Journal of Medical Internet Research最新文献

筛选
英文 中文
Economic Evaluations of Algorithm-Enabled Remote Monitoring of Cardiac Implantable Electronic Devices: Systematic Review. 基于算法的心脏植入式电子设备远程监测的经济评估:系统综述。
IF 8.2 2区 医学
Journal of Medical Internet Research Pub Date : 2026-11-13 DOI: 10.2196/106939
Hanan Daghash, Rohan Pandey, Ryan P W Kenny, Cristina Fernandez-Garcia, Edward Meinert, Gurdeep S Sagoo
{"title":"Economic Evaluations of Algorithm-Enabled Remote Monitoring of Cardiac Implantable Electronic Devices: Systematic Review.","authors":"Hanan Daghash, Rohan Pandey, Ryan P W Kenny, Cristina Fernandez-Garcia, Edward Meinert, Gurdeep S Sagoo","doi":"10.2196/106939","DOIUrl":"https://doi.org/10.2196/106939","url":null,"abstract":"<p><strong>Background: </strong>Algorithm-enabled remote monitoring using cardiac implantable electronic devices (CIEDs) is increasingly used to support earlier detection of clinical deterioration in heart failure and in at-risk populations. However, the economic value of these technologies remains uncertain because intervention design, implementation, and evaluation methods vary.</p><p><strong>Objective: </strong>This study aimed to systematically identify, appraise, and synthesize full economic evaluations of algorithm-enabled CIED remote monitoring in adults with established heart failure or at risk of heart failure.</p><p><strong>Methods: </strong>A systematic review was conducted in accordance with the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 guidelines. Searches were performed in MEDLINE, Embase, Scopus, Web of Science, and the Cochrane Library, with supplementary searches of health technology assessment sources. Eligible studies reported full economic evaluations of algorithm-enabled remote monitoring linked to CIEDs. Data were extracted using a structured form and synthesized narratively due to heterogeneity. Methodological and reporting quality were assessed using the CHEQUE (Criteria for Health Economic Quality Evaluation) checklist and CHEERS (Consolidated Health Economic Evaluation Reporting Standards) 2022 statement. One reviewer screened records and extracted the data. A second reviewer independently checked subsets of the screening decisions and extracted the data.</p><p><strong>Results: </strong>Ten economic evaluations were included. They used models, trial data, or observational data; some were reported within health technology assessments. Substantial heterogeneity was observed in population definitions, intervention characteristics, algorithm types, monitored parameters, clinical response pathways, and economic methods. Cost-effectiveness and cost-utility analyses were most common, with time horizons ranging from short-term follow-up to lifetime modeling. Several studies reported economically favorable findings, including dominance (ie, less costly with better health outcomes) or cost-effectiveness. However, outcomes varied across studies, and favorable estimates often relied on assumptions about reduced hospitalization and length of stay, while quality-adjusted life year gains were generally modest. Reporting of key implementation factors, including alert burden and diagnostic performance, was limited.</p><p><strong>Conclusions: </strong>There is economic evidence for algorithm-enabled CIED remote monitoring suggesting potential value in some settings, but the evidence remains methodologically heterogeneous and difficult to compare directly across studies. Findings are sensitive to differences in intervention design, modeling approaches, and clinical input data, which limit certainty and transferability. More robust and standardized evidence is needed before economic conclusions can be ","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"28 ","pages":"e106939"},"PeriodicalIF":8.2,"publicationDate":"2026-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13766657/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149407250","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}
引用次数: 0
Efficacy of Digital Health Interventions for Insomnia: Systematic Review and Meta-Analysis of Randomized Controlled Trials. 数字健康干预对失眠的疗效:随机对照试验的系统回顾和荟萃分析。
IF 8.2 2区 医学
Journal of Medical Internet Research Pub Date : 2026-11-13 DOI: 10.2196/90905
Shan Gao, Baiting Zhang, Xiaobo Li
