JMIR Publications

Recent Articles:

• 

  Artificial Intelligence

  Dec 12, 2025

  Stakeholder Criteria for Trust in Artificial Intelligence–Based Computer Perception Tools in Health Care: Qualitative Interview Study

  View Authors View Abstract

  Authors List:

  • Ansh Rai  
  • Meghan E Hurley  
  • John Herrington  
  • Eric A Storch  
  • Casey J Zampella  
  • Julia Parrish-Morris  
  • Anika Sonig  
  • Gabriel Lázaro-Muñoz  
  • Kristin Kostick-Quenet  

  Abstract:

  Background: Computer perception (CP) technologies hold significant promise for advancing precision mental health care systems, given their ability to leverage algorithmic analysis of continuous, passive sensing data from wearables and smartphones (eg, behavioral activity, geolocation, vocal features, and ambient environmental data) to infer clinically meaningful behavioral and physiological states. However, successful implementation critically depends on cultivating well-founded stakeholder trust. Objective: This study aims to investigate, across adolescents, caregivers, clinicians, and developers, the contingencies under which CP technologies are deemed trustworthy in health care. Methods: We conducted 80 semistructured interviews with a purposive sample of adolescents (n=20) diagnosed with autism, Tourette syndrome, anxiety, obsessive-compulsive disorder, or attention-deficit/hyperactivity disorder and their caregivers (n=20); practicing clinicians across psychiatry, psychology, and pediatrics (n=20); and CP system developers (n=20). Interview transcripts were coded by 2 independent coders and analyzed using multistage, inductive thematic content analysis to identify prominent themes. Results: Across stakeholder groups, 5 core criteria emerged as prerequisites for trust in CP outputs: (1) epistemic alignment—consistency between system outputs, personal experience, and existing diagnostic frameworks; (2) demonstrable rigor—training on representative data and validation in real-world contexts; (3) explainability—transparent communication of input variables, thresholds, and decision logic; (4) sensitivity to complexity—the capacity to accommodate heterogeneity and comorbidity in symptom expression; and (5) a nonsubstitutive role—technologies must augment, rather than supplant, clinical judgment. A novel and cautionary finding was that epistemic alignment—whether outputs affirmed participants’ preexisting beliefs, diagnostic expectations, or internal states—was a dominant factor in determining whether the tool was perceived as trustworthy. Participants also expressed relational trust, placing confidence in CP systems based on endorsements from respected peers, academic institutions, or regulatory agencies. However, both trust strategies raise significant concerns: confirmation bias may lead users to overvalue outputs that align with their assumptions, while surrogate trust may be misapplied in the absence of robust performance validation. Conclusions: This study advances empirical understanding of how trust is formed and calibrated around artificial intelligence–based CP technologies. While trust is commonly framed as a function of technical performance, our findings show that it is deeply shaped by cognitive heuristics, social relationships, and alignment with entrenched epistemologies. These dynamics can facilitate intuitive verification but may also constrain the transformative potential of CP systems by reinforcing existing beliefs. To address this, we recommend a dual strategy: (1) embedding CP tools within institutional frameworks that uphold rigorous validation, ethical oversight, and transparent design; and (2) providing clinicians with training and interface designs that support critical appraisal and minimize susceptibility to cognitive bias. Recalibrating trust to reflect actual system capacities—rather than familiarity or endorsement—is essential for ethically sound and clinically meaningful integration of CP technologies.

  • J Med Internet Res 2025;27(1):e78757

  • Choose one of the following formats:

  • Share this article:

    Or, copy the article link to your clipboard:

    Article URL

  • Citation

    • END

      for: Endnote

    • BibTeX

      for: BibDesk and LaTeX

    • RIS

      for: RefMan, Procite, Endnote, RefWorks

    Add this article to your Mendeley library Add this article to your CiteULike library Copy Citation to Clipboard

  • Metrics

    Discover Social Media mentions by hovering over the donut. Click the 'details' link for a full report.

• 

  eHealth Literacy / Digital Literacy

  Dec 12, 2025

  Support Strategies and Interventions for eHealth Inclusion: Scoping Review

  View Authors View Abstract

  Authors List:

  • Wieke E Bouwes  
  • Nynke D Scherpbier  
  • Eveline Hage  
  • Luc A R Tjalma  
  • Esther I Metting  

  Abstract:

