Journal of Medical Internet Research最新文献

{"title":"Early Prediction of Mortality Risk in Acute Respiratory Distress Syndrome: Systematic Review and Meta-Analysis.","authors":"Ruimin Tan, Chen Ge, Zhe Li, Yating Yan, He Guo, Wenjing Song, Qiong Zhu, Quansheng Du","doi":"10.2196/70537","DOIUrl":"10.2196/70537","url":null,"abstract":"<p><strong>Background: </strong>Acute respiratory distress syndrome (ARDS) is a life-threatening condition associated with high mortality rates. Despite advancements in critical care, reliable early prediction methods for ARDS-related mortality remain elusive. Accurate risk assessment is crucial for timely intervention and improved patient outcomes. Machine learning (ML) techniques have emerged as promising tools for mortality prediction in patients with ARDS, leveraging complex clinical datasets to identify key prognostic factors. However, the efficacy of ML-based models remains uncertain. This systematic review aims to assess the value of ML models in the early prediction of ARDS mortality risk and to provide evidence supporting the development of simplified, clinically applicable ML-based scoring tools for prognosis.</p><p><strong>Objective: </strong>This study systematically reviewed available literature on ML-based ARDS mortality prediction models, primarily aiming to evaluate the predictive performance of these models and compare their efficacy with conventional scoring systems. It also sought to identify limitations and provide insights for improving future ML-based prediction tools.</p><p><strong>Methods: </strong>A comprehensive literature search was conducted across PubMed, Web of Science, the Cochrane Library, and Embase, covering publications from inception to April 27, 2024. Studies developing or validating ML-based ARDS mortality predicting models were considered for inclusion. The methodological quality and risk of bias were assessed using the Prediction Model Risk of Bias Assessment Tool (PROBAST). Subgroup analyses were performed to explore heterogeneity in model performance based on dataset characteristics and validation approaches.</p><p><strong>Results: </strong>In total, 21 studies involving a total of 31,291 patients with ARDS were included. The meta-analysis demonstrated that ML models achieved relatively high predictive performance. In the training datasets, the pooled concordance index (C-index) was 0.84 (95% CI 0.81-0.86), while for in-hospital mortality prediction, the pooled C-index was 0.83 (95% CI 0.81-0.86). In the external validation datasets, the pooled C-index was 0.81 (95% CI 0.78-0.84), and the corresponding value for in-hospital mortality prediction was 0.80 (95% CI 0.77-0.84). ML models outperformed traditional scoring tools, which demonstrated lower predictive performance. The pooled area under the receiver operating characteristic curve (ROC-AUC) for standard scoring systems was 0.7 (95% CI 0.67-0.72). Specifically, 2 widely used clinical scoring systems, the Sequential Organ Failure Assessment (SOFA) and Simplified Acute Physiology Score II (SAPS-II), demonstrated ROC-AUCs of 0.64 (95% CI 0.62-0.67) and 0.70 (95% CI 0.66-0.74), respectively.</p><p><strong>Conclusions: </strong>ML-based models exhibited superior predictive accuracy over conventional scoring tools, suggesting their potential use in early ARD","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"27 ","pages":"e70537"},"PeriodicalIF":5.8,"publicationDate":"2025-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144111046","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Robust Cross-Platform Solution With the Sense2Quit System to Enhance Smoking Gesture Recognition: Model Development and Validation Study.","authors":"Anarghya Das, Juntao Feng, Maeve Brin, Patricia Cioe, Rebecca Schnall, Ming-Chun Huang, Wenyao Xu","doi":"10.2196/67186","DOIUrl":"https://doi.org/10.2196/67186","url":null,"abstract":"<p><strong>Background: </strong>Smoking is a leading cause of preventable death, and people with HIV have higher smoking rates and are more likely to experience smoking-related health issues. The Sense2Quit study introduces innovative advancements in smoking cessation technology by developing a comprehensive mobile app that integrates with smartwatches to provide real-time interventions for people with HIV attempting to quit smoking.</p><p><strong>Objective: </strong>We aim to develop an accurate smoking cessation app that uses everyday smartwatches and an artificial intelligence model to enhance the recognition of smoking gestures by effectively addressing confounding hand gestures that mimic smoking, thereby reducing false positives. The app ensures seamless usability across Android (Open Handset Alliance [led by Google]) and iOS platforms, with optimized communication and synchronization between devices for real-time monitoring.</p><p><strong>Methods: </strong>This study introduces the confounding resilient smoking model, specifically trained to distinguish smoking gestures from similar hand-to-mouth activities used by the Sense2Quit system. By incorporating confounding gestures into the model's training process, the system achieves high accuracy while maintaining efficiency on mobile devices. To validate the model, 30 participants, all people with HIV who smoked cigarettes, were recruited. Participants wore smartwatches on their wrists and performed various hand-to-mouth activities, including smoking and other gestures such as eating and drinking. Each participant spent 15 to 30 minutes completing the tasks, with each gesture lasting 5 seconds. The app was developed using the Flutter framework to ensure seamless functionality across Android and iOS platforms, with robust synchronization between the smartwatch and smartphone for real-time monitoring.