187) in Son La at preintervention. Across nearly all antigens, the percentage of children who received the vaccine on time was higher in the postintervention cohort compared with the preintervention cohort. Up-front costs associated with developing and deploying the NIIS were estimated at US $0.48 per child in the study provinces. The commune health center level showed cost savings from changing from the paper system to the NIIS, mainly driven by human resource time savings. At the administrative level, incremental costs resulted from changing from the paper system to the NIIS, as some costs increased, such as labor costs for supportive supervision and additional capital costs for equipment associated with the NIIS. <strong>Conclusions:</strong> The Hanoi and Son La provinces successfully transitioned to paperless reporting while maintaining or improving NIIS data quality and data use. However, improvements in data quality were not associated with improvements in the immunization program outcomes in both provinces. The COVID-19 pandemic likely had a negative influence on immunization program outcomes, particularly in Hanoi. These improvements entail up-front financial costs. 2024-03-18T10:45:04-04:00 https://www.jmir.org/2024/1/e50534/ Reducing Loneliness and Social Isolation of Older Adults Through Voice Assistants: Literature Review and Bibliometric Analysis2024-03-18T10:00:29-04:00Rachele Alessandra MarzialiClaudia FranceschettiAdrian DinculescuAlexandru NistorescuDominic Mircea KristályAdrian Alexandru MoșoiRonny BroekxMihaela MarinCristian VizitiuSorin-Aurel MoraruLorena RossiMirko Di Rosa<strong>Background:</strong> Loneliness and social isolation are major public health concerns for older adults, with severe mental and physical health consequences. New technologies may have a great impact in providing support to the daily lives of older adults and addressing the many challenges they face. In this scenario, technologies based on voice assistants (VAs) are of great interest and potential benefit in reducing loneliness and social isolation in this population, because they could overcome existing barriers with other digital technologies through easier and more natural human-computer interaction. <strong>Objective:</strong> This study aims to investigate the use of VAs to reduce loneliness and social isolation of older adults by performing a systematic literature review and a bibliometric cluster mapping analysis. <strong>Methods:</strong> We searched PubMed, Embase, and Scopus databases for articles that were published in the last 6 years, related to the following main topics: voice interface, VA, older adults, isolation, and loneliness. A total of 40 articles were found, of which 16 (40%) were included in this review. The included articles were then assessed through a qualitative scoring method and summarized. Finally, a bibliometric analysis was conducted using VOSviewer software (Leiden University’s Centre for Science and Technology Studies). <strong>Results:</strong> Of the 16 articles included in the review, only 2 (13%) were considered of poor methodological quality, whereas 9 (56%) were of medium quality and 5 (31%) were of high quality. Finally, through bibliometric analysis, 221 keywords were extracted, of which 36 (16%) were selected. The most important keywords, by number of occurrences and by total link strength; results of the analysis with the Association Strength normalization method; and default values were then presented. The final bibliometric network consisted of 36 selected keywords, which were grouped into 3 clusters related to 3 main topics (ie, VA use for social isolation among older adults, the significance of age in the context of loneliness, and the impact of sex factors on well-being). For most of the selected articles, the effect of VA on social isolation and loneliness of older adults was a minor theme. However, more investigations were done on user experience, obtaining preliminary positive results. <strong>Conclusions:</strong> Most articles on the use of VAs by older adults to reduce social isolation and loneliness focus on usability, acceptability, or user experience. Nevertheless, studies directly addressing the impact that using a VA has on the social isolation and loneliness of older adults find positive and promising results and provide important information for future research, interventions, and policy development in the field of geriatric care and technology. 