  Background: Policymakers increasingly promote eHealth as a way to improve healthcare efficiency. However, digitalization risks excluding individuals and groups who cannot fully engage with eHealth—for example, due to limited digital literacy or restricted access to resources. Targeted support, such as skills training, personalized guidance, or system-level initiatives, may help, but evidence on how such support is organized and whether it is effective remains limited. Objective: This scoping review aimed to map proposed strategies to promote eHealth inclusion, identify concrete support interventions, and report evidence on their outcomes Methods: This scoping review followed Arksey and O’Malley’s framework and the PRISMA-ScR guidelines. We searched PubMed, Scopus, Web of Science, and Embase for peer-reviewed studies published from 2014 onwards. We included empirical studies reporting on support to enhance eHealth inclusion. In total, 40 studies met the criteria: 19 examined support strategies and 21 evaluated targeted interventions. Strategies and interventions were categorized by actors at the micro level (interpersonal, such as family members, friends, or peers), meso level (organizations, such as healthcare organizations or community organizations), and macro level (policy or system). Results: Support strategies and interventions addressed a range of eHealth types, including video consultations, mobile health applications, and patient portals. Strategy studies often emphasized interpersonal support from family, friends, or peers, whereas interventions more often involved healthcare providers. Intervention outcomes, as identified during analysis, were grouped into adoption, use, skills, and attitudes. Adoption-focused interventions led by healthcare organizations showed limited effectiveness. Interventions targeting use partly demonstrated positive effects, such as increased completion of video visits, whereas outcomes related to attitudes were mixed. Nearly all multi-actor interventions—combining efforts across micro, meso, and macro levels—effectively improved eHealth skills, including digital and eHealth literacy. Examples include programs linking healthcare providers with community organizations, and initiatives pairing students with older adults, both of which improved these skills. Regional differences were also observed: healthcare providers played a dominant role in studies from the United States, community organizations were more prominent in African contexts, and multi-actor approaches were common in European studies. Conclusions: Overall, interventions yielded mixed results, but multi-actor collaborations frequently improved eHealth skills. These findings underscore the value of combining interpersonal, organizational, and policy-level efforts when designing support structures. For healthcare organizations, initiatives led solely by healthcare actors may suffice for promoting the use of specific applications (such as video consultations), but they seem insufficient for fostering broader eHealth literacy. Future research should address the sustainability and scalability of multi-actor interventions and how health system contexts and cultural factors shape their outcomes. Clinical Trial: Open Science Framework (OSF) 0.17605/OSF.IO/YRWFD; https://osf.io/6qmcj/overview

  • J Med Internet Res 2025;27(1):e79760

  • Choose one of the following formats:

  • Share this article:

    Or, copy the article link to your clipboard:

    Article URL

  • Citation

    • END

      for: Endnote

    • BibTeX

      for: BibDesk and LaTeX

    • RIS

      for: RefMan, Procite, Endnote, RefWorks

    Add this article to your Mendeley library Add this article to your CiteULike library Copy Citation to Clipboard

  • Metrics

    Discover Social Media mentions by hovering over the donut. Click the 'details' link for a full report.

• 

  New Methods

  Dec 12, 2025

  Lumbar Acceleration Gait Estimation: “Step-by-Step” Algorithm Updates and Improvements

  View Authors View Abstract

  Authors List:

  • Lukas Adamowicz  
  • Wenyi Lin  
  • F Isik Karahanoglu  
  • Xuemei Cai  
  • Mar Santamaria  
  • Charmaine Demanuele  
  • Junrui Di  

  Abstract:

  Background: Digital health technologies, such as accelerometry, offer low participant burden and provide quantitative metrics with ease of deployment, making them increasingly popular for gait monitoring. Remote gait monitoring delivers quantifiable, continuous health measures over extended periods, surpassing the limited insights from single clinic or laboratory visits and offering a more comprehensive health perspective. Numerous gait algorithm implementations, inspired by prior research, aim to standardize these metrics across devices. The SciKit Digital Health (SKDH) package exemplifies this as a device-agnostic framework. Objective: This study introduces a series of literature-informed enhancements to the SKDH gait algorithm, improving its performance against reference standards and reducing the need for manual parameter adjustments across diverse populations. Methods: A block-wise refinement process was undertaken, examining each algorithmic component for potential enhancements and evaluating their cumulative impact on the complete gait algorithm and the metrics generated. Results: Using data from healthy adult and pediatric participants, the novel gait event estimation method reduced the mean absolute error by more than 50% compared with its predecessor. Following the updates, the intraclass correlation values for final gait metric concordance with the in-laboratory reference improved markedly, from 0.50-0.74 to 0.81-0.90. Additionally, the systematic bias observed in the previous version’s gait speed estimation was rectified, narrowing the difference from the reference from 0.065-0.230 to 0.00-0.03 m/s. Conclusions: The findings from this study provide robust evidence supporting the validity of the enhancements made to the gait algorithm. They demonstrate that a single lumbar accelerometer can capture gait characteristics with high accuracy and reliability across various speeds and age groups.

  • J Med Internet Res 2025;27(1):e72831

  • Choose one of the following formats:

  • Share this article:

    Or, copy the article link to your clipboard:

    Article URL

  • Citation

    • END

      for: Endnote

    • BibTeX

      for: BibDesk and LaTeX

    • RIS

      for: RefMan, Procite, Endnote, RefWorks

    Add this article to your Mendeley library Add this article to your CiteULike library Copy Citation to Clipboard

  • Metrics

    Discover Social Media mentions by hovering over the donut. Click the 'details' link for a full report.