</p><p><strong>Results: </strong>The confounding resilient smoking model achieved an impressive F<sub>1</sub>-score of 97.52% in detecting smoking gestures, outperforming state-of-the-art models by distinguishing smoking from 15 other daily hand-to-mouth activities, including eating, drinking, and yawning. Its robustness and adaptability were further confirmed through leave-one-subject-out evaluation, demonstrating consistent reliability and generalizability across diverse individuals. The cross-platform app, developed using Flutter (Google), demonstrated consistent performance across Android and iOS devices, with only a 0.02-point difference in user experience ratings between the platforms (iOS 4.52 and Android 4.5). The app's continuous synchronization ensures accurate, real-time tracking of smoking behaviors, enhancing the system's overall utility for smoking cessation.</p><p><strong>Conclusions: </strong>Sense2Quit represents a significant advancement in smoking cessation technology. It delivers timely, just-in-time interventions through innovations in cross-platform communication optimization ","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"27 ","pages":"e67186"},"PeriodicalIF":5.8,"publicationDate":"2025-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144110982","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"To Implement or Not to Implement? A Commentary on the Pitfalls of Judging the Value and Risks of Personalized Prognostic Statistical Models.","authors":"Linda Baumbach, Walter Hötzendorfer, Jan Baumbach","doi":"10.2196/69341","DOIUrl":"https://doi.org/10.2196/69341","url":null,"abstract":"<p><strong>Unlabelled: </strong>Prognostic models in medicine have garnered significant attention, with established guidelines governing their development. However, there remains a lack of clarity regarding the appropriate circumstances for (1) creating and (2) implementing tools based on models with limited performance. This commentary addresses this gap by analyzing the pros and cons of tool development and providing a structured outline that includes critical questions to consider in the decision-making process, based on an example of patients with osteoarthritis. We propose three general justifications for the implementation of survey-based models: (1) mitigation of expectation bias among patients and clinicians, (2) advancement of personalized medicine, and (3) enhancement of existing predictive information sources. Nevertheless, it is crucial to acknowledge that implementing such models is always context-dependent and may harm certain patients, necessitating careful consideration of the withdrawal of tool development and implementation in specific cases. To facilitate the identification of these scenarios, we delineate 16 possibilities following the implementation of a personalized prognostic model and compare the consequences to a current one-size-fits-all treatment recommendation at a population level. Our analysis encompasses the possible patient benefits and harms resulting from implementing or not implementing personalized prognostic models and summarizes them. These findings, together with context-related factors, are important to consider when deciding if, how, and for whom a personalized prognostic tool should be created and implemented. We present a checklist of questions and an Excel sheet calculation table, allowing researchers to weigh the benefits and harms of creating and implementing a personalized prognostic model at a population level against one-size-fits-all standard care in a structured and standardized manner. We condense this into a single value using a uniform Benefit-Risk Score formula. Together with context-related factors, the calculation table and formula are designed to aid researchers in their decision-making process on providing a personalized prognostic tool and deciding for or against its complete or partial implementation. This work serves as a foundation for further discourse and refinement of tool development decisions for prognostic models in health care.</p>","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"27 ","pages":"e69341"},"PeriodicalIF":5.8,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144093638","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploring Ethics: Understanding the Role of Privacy Policies and Institutional Review Boards in Digital Health Companies.","authors":"Jacqlyn L Yourell, Kelsey L McAlister, Clare C Beatty, Jennifer L Huberty","doi":"10.2196/70711","DOIUrl":"10.2196/70711","url":null,"abstract":"<p><strong>Unlabelled: </strong>Research efforts are growing rapidly in the digital health industry, but with this growth comes increasing ethical challenges. In this viewpoint paper, we leverage over 20 years of combined experience across academia, industry, and digital health to address critical issues related to ethics, specifically privacy policies and institutional review board compliance, which are often misunderstood or misapplied. We examine the purpose of privacy policies and institutional review boards, provide brief examples where companies faced legal and ethical consequences due to shortcomings, and clarify common misconceptions. Finally, we offer recommendations on how digital health companies can improve their ethical practices and ensure compliance in a rapidly evolving landscape.