{"title":"Efficacy of Digital Health Interventions for Insomnia: Systematic Review and Meta-Analysis of Randomized Controlled Trials.","authors":"Shan Gao, Baiting Zhang, Xiaobo Li","doi":"10.2196/90905","DOIUrl":"https://doi.org/10.2196/90905","url":null,"abstract":"<p><strong>Background: </strong>Insomnia is common, and treatments are limited by tolerability and access. Digital health interventions (DHIs) are increasingly used for sleep management, but evidence comparing multiple outcomes is scarce.</p><p><strong>Objective: </strong>This study aimed to systematically evaluate the effects of DHIs on 8 sleep outcomes, including insomnia severity, sleep efficiency, total sleep time, and sleep quality.</p><p><strong>Methods: </strong>We systematically searched PubMed, Embase, Cochrane Library, Web of Science, Scopus, CINAHL, CNKI, CBM, VIP, Wanfang, ClinicalTrials.gov, and the American Academy of Sleep Medicine's website from inception to July 2026. Two reviewers (SG and BZ) independently screened studies, extracted data, and assessed risk of bias using the Cochrane Risk of Bias 2.0 tool. We included randomized controlled trials or controlled clinical trials comparing DHIs with any control in insomnia, without language restriction, and excluded experimental sleep deprivation, conference abstracts, protocols, and nonrandomized or noncontrolled designs. Pooled standardized mean differences (SMDs) with 95% CIs used restricted maximum likelihood with Hartung-Knapp-Sidik-Jonkman correction; 95% prediction intervals (PIs) used the Nagashima method. We also performed subgroup analyses by intervention category, comparator type, diagnostic criteria, and country income, plus sensitivity analyses, Egger tests, and GRADE (Grading of Recommendations Assessment, Development and Evaluation) assessment.</p><p><strong>Results: </strong>We included 44 randomized controlled trials (n=10,521) published between 2004 and 2026 across 14 countries. DHIs significantly improved insomnia severity (SMD -0.91, 95% CI -1.12 to -0.70), sleep efficiency (SMD 0.59, 95% CI 0.45-0.72), total sleep time (SMD 0.20, 95% CI 0.11-0.29), sleep quality (SMD -0.61, 95% CI -0.78 to -0.45), and secondary outcomes (SMDs -0.37 to -0.64). However, 95% PIs crossed the null for insomnia severity (-2.04 to 0.22), total sleep time (-0.05 to 0.46), and all secondary outcomes. Subgroup analyses showed larger insomnia severity effects in high- versus upper-middle-income countries, modality differences for sleep efficiency, and comparator-type differences for total sleep time (all <i>P</i><.01). Egger tests suggested small-study effects; sensitivity analyses did not change direction or significance. GRADE certainty ranged from very low to moderate.</p><p><strong>Conclusions: </strong>Although DHIs showed statistically significant average effects on multiple sleep outcomes, wide PIs crossing or approaching the null, effects approaching or below Minimum Clinically Important Difference thresholds, and very low-to-moderate GRADE certainty indicate that the evidence remains exploratory. Subgroup analyses revealed effect modifications by country income, intervention modality, and comparator type, underscoring contextual factors. Unlike previous reviews focusing on single ","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"28 ","pages":"e90905"},"PeriodicalIF":8.2,"publicationDate":"2026-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13766658/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149407253","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}
引用次数: 0
Informal Digital Information Use in Hospital Mass Casualty Incident Management During Wartime: Multicenter Cross-Sectional Questionnaire Study. 非正式数字信息在战时医院重大伤亡事件管理中的应用:多中心横断面问卷研究。
IF 8.2 2区 医学
Journal of Medical Internet Research Pub Date : 2026-11-13 DOI: 10.2196/109368
Maya Benudiz, Noam Sabag, Aya Cohen, Nikol Zorkin, Michael Markovits, Eyal Hashavia, Michal Koren, Or Peretz, Shachar Shapira, Daniel Trotzky
{"title":"Informal Digital Information Use in Hospital Mass Casualty Incident Management During Wartime: Multicenter Cross-Sectional Questionnaire Study.","authors":"Maya Benudiz, Noam Sabag, Aya Cohen, Nikol Zorkin, Michael Markovits, Eyal Hashavia, Michal Koren, Or Peretz, Shachar Shapira, Daniel Trotzky","doi":"10.2196/109368","DOIUrl":"https://doi.org/10.2196/109368","url":null,"abstract":"<p><strong>Background: </strong>Managing mass casualty incidents (MCIs) during an active warfare environment presents unique challenges, including operating under extreme uncertainty. Traditionally, emergency communications rely on strict, hierarchical channels from prehospital services to receiving hospitals. However, informal digital communication streams, particularly instant messaging apps such as WhatsApp and Telegram, are increasingly used within medical workflows. Despite international interest in public social media during disasters, empirical research regarding how hospital leadership echelons use informal messaging tools for real-time operational and clinical decision-making during active warfare remains sparse.