2024-03-18T10:00:29-04:00 https://www.jmir.org/2024/1/e48504/ The EMPOWER Occupational e–Mental Health Intervention Implementation Checklist to Foster e–Mental Health Interventions in the Workplace: Development Study2024-03-15T10:30:04-04:00Alberto RaggiRenaldo M BernardClaudia ToppoCarla SabariegoLuis Salvador CarullaSue LukersmithLeona Hakkaart-van RoijenDorota Merecz-KotBeatriz OlayaRodrigo Antunes LimaDesirée Gutiérrez-MarínEllen VorstenboschChiara CuratoliMartina Cacciatore<strong>Background:</strong> Occupational e–mental health (OeMH) interventions significantly reduce the burden of mental health conditions. The successful implementation of OeMH interventions is influenced by many implementation strategies, barriers, and facilitators across contexts, which, however, are not systematically tracked. One of the reasons is that international consensus on documenting and reporting the implementation of OeMH interventions is lacking. There is a need for practical guidance on the key factors influencing the implementation of interventions that organizations should consider. Stakeholder consultations secure a valuable source of information about these key strategies, barriers, and facilitators that are relevant to successful implementation of OeMH interventions. <strong>Objective:</strong> The objective of this study was to develop a brief checklist to guide the implementation of OeMH interventions. <strong>Methods:</strong> Based on the results of a recently published systematic review, we drafted a comprehensive checklist with a wide set of strategies, barriers, and facilitators that were identified as relevant for the implementation of OeMH interventions. We then used a 2-stage stakeholder consultation process to refine the draft checklist to a brief and practical checklist comprising key implementation factors. In the first stage, stakeholders evaluated the relevance and feasibility of items on the draft checklist using a web-based survey. The list of items comprised 12 facilitators presented as statements addressing “elements that positively affect implementation” and 17 barriers presented as statements addressing “concerns toward implementation.” If a strategy was deemed relevant, respondents were asked to rate it using a 4-point Likert scale ranging from “very difficult to implement” to “very easy to implement.” In the second stage, stakeholders were interviewed to elaborate on the most relevant barriers and facilitators shortlisted from the first stage. The interview mostly focused on the relevance and priority of strategies and factors affecting OeMH intervention implementation. In the interview, the stakeholders’ responses to the open survey’s questions were further explored. The final checklist included strategies ranked as relevant and feasible and the most relevant facilitators and barriers, which were endorsed during either the survey or the interviews. <strong>Results:</strong> In total, 26 stakeholders completed the web-based survey (response rate=24.8%) and 4 stakeholders participated in individual interviews. The OeMH intervention implementation checklist comprised 28 items, including 9 (32.1%) strategies, 8 (28.6%) barriers, and 11 (39.3%) facilitators. There was widespread agreement between findings from the survey and interviews, the most outstanding exception being the idea of proposing OeMH interventions as benefits for employees. <strong>Conclusions:</strong> Through our 2-stage stakeholder consultation, we developed a brief checklist that provides organizations with a guide for the implementation of OeMH interventions. Future research should empirically validate the effectiveness and usefulness of the checklist. 2024-03-15T10:30:04-04:00 https://www.jmir.org/2024/1/e47923/ Methods and Annotated Data Sets Used to Predict the Gender and Age of Twitter Users: Scoping Review2024-03-15T10:15:04-04:00Karen O'ConnorSu GolderDavy WeissenbacherAri Z KleinArjun MaggeGraciela Gonzalez-Hernandez<strong>Background:</strong> Patient health data collected from a variety of nontraditional resources, commonly referred to as <i>real-world data</i>, can be a key information source for health and social science research. Social media platforms, such as Twitter (Twitter, Inc), offer vast amounts of real-world data. An important aspect of incorporating social media data in scientific research is identifying the demographic characteristics of the users who posted those data. Age and gender are considered key demographics for assessing the representativeness of the sample and enable researchers to study subgroups and disparities effectively. However, deciphering the age and gender of social media users poses challenges. <strong>Objective:</strong> This scoping review aims to summarize the existing literature on the prediction of the age and gender of Twitter users and provide an overview of the methods used. <strong>Methods:</strong> We searched 15 electronic databases and carried out reference checking to identify relevant studies that met our inclusion criteria: studies that predicted the age or gender of Twitter users using computational methods. The screening process was performed independently by 2 researchers to ensure the accuracy and reliability of the included studies. <strong>Results:</strong> Of the initial 684 studies retrieved, 74 (10.8%) studies met our inclusion criteria. Among these 74 studies, 42 (57%) focused on predicting gender, 8 (11%) focused on predicting