</p>","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"27 ","pages":"e70711"},"PeriodicalIF":5.8,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12101787/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144078536","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluation of the Digital Support Tool Gro Health W8Buddy as Part of Tier 3 Weight Management Service: Observational Study.","authors":"Petra Hanson, Farah Abdelhameed, Mohammed Sahir, Nick Parsons, Arjun Panesar, Michaela de la Fosse, Charlotte Summers, Amit Kaura, Harpal Randeva, Vinod Menon, Thomas M Barber","doi":"10.2196/62661","DOIUrl":"10.2196/62661","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;The escalating prevalence of obesity worldwide increases the risk of chronic diseases and diminishes life expectancy, with a growing economic burden necessitating urgent intervention. The existing tiered approach to weight management, particularly specialist tier 3 services, falls short of meeting the population's needs. The emergence of digital health tools, while promising, remains underexplored in specialized National Health Service weight management services (WMSs).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This service evaluation study assessed the use, effectiveness, and clinical impact of the W8Buddy digital support tool as part of the National Health Service WMS.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;W8Buddy, a personalized digital platform, provides a tailored weight management plan to empower individuals and was collaboratively developed with input from patients, the clinical team, and DDM Health. It launched at the University Hospitals Coventry and Warwickshire tier 3 WMS in 2022. All patients accessing University Hospitals Coventry and Warwickshire WMS were offered W8Buddy as part of standard care. Data were analyzed using independent samples t tests and Fisher exact tests for continuous and categorical outcomes, respectively. Multiple linear regression analysis explored associations between participant weight, engagement with W8Buddy, and time in the service.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Complete datasets for weights were available for 421 patients (220 W8Buddy group and 192 nonuser control group). W8Buddy users, predominantly female (n=185, 84.1%) and Caucasian, had a mean age of 43 years, while nonusers averaged 46 years (P=.02). Starting weights were comparable: 134 kg in the W8Buddy group and 130.2 kg in controls (P=.14); however, W8Buddy users had slightly higher starting BMI (49.6 vs 46.8 kg/m&lt;sup&gt;2&lt;/sup&gt;, P=.08). A total of 33.5% (n=392) of patients activated W8Buddy and engaged with it. There was significant weight loss among W8Buddy users, with a 0.74 kg monthly loss compared to standard care (β=-.74, 95% CI -1.28 to -0.21; P=.007). The longer an individual stayed in this study and used W8Buddy, the more weight was lost. W8Buddy users with type 2 diabetes mellitus experienced a significant hemoglobin A&lt;sub&gt;1c&lt;/sub&gt; reduction (59.8 to 51.2 mmol/mol, P=.02) compared to nonusers with type 2 diabetes. W8Buddy users also showed significant improvement across the Satisfaction With Life Scale, the Karolinska Sleepiness Scale, and quality of life visual analog scale (P&lt;.001) during follow-up.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;Participants engaging with W8Buddy as part of a digitally enabled tier 3 WMS demonstrated significant improvements in clinical and psychological outcomes, with weight changes statistically significant compared to those not engaging with the digital tool. Reduction in hemoglobin A&lt;sub&gt;1c&lt;/sub&gt; was present in both groups; however, statistical significance was only reached among those engagi","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"27 ","pages":"e62661"},"PeriodicalIF":5.8,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12125558/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144078534","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Quality and Misinformation About Health Conditions in Online Peer Support Groups: Scoping Review.","authors":"Bethan M Treadgold, Neil S Coulson, John L Campbell, Jeffrey Lambert, Emma Pitchforth","doi":"10.2196/71140","DOIUrl":"10.2196/71140","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;The use of health-related online peer support groups to support self-management of health issues has become increasingly popular. The quality of information and advice may have important implications for public health and for the utility of such groups. There is some evidence of variable quality of web-based health information, but the extent to which misinformation is a problem in online peer support groups is unclear.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;We aimed to gain insight into the quality of information and advice about health conditions in online peer support groups and to review the tools available for assessing the quality of such information.