• 

  Artificial Intelligence

  Dec 11, 2025

  Factors Influencing Adoption of Large Language Models in Health Care: Multicenter Cross-Sectional Mixed Methods Observational Study

  View Authors View Abstract

  Authors List:

  • Xiongwen Yang  
  • Yi Xiao  
  • Di Liu  
  • Huiyin Deng  
  • Jian Huang  
  • Yubin Zhou  
  • Maoli Liang  
  • Longyan Dong  
  • Zihao Yuan  
  • Jing Yao  
  • Wankai Guo  
  • Chuan Xu  

  Abstract:

  Background: Background: Large language models (LLMs) such as ChatGPT are rapidly reshaping information management in health care by transforming how knowledge is accessed, communicated, and applied. However, their adoption in sensitive domains raises unresolved concerns regarding trust, privacy, and equity, especially in low- and middle-income countries with varying levels of digital readiness and institutional safeguards. Objective: Objective: This study aimed to examine the factors influencing adoption intent of LLMs among health care professionals (HCPs) and patients/caregivers (PCs) in China, with particular focus on trust, information behavior, and socio-technical readiness. Methods: Methods: We conducted a multicenter mixed-methods study across five tertiary hospitals, surveying 240 HCPs and 480 PCs and conducting semi-structured interviews with 30 participants. Quantitative analyses included logistic regression, random forest, and XGBoost models, supplemented with SHAP-based interpretability. Qualitative data were analyzed thematically to identify role-specific expectations and concerns. Results: Results: Trust, perceived usefulness, and digital readiness emerged as the strongest facilitators of LLM adoption, while privacy concerns, limited literacy, and socioeconomic disadvantage were significant barriers. Predictive models achieved strong performance (AUC = 0.83–0.96), with trust consistently identified as the central predictor across user groups. Qualitative findings highlighted distinct perspectives: HCPs emphasized workflow integration and accountability, whereas PCs prioritized plain-language comprehensibility and emotional reassurance. Conclusions: Conclusions: LLM adoption in health care depends less on technical performance than on managing trust, information behaviors, and socio-technical contexts. These findings extend information management theory by positioning socio-technical readiness as a critical construct and highlight that trust and ethical concerns outweigh demographic factors. Practically, the study points to the need for trust-centered, role-sensitive system design, inclusive digital literacy strategies, and governance frameworks that promote accountability and equitable participation.

  • J Med Internet Res 2025;27(1):e84918

  • Choose one of the following formats:

  • Share this article:

    Or, copy the article link to your clipboard:

    Article URL

  • Citation

    • END

      for: Endnote

    • BibTeX

      for: BibDesk and LaTeX

    • RIS

      for: RefMan, Procite, Endnote, RefWorks

    Add this article to your Mendeley library Add this article to your CiteULike library Copy Citation to Clipboard

  • Metrics

    Discover Social Media mentions by hovering over the donut. Click the 'details' link for a full report.

• 

  Digital Health Reviews

  Dec 11, 2025

  Digital Biomarkers of Cytokine Release Syndrome: Scoping Review and Ontology Development of the Role and Relevance of Digital Measures Using a Mixed Methods...

  View Authors View Abstract

  Authors List:

  • Christopher J Medberry  
  • Charlotte Zoe Angel  
  • Ashita S Batavia  
  • Sarah Bradley  
  • Nunzio Camerlingo  
  • Melinda Chen  
  • Mohamed Datoo  
  • Premal Kamdar  
  • Erik Koenig  
  • Lieke Kusters  
  • Celine Marquez  
  • Ujwani Nukala  
  • Michael Pettinati  
  • Ruth Phillips  
  • Daniel P Sanchez  
  • Nazila Shafagati  
  • Jenifer Siegelman  
  • Mark Stewart  
  • Cindy Varga  
  • Benjamin Vandendriessche  
  • Matt Wilkes  
  • Dana L Wolff-Hughes  
  • David Zahavi  
  • Sylvain Zorman  
  • Samantha J McClenahan  

  Abstract:

  Background: Advancements in cancer-targeted immunotherapies have transformed care, yet these therapies present a high likelihood of cytokine release syndrome (CRS), a potentially severe immune-related adverse event. The ability to identify CRS earlier could improve care by mitigating risks, widening patient access and reducing the burden on patients, caregivers, and healthcare providers. Digital health technologies (DHTs) are promising for early CRS detection by enabling continuous measurement of vital signs before symptoms are detected through standard intermittent clinical assessments. While the number of studies is increasing, inconsistencies in the symptoms and measures strongly associated with CRS highlight the need for a comprehensive review to identify the most reliable and commonly reported indicators. Despite this growing body of research, reliable predictive and diagnostic measures for early warning for CRS following the administration of immunotherapy have yet to be established. Objective: This scoping review aims to address this gap by developing an ontology of early warning signs for CRS – a structured model defining measurement concepts, properties, and interrelationships – for advancing early warning models for CRS. Methods: We conducted a mixed methods study including a scoping literature review, surveys, and interviews. The literature review searched PubMed and Embase (last searched 03/19/2024) for articles reporting measures collected between therapy administration and CRS onset and linked to CRS onset. Studies were limited to publications between January 2014 and March 2024 excluding those that did not assess an immunotherapy-based treatment, were not conducted in humans, did not compare collected measures to CRS diagnosed using standard of care, or were not available in English. Identified measures were further assessed through surveys and interviews with subject matter experts (n=22) and key opinion leaders (n=8), and analyzed using qualitative and quantitative methods. Results: Thirty studies met eligibility criteria and employed a variety of grading scales and threshold for severe CRS. A comprehensive ontology of early warning signs for CRS that includes physiological signs, clinical symptoms, and laboratory markers was developed. Within the full ontology, a common set of early warning signs for CRS - temperature, heart rate, blood pressure, and oxygen saturation - was identified as the minimally necessary data to evaluate for their predictive value for CRS. Three of these four signs align with the American Society for Transplantation and Cellular Therapy criteria for CRS grading and other clinical grading scales for CRS. Conclusions: Standardization and adoption of the ontology of early warning signs for CRS will streamline data collection to support the creation of robust, fit-for-purpose datasets. This approach ensures practical and informative data collection, ultimately enhancing the ability to predict and manage CRS effectively. Developing predictive models based on these early warning signs can enhance CRS risk assessment, support decentralized trials, and improve access to cancer-targeted immunotherapies.

  • J Med Internet Res 2025;27(1):e71956

  • Choose one of the following formats:

  • Share this article:

    Or, copy the article link to your clipboard:

    Article URL

  • Citation

    • END

      for: Endnote

    • BibTeX

      for: BibDesk and LaTeX

    • RIS

      for: RefMan, Procite, Endnote, RefWorks

    Add this article to your Mendeley library Add this article to your CiteULike library Copy Citation to Clipboard

  • Metrics

    Discover Social Media mentions by hovering over the donut. Click the 'details' link for a full report.

• 

  Digital Health Reviews

  Dec 10, 2025

  Development of a Hospital-at-Home Digital Twin for Patients With Frailty: Scoping Review

  View Authors View Abstract

  Authors List:

  • Faiza Yahya  
  • Matthew Cooper  
  • Wahib Saif  
  • Mohamad Kassem  
  • Hamde Nazar  

  Abstract:

  Background: Increasing demand on healthcare systems requires innovative and transformative solutions to deliver efficient, high-quality care. One promising approach is Digital Twin (DT) technology, which leverages real time data to create dynamic virtual representations of a physical entity (individuals or space) to anticipate future scenarios and support care decisions. While DTs have been explored in various sectors, their application in Hospital at Home (HaH), which delivers acute level care in home environments, remains unexplored. Objective: This review bridges a critical knowledge gap and examines the existing evidence on DT-enabling tools for managing patients with frailty in home settings. This will identify the underpinning architectural components required to inform a HaH-DT system which can support clinical decision-making. Methods: Six electronic databases (Embase, MEDLINE, Cochrane CENTRAL, CINAHL, Web of Science and Scopus) were searched, along with grey literature, to identifying primary studies published in English, between January 2019 and September 2025. Included studies had to report on the monitoring or management of patients with frailty within their own home, and information was charted on a pre-defined data collection form to answer the research objectives. Review articles, protocols, and conference abstracts were excluded. Results: Sixty-nine reports were included, of which 54% (n=37) used quantitative approaches, and 36% (n=25) were pilot or feasibility studies. Reports were analysed for DT-enabling tools and systematically mapped across the proposed five-layered DT architecture: sensing, communication, storage, analytics, and visualisation. Taxonomies of DT layers, their interconnections, and the classifications of the types of data collected (e.g., about the patient, the home environment, the use of medical equipment) are presented. This evidence identifies DT-enabling tools used for a variety of functions and a range of sensing technologies that exist (e.g., passive sensing via wearables, active physiological sensors, ambient sensors to detect motion/environmental changes). The most prevalent modes of communication were wireless and network-based (n=36), with the majority using Bluetooth (n=12). This review highlights better understanding of data management, in particular secure storage, is required within local healthcare systems. The emerging potential of predictive and prescriptive analytics, which can enable clinicians to predict risk, support clinical decision-making, or activate alert-triggered health interventions were mapped. Existing evidence suggests analytics methods are currently largely descriptive with a lack of advanced methods such as prescriptive analytics to enable recommendations of an optimal course of action, and the absence of diagnostic analytics which can highlight why a situation has occurred. Reported DT-enabling tools demonstrate patient-centered benefits, including enhanced motivation, reassurance, and personalised care. However, concerns persist regarding device accuracy, user acceptability, and implications for carers and organisational workflows. Conclusions: This review is among the first to systematically map DT-enabling tools to inform a potential HaH-DT in patients with frailty and organised by a 5-layered conceptual model. Understanding these architectural layers provides the foundations to enable stakeholders advance research and development in areas where there are knowledge gaps and consider how a HaH DT can effectively operate within current healthcare systems. By leveraging technology-enabled care in complex home-based settings, there is great potential to deliver safer, personalised and timely care.