age, and 24 (32%) predicted a combination of both age and gender. Gender prediction was predominantly approached as a binary classification task, with the reported performance of the methods ranging from 0.58 to 0.96 <i>F</i><sub>1</sub>-score or 0.51 to 0.97 accuracy. Age prediction approaches varied in terms of classification groups, with a higher range of reported performance, ranging from 0.31 to 0.94 <i>F</i><sub>1</sub>-score or 0.43 to 0.86 accuracy. The heterogeneous nature of the studies and the reporting of dissimilar performance metrics made it challenging to quantitatively synthesize results and draw definitive conclusions. <strong>Conclusions:</strong> Our review found that although automated methods for predicting the age and gender of Twitter users have evolved to incorporate techniques such as deep neural networks, a significant proportion of the attempts rely on traditional machine learning methods, suggesting that there is potential to improve the performance of these tasks by using more advanced methods. Gender prediction has generally achieved a higher reported performance than age prediction. However, the lack of standardized reporting of performance metrics or standard annotated corpora to evaluate the methods used hinders any meaningful comparison of the approaches. Potential biases stemming from the collection and labeling of data used in the studies was identified as a problem, emphasizing the need for careful consideration and mitigation of biases in future studies. This scoping review provides valuable insights into the methods used for predicting the age and gender of Twitter users, along with the challenges and considerations associated with these methods. <strong>Trial Registration:</strong> 2024-03-15T10:15:04-04:00 https://www.jmir.org/2024/1/e49440/ Exploring the Types of Social Support Exchanged by Survivors of Pediatric Stroke and Their Families in an Online Peer Support Community: Qualitative Thematic Analysis2024-03-15T10:00:04-04:00William J A WrightCharlotte HowdleNeil S CoulsonAnna De Simoni<strong>Background:</strong> Pediatric stroke is relatively rare and underresearched, and there is little awareness of its occurrence in wider society. There is a paucity of literature on the effectiveness of interventions to improve rehabilitation and the services available to survivors. Access to online health communities through the internet may be a means of support for patients with pediatric stroke and their families during recovery; however, little research has been done in this area. <strong>Objective:</strong> This study aims to identify the types of social support provided by an online peer support group to survivors of pediatric stroke and their families. <strong>Methods:</strong> This was a qualitative thematic analysis of posts from a pediatric stroke population on a UK online stroke community active between 2004 and 2011. The population was split into 2 groups based on whether stroke survivors were aged ≤18 years or aged >18 years at the time of posting. The posts were read by 2 authors who used the adapted Social Support Behavior Code to analyze the types of social support exchanged. <strong>Results:</strong> A total of 52 participants who experienced a pediatric stroke were identified, who posted a total of 425 messages to the community. About 41 survivors were aged ≤18 years at the time of posting and were written about by others (31/35 were mothers), while 11 were aged >18 years and were writing about themselves. Survivors and their families joined together in discussion threads. Support was offered and received by all participants, regardless of age. Of all 425 posts, 193 (45.4%) contained at least 1 instance of social support. All 5 types of social support were identified: informational, emotional, network, esteem support, and tangible aid. Informational and emotional support were most commonly exchanged. Emotional support was offered more often than informational support among participants aged ≤18 years at the time of posting; this finding was reversed in the group aged >18 years. Network support and esteem support were less commonly exchanged. Notably, the access subcategory of network support was not exchanged with the community. Tangible aid was the least commonly offered type of support. The exchanged social support provided insight into rehabilitation interventions and the unmet needs of pediatric stroke survivors. <strong>Conclusions:</strong> We found evidence of engagement of childhood stroke survivors and their families in an online stroke community, with peer support being exchanged between both long- and short-term survivors of pediatric stroke. Engagement of long-term survivors of pediatric stroke through the online community was key, as they were able to offer informational support from lived experience. Further interventional research is needed to assess health and rehabilitation outcomes from engagement with online support