</p><p><strong>Objective: </strong>This study aimed to characterize the adoption of social media and instant messaging platforms as early information sources among hospital-based MCI managers during wartime and to evaluate their specific impact on real-time operational and clinical decision-making.</p><p><strong>Methods: </strong>A multicenter, cross-sectional study was conducted using a structured questionnaire distributed across all 24 national medical centers authorized to receive MCIs during wartime in Israel. Target respondents encompassed diverse leadership echelons, including emergency department directors, trauma service directors, trauma coordinators, charge nurses, emergency team members, and hospital executive leadership.</p><p><strong>Results: </strong>Overall, 76 medical professionals representing key decision-makers across national receiving centers completed the survey. WhatsApp emerged as the most frequently used platform (median 3.0, IQR 2.00-4.00). Although these informal channels provided rapid initial intelligence, 65.3% (49/75) of respondents encountered false information during emergency events. Consequently, 81.3% (n=61) reported routinely verifying social media data against official channels before executing major actions. Multivariate regression analysis revealed distinct pathways of influence: higher platform use intensity was strongly and independently associated with enhanced situational awareness (<i>P</i>=.002) and greater operational decision-making influence (<i>P</i>=.02). In addition, participants' level of trust and reliance was associated with clinical decisions (<i>P</i>=.01) and real-time team management (<i>P</i>=.03). Furthermore, active platform engagement during live threat conditions was positively correlated with heightened situational awareness during missile launch alerts (<i>P</i><.001) and missile fall alerts (<i>P</i><.001). Platform use and trust behaviors remained consistent across years of professional experience, qualifications, and executive roles.</p><p><strong>Conclusions: </strong>Informal digital platforms, dominated by WhatsApp, serve as vital, rapid early information channels for hospital MCI leadership during wartime emergencies. While use intensity directly enhances si","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"28 ","pages":"e109368"},"PeriodicalIF":8.2,"publicationDate":"2026-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13761662/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149407260","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}
引用次数: 0
Effectiveness of Conversational Agents for Depression and Anxiety: Systematic Review and Network Dose-Response Meta-Analysis of Agent Types, Dose, and Human Support. 会话代理治疗抑郁和焦虑的有效性:系统评价和网络剂量-反应荟萃分析:代理类型、剂量和人的支持。
IF 8.2 2区 医学
Journal of Medical Internet Research Pub Date : 2026-11-13 DOI: 10.2196/104186
Pengyu Yang, Ping Lei Chui, Mingxin He, Yao Wu, Pengfei Cheng, Minxiang Li, Haojie Sun, Lurong Cai, Hua Zhang
{"title":"Effectiveness of Conversational Agents for Depression and Anxiety: Systematic Review and Network Dose-Response Meta-Analysis of Agent Types, Dose, and Human Support.","authors":"Pengyu Yang, Ping Lei Chui, Mingxin He, Yao Wu, Pengfei Cheng, Minxiang Li, Haojie Sun, Lurong Cai, Hua Zhang","doi":"10.2196/104186","DOIUrl":"https://doi.org/10.2196/104186","url":null,"abstract":"<p><strong>Background: </strong>Conversational agents (CAs) are increasingly used to deliver scalable interventions for depression and anxiety, but existing evidence has often treated these tools as a single category. The comparative effectiveness of different agent types, intervention doses, and levels of human support remains unclear.</p><p><strong>Objective: </strong>This review systematically evaluated the comparative effectiveness of various CA modalities and levels of human support, as well as potential dose-response relationships across different CA types.</p><p><strong>Methods: </strong>A comprehensive search of PubMed, Embase, Web of Science, Scopus, Ovid, CINAHL, and Psychology and Behavioral Sciences Collection (PBSC) databases was conducted from inception to December 2025. Eligible studies were randomized controlled trials (RCTs) evaluating CA-based interventions. We conducted a random-effects network meta-analysis (NMA) using postintervention outcomes and assessed inconsistency and risk of bias (RoB). Evidence certainty was assessed using the CINeMA (confidence in network meta-analysis) framework. Where data permitted, model-based network dose-response meta-analysis (MBNMA) was performed to examine dose-response associations.