  • J Med Internet Res 2025;27(1):e81510

  • Choose one of the following formats:

  • Share this article:

    Or, copy the article link to your clipboard:

    Article URL

  • Citation

    • END

      for: Endnote

    • BibTeX

      for: BibDesk and LaTeX

    • RIS

      for: RefMan, Procite, Endnote, RefWorks

    Add this article to your Mendeley library Add this article to your CiteULike library Copy Citation to Clipboard

  • Metrics

    Discover Social Media mentions by hovering over the donut. Click the 'details' link for a full report.

• 

  Viewpoints and Perspectives

  Dec 10, 2025

  Ethical Considerations for the Use of Social Media in the Human Subjects Research Setting

  View Authors View Abstract

  Authors List:

  • Tara Coffin  

  Abstract:

  The integration of social media into human subjects research offers significant opportunities for data collection, disease surveillance, and participant recruitment. However, it also poses a number of ethical challenges. This article evaluates the dual nature of social media as a research tool, highlighting its potential benefits while also addressing concerns about exacerbating health disparities, compromising participant privacy and confidentiality, and perpetuating discriminatory practices. By exploring issues related to equity and privacy, this article discusses the implications of digital recruitment and online behavioral advertising, underscoring the vital role of Institutional Review Boards (IRBs) in ensuring ethical standards are upheld. Furthermore, this work proposes key strategies for researchers and regulatory authorities, emphasizing community engagement and inclusive recruitment practices. The analysis aims to guide stakeholders in navigating the ethical complexities of digital research, fostering transparency, trust, and accountability in the realm of human subjects research.

  • J Med Internet Res 2025;27(1):e78183

  • Choose one of the following formats:

  • Share this article:

    Or, copy the article link to your clipboard:

    Article URL

  • Citation

    • END

      for: Endnote

    • BibTeX

      for: BibDesk and LaTeX

    • RIS

      for: RefMan, Procite, Endnote, RefWorks

    Add this article to your Mendeley library Add this article to your CiteULike library Copy Citation to Clipboard

  • Metrics

    Discover Social Media mentions by hovering over the donut. Click the 'details' link for a full report.

• 

  Web-based and Mobile Health...

  Dec 10, 2025

  Development and Validation of a Web-Based Machine Learning Model for Predicting Early Neurological Deterioration Following Stroke Thrombolysis: Multicenter...

  View Authors View Abstract

  Authors List:

  • Juan Li  
  • Huanxian Chang  
  • Shouyun Du  
  • Chunyang Zhang  
  • Han Zhang  
  • Luming Li  
  • Lingsheng Kong  
  • Guodong Li  
  • Tingting Liang  
  • Ronghong Yang  
  • Bingchao Xu  
  • Xinyu Zhou  
  • Guanghui Zhang  
  • Yongan Sun  
  • Xiaobing He  
  • Bei Xu  
  • Zaipo Li  
  • Yanan He  
  • Mingli He  

  Abstract:

  Background: Early neurological deterioration (END) significantly worsens outcomes in acute ischemic stroke (AIS) patients receiving intravenous thrombolysis (IVT), yet clinicians lack reliable tools to identify high-risk patients who need intensified monitoring and preemptive interventions. Objective: To develop and validate a high-performance machine learning model for END prediction that enables personalized risk-stratified management of AIS patients after thrombolysis. Methods: This multicenter study analyzed 1,927 IVT-treated AIS patients from three hospitals, comprising a development cohort (n=1,361) from Lianyungang Clinical Medical College and an external validation cohort (n=566) from two independent hospitals. We systematically evaluated 27 clinical parameters using multiple machine learning algorithms to develop ENDRAS, a prediction model based on six readily available clinical variables. Model performance was assessed through comprehensive metrics (AUC, accuracy, precision, recall, F1-score) in both internal and external validation cohorts. Results: The XGBoost-based Early Neurological Deterioration Risk Assessment Score (ENDRAS) showed promising predictive performance (AUC=0.988，95% CI：0.983-0.993) using six readily available parameters: TOAST classification, intracranial artery stenosis severity, NIHSS score, systolic blood pressure, neutrophil count, and red blood cell distribution width. We established a dual-pathway management protocol stratifying patients into low-risk (<29%) and high-risk (≥29%) groups, where high-risk patients receive intensive monitoring with hourly assessments and expedited imaging, while low-risk patients follow a resource-optimized protocol without compromising safety. Implemented as a web-based calculator with <0.02-second computation time, ENDRAS enables real-time clinical decision support at the point of care. Conclusions: ENDRAS integrates END prediction into actionable clinical pathways, potentially improving post-thrombolysis care through personalized monitoring strategies and targeted interventions. Its robust performance in merged cohorts, efficient computation time, and structured management framework address key challenges in stroke care while enhancing resource utilization. Further prospective validation across diverse populations is needed to fully establish ENDRAS as a standard clinical decision-support system, but its ability to identify high-risk patients early may significantly improve outcomes in acute ischemic stroke. Clinical Trial: China Clinical Trial Registry ChiCTR2400085504;