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;A scoping review was undertaken following the Joanna Briggs Institute scoping review methodology. We searched electronic databases (MEDLINE [Ovid], CINAHL, Web of Science, ASSIA, ProQuest Dissertation and Theses, and Google Scholar) for literature published before November 2023, as well as citations of included articles. Primary research studies, reviews, and gray literature that explored the quality of information and advice in online peer support groups were included. Title and abstracts were independently screened by 2 reviewers. Data were extracted and tabulated, and key findings were summarized narratively.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;A total of 14 (0.45%) relevant articles, from 3136 articles identified, were included. Of these, 10 (71%) were primary research articles comprising diverse quality appraisal methodologies, and 4 (29%) were review articles. All articles had been published between 2014 and 2023. Across the literature, there was more evidence of poor quality information and misinformation than of good quality information and advice, particularly around long-term and life-threatening conditions. There were varying degrees of misinformation about non-life-threatening conditions and about mental health conditions. Misinformation about noncommunicable diseases was reported as particularly prevalent on Facebook. Fellow online peer support group users often played an active role in correcting misinformation by replying to false claims or providing correct information in subsequent posts. Quality appraisal tools were reported as being used by researchers and health care professionals in appraising the quality of information and advice, including established tools for the appraisal of health-related information (eg, DISCERN, HONcode criteria, and Journal of the American Medical Association benchmark criteria). No tools reported were specifically designed to appraise online peer support group content.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;While there is good quality information and advice exchanged between users in online peer support groups, our findings show that misinformation is a problem, which is a matter of public health concern. Confidence in the quality of information shared may determine the utility of online peer su","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"27 ","pages":"e71140"},"PeriodicalIF":5.8,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12125560/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144078599","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluation of a Machine Learning Model Based on Laboratory Parameters for the Prediction of Influenza A and B in Chongqing, China: Multicenter Model Development and Validation Study.","authors":"Weiwei Hu, Yulong Liu, Jian Dong, Xuelian Peng, Chunyan Yang, Honglin Wang, Yong Chen, Shan Shi, Jin Li","doi":"10.2196/67847","DOIUrl":"10.2196/67847","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Influenza viruses are major pathogens responsible for acute respiratory infections in humans, which present with symptoms such as fever, cough, sore throat, muscle pain, and fatigue. While molecular diagnostics remain the gold standard, their limited accessibility in resource-poor settings underscores the need for rapid, cost-effective alternatives. Routine blood parameters offer promising predictive value but lack integration into intelligent diagnostic systems for influenza subtyping.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study aimed to develop a machine learning model using 24 routine blood parameters to predict influenza A and B infections and validate a deployable diagnostic tool for low-resource clinical settings.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;In this multicenter retrospective study, 6628 adult patients (internal cohort: n=2951; external validation: n=3677) diagnosed with influenza A virus infection (A+ group), influenza B virus infection (B+ group), or those presenting with influenza-like symptoms but testing negative for both viruses (A-/B- group) were enrolled from 3 hospitals between January 2023 and May 2024. The CatBoost (CATB) algorithm was optimized via 5-fold cross-validation and random grid search using 24 routine blood parameters. Model performance was evaluated using metrics such as the area under the curve (AUC), accuracy, specificity, sensitivity, positive predictive value, negative predictive value, and F&lt;sub&gt;1&lt;/sub&gt;-score across internal testing and external validation cohorts, with Shapley additive explanations analysis identifying key biomarkers. The Artificial Intelligence Prediction of Influenza A and B (AI-Lab) tool was subsequently developed on the basis of the best-performing model.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;In the internal testing cohort, 7 models (K-nearest neighbors, naïve Bayes, decision tree, random forest, extreme gradient boosting, gradient-boosting decision tree, and CatBoost) were evaluated. The AUC values for diagnosing influenza A ranged from 0.788 to 0.923, and those for influenza B from 0.672 to 0.863. The CATB-based AI-Lab model achieved superior performance in influenza A detection (AUC 0.923, 95% CI 0.897-0.947) and influenza B (AUC 0.863, 95% CI 0.814-0.911), significantly outperforming conventional models (K-nearest neighbors, RF, and XGBoost; all P&lt;.001). During external validation, AI-Lab demonstrated high performance, achieving an accuracy of 0.913 for differentiating the A+ group from the A-/B- group and 0.939 for distinguishing the B+ group from the A-/B- group.