</p><p><strong>Results: </strong>A total of 41 studies (n=7577) were included. NMA showed that AI-enhanced intensive human support (AEIHS) appeared to produce greater symptom improvement for depression and anxiety compared with pure human digital guidance (PHDG; Hedges g=-4.28, 95% CI -5.56 to -2.99) and open-ended multimodal-enhanced chatbot (OEMM; Hedges g=-4.49, 95% CI -6.31 to -2.66), whereas most other comparisons were not statistically significant. MBNMA indicated that goal-oriented conversational agent (GOCA) and highly structured modular chatbot (HSMC) appeared to exhibit nonlinear effects, with preliminary evidence suggesting potentially enhanced response at low-to-moderate doses, though these findings require further investigation. However, publication bias was detected for depression (Egger P=.02), and the overall certainty of evidence was very low, primarily due to RoB, indirectness, and imprecision.</p><p><strong>Conclusions: </strong>While hybrid CA models with enhanced human involvement appeared to show potential advantages over fully automated systems, the evidence base remains limited. The very low certainty of evidence constrains confidence in comparative rankings and dose recommendations. Future high-quality trials are needed to establish optimal CA architectures and intervention doses for scalable mental health care.</p><p><strong>Trial registration: </strong>PROSPERO CRD420251145207; https://www.crd.york.ac.uk/PROSPERO/view/CRD420251145207.</p>","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"28 ","pages":"e104186"},"PeriodicalIF":8.2,"publicationDate":"2026-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149407251","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}
引用次数: 0
Electronic Health Record-Embedded Workflow to Operationalize Whole-Person Screening in Safety-Net Primary Care: Observational Implementation Evaluation Study. 嵌入电子健康记录的工作流程在安全网初级保健中实施全人筛查:观察性实施评估研究。
IF 8.2 2区 医学
Journal of Medical Internet Research Pub Date : 2026-11-13 DOI: 10.2196/101920
Dhruv Khurana, Shunling Tsang, Geoffrey Leung, Bijan Sasaninia, Edward Bacho, Mahbuba Khan, Anthony Firek
{"title":"Electronic Health Record-Embedded Workflow to Operationalize Whole-Person Screening in Safety-Net Primary Care: Observational Implementation Evaluation Study.","authors":"Dhruv Khurana, Shunling Tsang, Geoffrey Leung, Bijan Sasaninia, Edward Bacho, Mahbuba Khan, Anthony Firek","doi":"10.2196/101920","DOIUrl":"https://doi.org/10.2196/101920","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Health systems increasingly screen patients for social and whole-person needs. Yet, electronic health record data often remain passive when no workflow translates identified needs into structured action during routine care. In safety-net and federally qualified health center (FQHC) settings, this gap is especially consequential because clinicians must address multidomain needs within time-constrained encounters while meeting documentation, coding, and referral requirements.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;This study evaluated the implementation and recorded use of an Epic-based digital workflow that links a Whole PERSON Health Score (WPHS) assessment to a Best Practice Advisory (BPA) and SmartSet, along with a separate Power BI accountability dashboard, in a safety-net FQHC network.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;We conducted an observational implementation evaluation of the WPHS BPA-SmartSet workflow at Riverside University Health System using the RE-AIM (Reach, Effectiveness, Adoption, Implementation, and Maintenance) framework. We analyzed encounter-level WPHS assessments and BPA presentation records from January 2023 through July 2026. We examined screening reach, temporal correspondence between BPA presentations and preceding qualifying WPHS assessments, recorded downstream workflow activity, variation across clinics, and trends over time using descriptive statistics. As a sensitivity analysis, we estimated logistic regression models with clinic fixed effects and 2-way patient- and provider-clustered robust SEs to evaluate temporal patterns in SmartSet opening and downstream workflow activity.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;During the study period, 177,821 WPHS assessments were completed among 115,022 unique patients; 173,763/177,821 (97.7%) identified at least one qualifying yellow or red domain. Among 107,010 BPA presentations involving 101,297 unique patients, 104,049 (97.2%) were linked to a uniquely identifiable most-recent qualifying WPHS assessment; among these, 99.1% (103,122/104,049) occurred within 7 days. The SmartSet was opened in 82.9% (88,736/107,010) of BPA presentations, and broad structured downstream workflow activity was documented in 82.4% (88,160/107,010); Z-code documentation in 42.6% (45,632/107,010), and referrals in 23.4% (25,061/107,010). SmartSet opening increased from 41.3% (262/634) in January 2023 to 94.3% (4262/4520) in July 2026.