  • J Med Internet Res 2025;27(1):e77858

  • Choose one of the following formats:

  • Share this article:

    Or, copy the article link to your clipboard:

    Article URL

  • Citation

    • END

      for: Endnote

    • BibTeX

      for: BibDesk and LaTeX

    • RIS

      for: RefMan, Procite, Endnote, RefWorks

    Add this article to your Mendeley library Add this article to your CiteULike library Copy Citation to Clipboard

  • Metrics

    Discover Social Media mentions by hovering over the donut. Click the 'details' link for a full report.

• 

  Clinical Information and Decision Making

  Dec 10, 2025

  Development and Validation of an Electronic Health Record–Based Algorithm for Identifying Patients With Long-Term Opioid Therapy: Cross-Sectional Study

  View Authors View Abstract

  Authors List:

  • Shu Huang  
  • Tianze Jiao  
  • Serena Jingchuan Guo  
  • Jill A Star  
  • Jie Xu  
  • Jiang Bian  
  • Debbie L Wilson  
  • Amie J Goodin  

  Abstract:

  Background: Health care providers must carefully monitor patients receiving long-term opioid therapy (LTOT) to minimize risks and maximize benefits. Yet, algorithms to support intervention during patient encounters are lacking, with accurate LTOT identification in routine care being the essential first step. Objective: This study aims to develop and validate an LTOT identification algorithm using electronic health record (EHR) data. Methods: In this cross-sectional study, we used 2016-2021 OneFlorida+ EHR data linked with Florida Medicaid claims to identify patients aged ≥18 years who received opioid prescriptions. The main outcome was the first LTOT episode in the algorithm development (2016-2018) and validation (2019-2021) periods. A Medicaid claims-based LTOT algorithm served as the reference standard, defined as ≥90 days of continuous opioid use with ≤15-day gaps. Given strong correlations among covariates, an elastic net regression model was applied to identify LTOT episodes in EHR data using patient characteristics, clinically relevant features, and medication use, and to evaluate the model’s classification performance. We randomly split the 2016-2018 cohort into development and internal validation datasets (2:1 ratio), stratified by LTOT incidence. External validation was performed using 2019-2021 data. Results: Among 64,206 eligible patients identified in 2016-2018 (mean age 35.7, SD 12.3 years; 51,421/64,206, 80.1% female), a total of 8899 (13.9%) had LTOT. Among 50,009 eligible patients identified in 2019-2021 (mean age 37.3, SD 12.5 years; 39,866/50,009, 79.7% female), a total of 6000 (12%) had LTOT. The model selected 29 out of 131 candidate features. Among 2967 individuals with LTOT in the 2016-2018 OneFlorida+ internal validation dataset, a total of 2176 (73.3%) individuals were identified in the top 3 deciles of risk scores. The model achieved a C-statistic of 0.83 (95% CI 0.82-0.84), with 73.4% (95% CI 71.8%-75%) sensitivity, 76.8% (95% CI 76.2%-77.4%) specificity, 33.8% (95% CI 33.1%-34.6%) precision, 76.3% (95% CI 75.8%-76.9%) accuracy, and an F₁-score of 0.46. In the 2019-2021 OneFlorida+ external validation dataset, a total of 75.5% (4527/6000) individuals were correctly captured in the top 3 risk subgroups. The model achieved a C-statistic of 0.83 (95% CI 0.83-0.84), with 78.8% (95% CI 77.8%-79.9%) sensitivity, 73.3% (95% CI 72.9%-73.7%) specificity, 28.7% (95% CI 28.3%-29.1%) precision, 73.9% (73.6%-74.3%) accuracy, and an F₁-score of 0.42. Conclusions: The EHR-based LTOT algorithm showed comparable accuracy to the claims-based reference and may support risk stratification and inform decision-making during clinical encounters.