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;The CATB-based AI-Lab tool demonstrated high diagnostic accuracy for influenza A and B subtyping using routine laboratory data, achieving performance comparable to rapid antigen testing. By enabling timely subtype differentiation without specialized equipment, this system addresses critical gaps in managing influenza outbreaks, particularly in resource-constrain","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"27 ","pages":"e67847"},"PeriodicalIF":5.8,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12123241/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144078533","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Experiences Receiving and Delivering Virtual Health Care For Women: Qualitative Evidence Synthesis.","authors":"Karen M Goldstein, Sharron Rushton, Allison A Lewinski, Abigail Shapiro, Tiera Lanford-Davey, Jessica N Coleman, Neetu Chawla, Dhara B Patel, Katherine Van Loon, Megan Shepherd-Banigan, Catherine Sims, Sarah Cantrell, Susan Alton Dailey, Jennifer M Gierisch","doi":"10.2196/68314","DOIUrl":"10.2196/68314","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Persisting sex- and gender-based disparities in access to high-quality, personalized health care in the United States can lead to devastating outcomes with long-lasting consequences. Strategic use of virtual resources could expand equitable health care access for women. However, optimal approaches and timing for individualized, virtually delivered health care for women are unclear.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study aims to conduct a detailed analysis of the current literature to answer the following question: \"According to women and their health care teams, what are the reported successes and challenges in accessing, delivering, and participating in synchronous virtual health care for women?\"&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;We conducted a qualitative evidence synthesis using a best-fit framework approach based on the Nonadoption, Abandonment, Scale-up, Spread, and Sustainability (NASSS) framework and concepts from the Public Health Critical Race Praxis. We searched MEDLINE, Embase, and CINAHL from January 1, 2010, to October 10, 2022, using a combination of database-specific, relevant, controlled vocabulary terms and keywords; this search was updated in MEDLINE through January 2024. Additional citations were identified through handsearching. Our eligibility criteria were developed using the Sample, Phenomenon of Interest, Design, Evaluation, Research type tool to identify qualitative studies addressing synchronous virtual care for women. Citations were screened in duplicate, and eligible articles were abstracted. An iterative thematic synthesis approach was used to identify descriptive themes related to the successes and challenges related to delivering high-quality virtual care. Data reduction was performed using inductive and deductive reasoning. Quality assessment was conducted using the Critical Appraisal Skills Program and certainty of evidence using Confidence in the Evidence from Reviews of Qualitative Research approaches.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Of 85 eligible articles, we sampled 51 (60%) for data extraction based on representation of patient and clinician perspectives, marginalized voices, and relevance to a variety of clinical contexts. We identified themes across NASSS domains, including difficulty building rapport and emotional connections in the virtual setting, the amplification of barriers for women with preexisting challenges (eg, language barriers, limited transportation, and family and social commitments), and differing perceptions of privacy and safety related to virtual care depending on patient home context. Themes found to have high confidence included the value of convenience and cost savings offered by virtual care, the importance of patient choice in visit modality, the potential for negative impact on user well-being, considering the clinical context of modality choice, the importance of technology usability, and the value of virtual care for women located in regions wi","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"27 ","pages":"e68314"},"PeriodicalIF":5.8,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12123244/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144078535","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Patients' Perceptions of Artificial Intelligence Acceptance, Challenges, and Use in Medical Care: Qualitative Study.","authors":"Jana Gundlack, Carolin Thiel, Sarah Negash, Charlotte Buch, Timo Apfelbacher, Kathleen Denny, Jan Christoph, Rafael Mikolajczyk, Susanne Unverzagt, Thomas Frese","doi":"10.2196/70487","DOIUrl":"10.2196/70487","url":null,"abstract":"<p><strong>Background: </strong>Artificial intelligence (AI) is increasingly used in medical care, particularly in the areas of image recognition and processing. While its practical use in other areas is still limited, an understanding of patients' needs is essential for the practical and sustainable implementation of AI, which could further acceptance of new innovations.</p><p><strong>Objective: </strong>The objective of this study was to explore patients' perceptions toward acceptance, challenges of implementation, and potential applications of AI in medical care.