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;In this safety-net FQHC setting, whole-person need was common and often multidomain, and an Epic BPA-SmartSet workflow was associated with high rates of SmartSet opening and documented downstream workflow activity across observed BPA presentations. BPA presentations were highly concordant with preceding qualifying WPHS assessments, and workflow activity increased substantially over the implementation period. For digital health leaders seeking to operationalize whole-person care, the findings support electronic hea","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"28 ","pages":"e101920"},"PeriodicalIF":8.2,"publicationDate":"2026-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149407254","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}
引用次数: 0
Securing WIC Virtual Services: The Overlooked Digital Health Tool in America's Maternal Mortality Crisis. 保护WIC虚拟服务:在美国孕产妇死亡率危机中被忽视的数字健康工具。
IF 8.2 2区 医学
Journal of Medical Internet Research Pub Date : 2026-11-13 DOI: 10.2196/116350
Anika Nayak
{"title":"Securing WIC Virtual Services: The Overlooked Digital Health Tool in America's Maternal Mortality Crisis.","authors":"Anika Nayak","doi":"10.2196/116350","DOIUrl":"https://doi.org/10.2196/116350","url":null,"abstract":"<p><strong>Unlabelled: </strong>The US government has only weeks left to either approve the 2027 federal spending bills or extend government funding to avoid funding lapses for essential programs. In this <i>News and Perspectives</i> article, JMIR Correspondent Anika Nayak reports on one such program-The Special Supplemental Nutrition Program for Women, Infants, and Children-and explains why Congress should seize the opportunity to make the program's remote services a permanent feature.</p>","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"28 ","pages":"e116350"},"PeriodicalIF":8.2,"publicationDate":"2026-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13766586/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149407266","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}
引用次数: 0
Evolving Perspectives on Patient-Accessible Electronic Health Records in Sweden: Comparative Survey Study. 瑞典患者可访问电子健康记录的演变观点:比较调查研究。
IF 8.2 2区 医学
Journal of Medical Internet Research Pub Date : 2026-11-13 DOI: 10.2196/76757
Jonas Moll, Hanife Rexhepi, Gunilla Myreteg, Charlotte Blease, Annika Bärkås, Åsa Cajander, Josefin Hagström, Isto Huvila, Maria Hägglund, Bridget Kane, Gunnar O Klein, Sari Kujala, Irene Muli, Rose-Mharie Åhlfeldt, Anna Kharko
{"title":"Evolving Perspectives on Patient-Accessible Electronic Health Records in Sweden: Comparative Survey Study.","authors":"Jonas Moll, Hanife Rexhepi, Gunilla Myreteg, Charlotte Blease, Annika Bärkås, Åsa Cajander, Josefin Hagström, Isto Huvila, Maria Hägglund, Bridget Kane, Gunnar O Klein, Sari Kujala, Irene Muli, Rose-Mharie Åhlfeldt, Anna Kharko","doi":"10.2196/76757","DOIUrl":"https://doi.org/10.2196/76757","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Patient-accessible electronic health records (PAEHRs) aim to enhance patient engagement by providing access to clinical information. In Sweden, implementation of a national PAEHR began in 2012 and reached nationwide scale-up in 2018. Adoption and use have steadily increased over time. So far, few studies report on how perspectives on PAEHRs evolve, informing on long-term use and development of the services.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;Data were compared from 2 national patient surveys conducted in Sweden (in 2016 and 2022) regarding patients' experiences and usage of PAEHRs. The aim is to explore and understand possible changes in patients' reasons for use and perceived value of the different information types and functions provided.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;The 2016 survey included responses from 2587 respondents, while the 2022 survey included 13,008 respondents. In 2016, the proportion of respondents who identified as women was 66.8% (1629/2437) and 67.3% (8753/13,008) in 2022. The largest age groups in 2016 were 55-64 years and 65-74 years in 2022. The surveys collected data on patients' experiences with PAEHRs, including demographic information, reasons for using, and perceived impacts on communication with health care professionals. Users who logged in to the PAEHR during the survey periods were invited to participate in the respective survey through a link on the login page.