  • J Med Internet Res 2025;27(1):e76999

  • Choose one of the following formats:

  • Share this article:

    Or, copy the article link to your clipboard:

    Article URL

  • Citation

    • END

      for: Endnote

    • BibTeX

      for: BibDesk and LaTeX

    • RIS

      for: RefMan, Procite, Endnote, RefWorks

    Add this article to your Mendeley library Add this article to your CiteULike library Copy Citation to Clipboard

  • Metrics

    Discover Social Media mentions by hovering over the donut. Click the 'details' link for a full report.

• 

  Digital Health Reviews

  Dec 9, 2025

  Data Visualization Support for Interdisciplinary Team Treatment Planning in Clinical Oncology: Scoping Review

  View Authors View Abstract

  Authors List:

  • Dominik Boehm  
  • Cosima Strantz  
  • Arsenij Ustjanzew  
  • Iryna Manuilova  
  • Alexander Scheiter  
  • Thomas Pauli  
  • Nicole Hechtel  
  • Niklas Reimer  
  • Jan Christoph  
  • Hauke Busch  
  • Thomas Ganslandt  
  • Philipp Unberath  

  Abstract:

  Background: Complex and expanding datasets in clinical oncology applications require flexible and interactive visualization of patient data to provide physicians and other medical professionals with maximum amount of information. In particular, interdisciplinary tumor conferences profit from customized tools to integrate, link, and visualize relevant data from all professions involved. Objective: Our objective was to identify and present currently available data visualization tools for tumor boards and related areas. We wanted to provide an overview of not only the digital tools currently used in tumor board settings but also of the data they include, their respective visualization solutions, and their integration into hospital processes. Methods: This scoping review was based on the scoping study framework by Arksey and O’Malley and attempted to answer the following research question: “What are the key features of data visualization solutions used in molecular and organ tumor boards, and how are these elements integrated and used within the clinical setting?” The following electronic databases were searched for articles: PubMed, Web of Science, and Scopus. Articles were deemed eligible if published in English in the last 10 years. Eligible articles were first deduplicated, followed by screening of titles and abstracts. Full-text screening was then conducted to decide on article selection. All included articles were analyzed using a data extraction template. The template included a variety of meta-information, as well as specific fields aiming to answer the research question. Results: The review process started with 2049 articles, of which 1014 (49.49%) were included in the title and abstract screening. A total of 5.47% (112/2049) of the publications were eligible for full-text screening, leading to 2.93% (60/2049) of the publications being eligible for final inclusion. They covered 49 distinct visualization tools and applications. We discovered a variety of innovative visualization solutions, most often driven by the complexity of omics data, represented in 96% (47/49) of the tools. Tables remained the most used tool for the visualization of data types described in the articles. Approximately one-third of the identified tools (16/49, 33%) were systematically evaluated in some form. For most discovered tools (37/49, 76%), there was no documentation of implementation into the clinical routine. A significant number of applications (21/49, 43%) were available through open-source access. Conclusions: There is a wide range of projects providing visualization solutions for tumor boards and clinical oncology applications. Among the few tools that have made their way into clinical routine settings, there are both commercial and academic solutions. While tables for a variety of data types remain the dominant visualization strategy, the complexity of omics data appears to be the driving force behind many visualization innovations in the domain of tumor boards. Trial Registration:

  • J Med Internet Res 2025;27(1):e69104

  • Choose one of the following formats:

  • Share this article:

    Or, copy the article link to your clipboard:

    Article URL

  • Citation

    • END

      for: Endnote

    • BibTeX

      for: BibDesk and LaTeX

    • RIS

      for: RefMan, Procite, Endnote, RefWorks

    Add this article to your Mendeley library Add this article to your CiteULike library Copy Citation to Clipboard

  • Metrics

    Discover Social Media mentions by hovering over the donut. Click the 'details' link for a full report.

• 

  Digital Health Reviews

  Dec 9, 2025

  Artificial Intelligence–Enabled Imaging for Predicting Preoperative Extraprostatic Extension in Prostate Cancer: Systematic Review and Meta-Analysis

  View Authors View Abstract

  Authors List:

  • Xin Zhang  
  • Yiting Qi  
  • Xi Wang  
  • Haowen Chen  
  • Jia Li  

  Abstract:

  Background: Artificial intelligence (AI) techniques, particularly those employing machine learning (ML) and deep learning (DL) to analyze multimodal imaging data, have shown considerable promise in enhancing preoperative prediction of extraprostatic extension (EPE). Objective: This meta-analysis explores the diagnostic performance of artificial intelligence-enabled imaging techniques versus radiologists for predicting preoperative EPE in prostate cancer (PCa). Methods: We conducted a systematic review of literature from PubMed, Embase, and Web of Science, following PRISMA-DTA guidelines. The included studies applied AI techniques to predict EPE using mpMRI and PSMA PET imaging. Sensitivity, specificity, and area under the curve (AUC) for both internal and external validation sets were extracted and combined using a bi-variate random-effects model. The quality of the included studies was assessed using the modified QUADAS-2 tool. Results: A total of 21 studies were analyzed. The mpMRI-based AI demonstrated a pooled sensitivity of 0.78, specificity of 0.76, and an AUC of 0.84, significantly outperforming traditional radiologists, whose pooled sensitivity for detecting EPE was 0.69, specificity was 0.72, and AUC was 0.76. Conversely, the PSMA PET-based AI showed a pooled sensitivity of 0.73, specificity of 0.61, and an AUC of 0.74, indicating moderate performance but no significant advantage over either mpMRI-based AI or radiologists. Conclusions: This study indicates that the mpMRI-based AI model has higher sensitivity and AUC values compared to radiologists. However, the PSMA PET-based AI shows no additional advantage in diagnostic performance for predicting preoperative EPE in prostate cancer, whether compared to mpMRI or human-interpreted PET. Limitations include the retrospective design and high heterogeneity which may introduce bias and affect generalizability. Larger, diverse cohorts are essential for confirming these findings and optimizing the integration of AI in clinical practice.

  • J Med Internet Res 2025;27(1):e80981

  • Choose one of the following formats:

  • Share this article:

    Or, copy the article link to your clipboard:

    Article URL

  • Citation

    • END

      for: Endnote

    • BibTeX

      for: BibDesk and LaTeX

    • RIS

      for: RefMan, Procite, Endnote, RefWorks

    Add this article to your Mendeley library Add this article to your CiteULike library Copy Citation to Clipboard

  • Metrics

    Discover Social Media mentions by hovering over the donut. Click the 'details' link for a full report.

• 

  Artificial Intelligence

  Dec 9, 2025

  Adoption of Machine Learning in US Hospital Electronic Health Record Systems: Retrospective Observational Study

  View Authors View Abstract

  Authors List:

  • Huang Huang  
  • Wei Lyu  
  • Md Mahmud Hasan  
  • Shannon H Houser  

  Abstract:

  Background: While machine learning (ML) technologies have shifted from development to real-world deployment over the past decade, U.S. healthcare providers and hospital administrators have increasingly embraced ML, particularly through its integration with electronic health record (EHR) systems. This evolving landscape underscores the need for empirical evidence on ML adoption and its determinants; however, the relationship between hospital characteristics and ML integration within EHR systems remains insufficiently explored. Objective: To examine the current state of ML adoption within EHR systems across U.S. general acute care hospitals and to identify hospital characteristics associated with ML implementation. Methods: We used linked data between the 2022-2023 American Hospital Association (AHA) Annual Survey and the 2023-2024 AHA Information Technology Supplement Survey. The sample includes 2,562 general and acute care hospitals in the U.S. with a total of 4,055 observations over two years. Applying inverse probability weighting to address non-response bias, we used descriptive statistics to assess ML adoption patterns and multivariate logistic regression models to identify hospital characteristics associated with ML adoption. Results: Overall, about 75% of hospitals had adopted ML functions within their EHR systems in 2023-2024, and the majority tend to adopt both clinical and operational ML functions simultaneously. The most commonly adopted individual functions were predicting inpatient risks and outpatient follow-up. ML model evaluation practices, while still limited overall, showed notable improvement. Multivariate regression estimates indicate that hospitals were more likely to adopt any ML if they were not-for-profit (4.4 percentage-points; 95% CI [0.6, 8.2]; P=.02), large hospitals (15 percentage-points; 95% CI [9.4, 21]; P<.001), operated in metropolitan areas (4.3 percentage-points; 95% CI [0.8, 7.8]; P=.02), contracted with leading EHR vendors (20.6 percentage-points; 95% CI [17.1, 24]; P<.001), and affiliated with a health system (26.8 percentage-points; 95% CI [22.4, 31.3]; P<.001). Similar patterns were observed for predicting the adoption of both clinical and operative ML. We also identified specific hospital characteristics associated with the adoption of individual ML functions. Conclusions: ML adoption in hospitals is influenced by organizational resources and strategic priorities, raising concerns about potential digital inequities. Limited quality control and evaluation practices highlight the need for stronger regulatory oversight and targeted support for under-resourced hospitals. As the integration of ML into EHR systems expands, disparities in both adoption and oversight become increasingly critical. To ensure equitable, safe, and effective implementation of ML technologies in healthcare, well-designed policies must address these gaps and promote inclusive innovation across all hospital settings.

  • J Med Internet Res 2025;27(1):e76126

  • Choose one of the following formats:

  • Share this article:

    Or, copy the article link to your clipboard:

    Article URL

  • Citation

    • END

      for: Endnote

    • BibTeX

      for: BibDesk and LaTeX

    • RIS

      for: RefMan, Procite, Endnote, RefWorks

    Add this article to your Mendeley library Add this article to your CiteULike library Copy Citation to Clipboard

  • Metrics

    Discover Social Media mentions by hovering over the donut. Click the 'details' link for a full report.