groups. Research is also needed to ensure safe, nurturing online communities. <strong>Trial Registration:</strong> Not applicable 2024-03-15T10:00:04-04:00 https://www.jmir.org/2024/1/e50882/ Quality and Dependability of ChatGPT and DingXiangYuan Forums for Remote Orthopedic Consultations: Comparative Analysis2024-03-14T10:45:04-04:00Zhaowen XueYiming ZhangWenyi GanHuajun WangGuorong SheXiaofei Zheng<strong>Background:</strong> The widespread use of artificial intelligence, such as ChatGPT (OpenAI), is transforming sectors, including health care, while separate advancements of the internet have enabled platforms such as China’s DingXiangYuan to offer remote medical services. <strong>Objective:</strong> This study evaluates ChatGPT-4’s responses against those of professional health care providers in telemedicine, assessing artificial intelligence’s capability to support the surge in remote medical consultations and its impact on health care delivery. <strong>Methods:</strong> We sourced remote orthopedic consultations from “Doctor DingXiang,” with responses from its certified physicians as the control and ChatGPT’s responses as the experimental group. In all, 3 blindfolded, experienced orthopedic surgeons assessed responses against 7 criteria: “logical reasoning,” “internal information,” “external information,” “guiding function,” “therapeutic effect,” “medical knowledge popularization education,” and “overall satisfaction.” We used Fleiss κ to measure agreement among multiple raters. <strong>Results:</strong> Initially, consultation records for a cumulative count of 8 maladies (equivalent to 800 cases) were gathered. We ultimately included 73 consultation records by May 2023, following primary and rescreening, in which no communication records containing private information, images, or voice messages were transmitted. After statistical scoring, we discovered that ChatGPT’s “internal information” score (mean 4.61, SD 0.52 points vs mean 4.66, SD 0.49 points; <i>P</i>=.43) and “therapeutic effect” score (mean 4.43, SD 0.75 points vs mean 4.55, SD 0.62 points; <i>P</i>=.32) were lower than those of the control group, but the differences were not statistically significant. ChatGPT showed better performance with a higher “logical reasoning” score (mean 4.81, SD 0.36 points vs mean 4.75, SD 0.39 points; <i>P</i>=.38), “external information” score (mean 4.06, SD 0.72 points vs mean 3.92, SD 0.77 points; <i>P</i>=.25), and “guiding function” score (mean 4.73, SD 0.51 points vs mean 4.72, SD 0.54 points; <i>P</i>=.96), although the differences were not statistically significant. Meanwhile, the “medical knowledge popularization education” score of ChatGPT was better than that of the control group (mean 4.49, SD 0.67 points vs mean 3.87, SD 1.01 points; <i>P</i><.001), and the difference was statistically significant. In terms of “overall satisfaction,” the difference was not statistically significant between the groups (mean 8.35, SD 1.38 points vs mean 8.37, SD 1.24 points; <i>P</i>=.92). According to how Fleiss κ values were interpreted, 6 of the control group’s score points were classified as displaying “fair agreement” (<i>P</i><.001), and 1 was classified as showing “substantial agreement” (<i>P</i><.001). In the experimental group, 3 points were classified as indicating “fair agreement,” while 4 suggested “moderate agreement” (<i>P</i><.001). <strong>Conclusions:</strong> ChatGPT-4 matches the expertise found in DingXiangYuan forums’ paid consultations, excelling particularly in scientific education. It presents a promising alternative for remote health advice. For health care professionals, it could act as an aid in patient education, while patients may use it as a convenient tool for health inquiries. 2024-03-14T10:45:04-04:00 https://www.jmir.org/2024/1/e42904/ Validation of 3 Computer-Aided Facial Phenotyping Tools (DeepGestalt, GestaltMatcher, and D-Score): Comparative Diagnostic Accuracy Study2024-03-13T11:00:04-04:00Alisa Maria Vittoria ReiterJean Tori PantelMagdalena DanyelDenise HornClaus-Eric OttMartin Atta Mensah<strong>Background:</strong> While characteristic facial features provide important clues for finding the correct diagnosis in genetic syndromes, valid assessment can be challenging. The next-generation phenotyping algorithm DeepGestalt analyzes patient images and provides syndrome suggestions. GestaltMatcher matches patient images with similar facial features. The new D-Score provides a score for the degree of facial dysmorphism. <strong>Objective:</strong> We aimed to test state-of-the-art facial phenotyping tools by benchmarking GestaltMatcher and D-Score and comparing them to DeepGestalt. <strong>Methods:</strong> Using a retrospective sample of 4796 images of patients with 486 different genetic syndromes (London Medical Database, GestaltMatcher Database, and literature images) and 323 inconspicuous control images, we determined the clinical use of D-Score, GestaltMatcher, and