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Chi-square tests (&lt;i&gt;P&lt;/i&gt;&lt;.05) were used to check for differences in responses between the 2 surveys. Due to the large difference in the number of respondents between the 2 surveys, the effect sizes are fairly small, ranging from 0.02 to 0.19. Key findings indicate an increase in the positive perception of PAEHRs over the past 6 years. In 2022, 72.3% of respondents reported that PAEHRs supported communication with health care professionals, compared with 60.0% in 2016 (&lt;i&gt;P&lt;/i&gt;&lt;.001). The primary reason for using PAEHRs shifted from general interest in 2016 to preparing for health care visits in 2022. There was also an increase in patients valuing access to their lab test results, from 95.0% in 2016 to 97.8% in 2022 (&lt;i&gt;P&lt;/i&gt;&lt;.001; Cramer V=0.06).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;The study demonstrates that the overall highly positive patient attitude towards and usage of PAEHRs in 2016 persisted and was strengthened in 2022. The findings point to the growing importance of PAEHRs in enhancing patient engagement and communication with health care professionals, and to the acceptance and promotion of PAEHR within the Swedish health care system. This research provides valuable insights into the evolving landscape of PAEHR and its impact on patient-centered care. Increased use of PAEHRs may suggest that such systems can support better-informed patients, improve transparency in health care, and facilitate patient participation in care. The results can guide future policies and the development o","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"28 ","pages":"e76757"},"PeriodicalIF":8.2,"publicationDate":"2026-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13766677/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149407256","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}
引用次数: 0
Challenges of Single-Reference Benchmarks for Clinical Reasoning in Large Language Model-Based Decision Support. 基于大语言模型的决策支持中临床推理单参考基准的挑战。
IF 8.2 2区 医学
Journal of Medical Internet Research Pub Date : 2026-11-13 DOI: 10.2196/99019
Jiawei Zhou, Hanqing He, Weijie Yu, Zihan Zhong, Qiang Ju, Shuhang Wang, Xiaochuan Wang, Ning Li
{"title":"Challenges of Single-Reference Benchmarks for Clinical Reasoning in Large Language Model-Based Decision Support.","authors":"Jiawei Zhou, Hanqing He, Weijie Yu, Zihan Zhong, Qiang Ju, Shuhang Wang, Xiaochuan Wang, Ning Li","doi":"10.2196/99019","DOIUrl":"https://doi.org/10.2196/99019","url":null,"abstract":"<p><strong>Unlabelled: </strong>This viewpoint addresses developers and evaluators of large language model (LLM)-based clinical decision support systems. Although recent benchmarks increasingly evaluate multiple clinical reasoning domains, many still rely substantially on reference decision agreement-whether model outputs conform to predefined decisions. Our aim is to clarify when such agreement remains useful, when it becomes insufficient for complex or preference-sensitive decisions, and how it can be complemented by reasoning-centered assessment. Clinical decision-making often depends on structured reasoning under uncertainty, integrating probabilistic evidence, contextual constraints, and patient values. Using oncology as an illustrative domain, we argue that some decision variability is a structural feature of clinical reasoning rather than noise or error. Used alone in such settings, single-reference benchmarks may conflate reasonable divergence with incorrectness and reward answer imitation over transparent reasoning. We conclude that reference decision agreement should be retained for tasks with stable ground truth but supplemented by evidence grounding, reasoning quality, patient-centeredness, and safety checks for open-ended clinical decision support. This multidimensional approach is intended to support safer and more clinically meaningful evaluation.</p>","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"28 ","pages":"e99019"},"PeriodicalIF":8.2,"publicationDate":"2026-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13766656/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149407248","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}
引用次数: 0
Health Canada's Disclosure and Use of AI Raises Questions Around Effectiveness and Accountability. 加拿大卫生部对人工智能的披露和使用引发了有关有效性和问责制的问题。
IF 8.2 2区 医学
Journal of Medical Internet Research Pub Date : 2026-11-13 DOI: 10.2196/115222
Simon Spichak