</p><p><strong>Methods: </strong>The study used a qualitative research design. To capture a broad range of patient perspectives, we conducted semistructured focus groups (FGs). As a stimulus for the FGs and as an introduction to the topic, we presented a video defining AI and showing 3 potential AI applications in health care. Participants were recruited from different locations in the regions of Halle (Saale) and Erlangen, Germany; all but one group were from outpatient settings. We analyzed the data using a content analysis approach.</p><p><strong>Results: </strong>A total of 35 patients (13 female and 22 male; age: range 23-92, median 50 years) participated in 6 focus groups. They highlighted that AI acceptance in medical care could be improved through user-friendly applications, clear instructions, feedback mechanisms, and a patient-centered approach. Perceived key barriers included data protection concerns, lack of human oversight, and profit-driven motives. Perceived challenges and requirements for AI implementation involved compatibility, training of end users, environmental sustainability, and adherence to quality standards. Potential AI application areas identified were diagnostics, image and data processing, and administrative tasks, though participants stressed that AI should remain a support tool, not an autonomous system. Psychology was an area where its use was opposed due to the need for human interaction.</p><p><strong>Conclusions: </strong>Patients were generally open to the use of AI in medical care as a support tool rather than as an independent decision-making system. Acceptance and successful use of AI in medical care could be achieved if it is easy to use, adapted to individual characteristics of the users, and accessible to everyone, with the primary aim of enhancing patient well-being. AI in health care requires a regulatory framework, quality standards, and monitoring to ensure socially fair and environmentally sustainable development. However, the successful implementation of AI in medical practice depends on overcoming the mentioned challenges and addressing user needs.</p>","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"27 ","pages":"e70487"},"PeriodicalIF":5.8,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12123243/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144078594","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AI-Assisted Hypothesis Generation to Address Challenges in Cardiotoxicity Research: Simulation Study Using ChatGPT With GPT-4o.","authors":"Yilan Li, Tianshu Gu, Chengyuan Yang, Minghui Li, Congyi Wang, Lan Yao, Weikuan Gu, DianJun Sun","doi":"10.2196/66161","DOIUrl":"10.2196/66161","url":null,"abstract":"<p><strong>Background: </strong>Cardiotoxicity is a major concern in heart disease research because it can lead to severe cardiac damage, including heart failure and arrhythmias.</p><p><strong>Objective: </strong>This study aimed to explore the ability of ChatGPT with GPT-4o to generate innovative research hypotheses to address 5 major challenges in cardiotoxicity research: the complexity of mechanisms, variability among patients, the lack of detection sensitivity, the lack of reliable biomarkers, and the limitations of animal models.</p><p><strong>Methods: </strong>ChatGPT with GPT-4o was used to generate multiple hypotheses for each of the 5 challenges. These hypotheses were then independently evaluated by 3 experts for novelty and feasibility. ChatGPT with GPT-4o subsequently selected the most promising hypothesis from each category and provided detailed experimental plans, including background, rationale, experimental design, expected outcomes, potential pitfalls, and alternative approaches.</p><p><strong>Results: </strong>ChatGPT with GPT-4o generated 96 hypotheses, of which 13 (14%) were rated as highly novel and 62 (65%) as moderately novel. The average group score of 3.85 indicated a strong level of innovation in these hypotheses. Literature searching identified at least 1 relevant publication for 28 (29%) of the 96 hypotheses. The selected hypotheses included using single-cell RNA sequencing to understand cellular heterogeneity, integrating artificial intelligence with genetic profiles for personalized cardiotoxicity risk prediction, applying machine learning to electrocardiogram data for enhanced detection sensitivity, using multi-omics approaches for biomarker discovery, and developing 3D bioprinted heart tissues to overcome the limitations of animal models. Our group's evaluation of the 30 dimensions of the experimental plans for the 5 hypotheses selected by ChatGPT with GPT-4o revealed consistent strengths in the background, rationale, and alternative approaches, with most of the hypotheses (20/30, 67%) receiving scores of ≥4 in these areas. While the hypotheses were generally well received, the experimental designs were often deemed overly ambitious, highlighting the need for more practical considerations.</p><p><strong>Conclusions: </strong>Our study demonstrates that ChatGPT with GPT-4o can generate innovative and potentially impactful hypotheses for overcoming critical challenges in cardiotoxicity research. These findings suggest that artificial intelligence-assisted hypothesis generation could play a crucial role in advancing the field of cardiotoxicity, leading to more accurate predictions, earlier detection, and better patient outcomes.</p>","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"27 ","pages":"e66161"},"PeriodicalIF":5.8,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12123237/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144078452","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}