DeepGestalt, evaluating sensitivity; specificity; accuracy; the number of supported diagnoses; and potential biases such as age, sex, and ethnicity. <strong>Results:</strong> DeepGestalt suggested 340 distinct syndromes and GestaltMatcher suggested 1128 syndromes. The top-30 sensitivity was higher for DeepGestalt (88%, SD 18%) than for GestaltMatcher (76%, SD 26%). DeepGestalt generally assigned lower scores but provided higher scores for patient images than for inconspicuous control images, thus allowing the 2 cohorts to be separated with an area under the receiver operating characteristic curve (AUROC) of 0.73. GestaltMatcher could not separate the 2 classes (AUROC 0.55). Trained for this purpose, D-Score achieved the highest discriminatory power (AUROC 0.86). D-Score’s levels increased with the age of the depicted individuals. Male individuals yielded higher D-scores than female individuals. Ethnicity did not appear to influence D-scores. <strong>Conclusions:</strong> If used with caution, algorithms such as D-score could help clinicians with constrained resources or limited experience in syndromology to decide whether a patient needs further genetic evaluation. Algorithms such as DeepGestalt could support diagnosing rather common genetic syndromes with facial abnormalities, whereas algorithms such as GestaltMatcher could suggest rare diagnoses that are unknown to the clinician in patients with a characteristic, dysmorphic face. 2024-03-13T11:00:04-04:00 https://www.jmir.org/2024/1/e50741/ Effects of a Social Media Intervention on Vaping Intentions: Randomized Dose-Response Experiment2024-03-12T10:30:03-04:00William Douglas EvansJeffrey BingenheimerJennifer CantrellJennifer KreslakeShreya TulsianiMegumi IchimiyaAlexander P D'EsterreRaquel GerardMadeline MartinElizabeth C Hair<strong>Background:</strong> e-Cigarette use, especially by young adults, is at unacceptably high levels and represents a public health risk factor. Digital media are increasingly being used to deliver antivaping campaigns, but little is known about their effectiveness or the dose-response effects of content delivery. <strong>Objective:</strong> The objectives of this study were to evaluate (1) the effectiveness of a 60-day antivaping social media intervention in changing vaping use intentions and beliefs related to the stimulus content and (2) the dose-response effects of varying levels of exposure to the intervention on vaping outcomes, including anti-industry beliefs, vaping intentions, and other attitudes and beliefs related to vaping. <strong>Methods:</strong> Participants were adults aged 18 to 24 years in the United States. They were recruited into the study through Facebook (Meta Platforms) and Instagram (Meta Platforms), completed a baseline survey, and then randomized to 1 of the 5 conditions: 0 (control), 4, 8, 16, and 32 exposures over a 15-day period between each survey wave. Follow-up data were collected 30 and 60 days after randomization. We conducted stratified analyses of the full sample and in subsamples defined by the baseline vaping status (never, former, and current). Stimulus was delivered through Facebook and Instagram in four 15-second social media videos focused on anti-industry beliefs about vaping. The main outcome measures reported in this study were self-reported exposure to social media intervention content, attitudes and beliefs about vaping, and vaping intentions. We estimated a series of multivariate linear regressions in Stata 17 (StataCorp). To capture the dose-response effect, we assigned each study arm a numerical value corresponding to the number of advertisements (exposures) delivered to participants in each arm and used this number as our focal independent variable. In each model, the predictor was the treatment arm to which each participant was assigned. <strong>Results:</strong> The baseline sample consisted of 1491 participants, and the final analysis sample consisted of 57.28% (854/1491) of the participants retained at the 60-day follow-up. We compared the retained participants with those lost to follow-up and found no statistically significant differences across demographic variables. We found a significant effect of the social media treatment on vaping intentions (β=−0.138, 95% CI −0.266 to −0.010; <i>P</i>=.04) and anti-industry beliefs (β=−0.122, 95% CI 0.008-0.237; <i>P</i>=.04) targeted by the intervention content among current vapers but not among the full sample or other strata. We found no significant effects of self-reported exposure to the stimulus. <strong>Conclusions:</strong> Social media interventions are a promising approach to preventing vaping among young adults. More research is needed on how to optimize the dosage of such interventions and the extent to which long-term exposure may affect vaping use over time. <strong>Trial Registration:</strong> ClinicalTrials.gov NCT04867668; https://clinicaltrials.gov/study/NCT04867668 2024-03-12T10:30:03-04:00