{"title":"Health Canada's Disclosure and Use of AI Raises Questions Around Effectiveness and Accountability.","authors":"Simon Spichak","doi":"10.2196/115222","DOIUrl":"https://doi.org/10.2196/115222","url":null,"abstract":"<p><strong>Unlabelled: </strong>Canada's AI register lists 6 AI tools used by Health Canada-but is that the full picture? In this <i>News and Perspectives</i> article, JMIR Correspondent Simon Spichak reports on AI governance and transparency in Canada's federal health department.</p>","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"28 ","pages":"e115222"},"PeriodicalIF":8.2,"publicationDate":"2026-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13765783/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149407259","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}
引用次数: 0
A Fine-Tuned Large Language Model Workflow to Support Risk of Bias Assessment: Development, External Validation, and Reviewer Verification Study. 支持偏见风险评估的微调大型语言模型工作流:开发、外部验证和审稿人验证研究。
IF 8.2 2区 医学
Journal of Medical Internet Research Pub Date : 2026-11-13 DOI: 10.2196/108001
Yitian Li, Jingyu Chen, Liting Liang, Xingyun Geng, Guohua Wang, Jinsong Geng
{"title":"A Fine-Tuned Large Language Model Workflow to Support Risk of Bias Assessment: Development, External Validation, and Reviewer Verification Study.","authors":"Yitian Li, Jingyu Chen, Liting Liang, Xingyun Geng, Guohua Wang, Jinsong Geng","doi":"10.2196/108001","DOIUrl":"https://doi.org/10.2196/108001","url":null,"abstract":"<p><strong>Background: </strong>Given that randomized controlled trials (RCTs) are the gold standard for effectiveness research, assessing their risk of bias (RoB) becomes an indispensable step in systematic reviews. Yet this task remains time-consuming and prone to reviewer subjectivity. While large language models may accelerate the process, they lack transparent, traceable judgments linked to trial reports.</p><p><strong>Objective: </strong>To bridge methodological gaps and improve both efficiency and consistency, this study developed and externally validated TRoB-1, a fine-tuned open-weight large language model workflow for RoB assessment of RCTs.</p><p><strong>Methods: </strong>TRoB-1 was developed specifically for the Cochrane risk of bias tool version 1 (RoB 1), which is the most widely adopted instrument for critical appraisal of RCTs. The workflow generates preliminary judgments and supporting quotations from reviewer-selected passages for the target RoB domains. The workflow was built on 2-stage supervised fine-tuning of Gemma 2-9B-Instruct using 4-bit quantized low-rank adaptation. The training set comprised 4321 RoB records extracted from systematic reviews of chronic obstructive pulmonary disease, diabetes, and hypertension. The validation set consisted of 161 records from recently published RCTs covering a broader disease area. The reference standard was established by 2 independent reviewers. Two clinicians blinded to the reference standard verified TRoB-1-assisted assessments through a locally hosted web interface. Using the same reference standard, the performance of TRoB-1 raw outputs was compared with that of the Gemma 2 base workflow, and clinician-verified outputs were compared with raw TRoB-1 outputs.</p><p><strong>Results: </strong>TRoB-1 successfully generated structured outputs for all 161 validation records. In independent clinician-assisted assessments using the same workflow, raw TRoB-1 accuracy ranged from 73.3% (n=118) to 73.9% (n=119), compared with 52.2% (n=84) to 60.2% (n=97) for the Gemma 2 base model. After verification, accuracy ranged from 82.0% (n=132) to 84.5% (n=136) and macro-<i>F</i><sub>1</sub> from 0.709 to 0.776. Accuracy remained higher for raw TRoB-1 after excluding invalid base-model outputs, and verification did not change any correct judgment to an incorrect one. Clinician 1 corrected 13 initially incorrect judgments and clinician 2 corrected 18. The <i>F</i><sub>1</sub>-score for judgments of high-RoB increased from 0.600 to 0.784 for clinician 1 and from 0.571 to 0.821 for clinician 2.</p><p><strong>Conclusions: </strong>TRoB-1 combined task-specific fine-tuning, evidence-linked outputs, and clinician verification in a transparent workflow for reviewer-supported RoB assessment. The TRoB-1 web interface provides a practical platform for integrating RoB into evidence synthesis, particularly for living systematic reviews where timely updates are critical.</p>","PeriodicalId":16337,"journal":{"name":"Journal of Medical Internet Research","volume":"28 ","pages":"e108001"},"PeriodicalIF":8.2,"publicationDate":"2026-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13765787/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149407247","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}
引用次数: 0
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信
小红书