JMIR Medical Informatics最新文献

{"title":"Ambient AI Scribe Technology and Perceived Documentation Efficiency Among Surgeons: Cross-Sectional Study.","authors":"Sophia Luo, Katlyn McKay, Tatiana Zabaleta, Jeffrey S Upperman, Jamie R Robinson","doi":"10.2196/89329","DOIUrl":"10.2196/89329","url":null,"abstract":"<p><strong>Background: </strong>Clinical documentation demands a significant share of surgeons' time and can contribute to documentation-related burden and burnout. While electronic health records (EHRs) offer accessibility and completeness, they also impose a substantial documentation burden. Ambient AI scribe solutions aim to reduce this burden by capturing patient-clinician dialogue in real time to automate clinical documentation. However, their specific impact on surgical practice remains under-studied.</p><p><strong>Objective: </strong>We aimed to evaluate surgeons' perceptions of documentation efficiency, documentation timeliness, and burnout following implementation of an ambient AI documentation tool within the EHR during outpatient clinical encounters.</p><p><strong>Methods: </strong>We conducted a single-center cross-sectional survey of all surgical faculty members at a tertiary care academic institution 3 months after institutional implementation of the ambient AI-powered clinical documentation tool Dragon Ambient Experience (DAX) Copilot. A total of 368 faculty surgeons representing 12 surgical subspecialties were invited to participate. Participants were asked to retrospectively assess their baseline perceptions of documentation burden and subsequently report perceived changes following DAX Copilot implementation using standardized Likert-scale survey items. Descriptive analyses were performed among active DAX Copilot users. Open-ended responses were analyzed using practical thematic analysis.</p><p><strong>Results: </strong>The survey was completed by 28.5% (105/368) of the invited surgeons, with 38.1% (40/105) of participants reporting active DAX Copilot use. Overall, 77.5% (31/40) of users reported some or significant improvement in perceived documentation efficiency. Of those who reported a negative or neutral baseline perception of documentation time, 75.8% (25/33) reported an improved perception of efficiency following implementation of the ambient AI tool, whereas 85.7% (6/7) of surgeons with positive baseline perceptions of documentation time also reported further improvement. Improvements in perceived documentation timeliness were reported by 70.4% (19/27) of surgeons who previously reported negative or neutral baseline perceptions of timeliness and 76.9% (10/13) of surgeons with positive baseline perceptions. Additionally, 72.5% (29/40) of respondents reported enhanced documentation accuracy, detail, and consistency after DAX Copilot implementation. Improvements in self-reported burnout levels were reported less frequently, with 59.0% (23/39) of respondents reporting some or significant improvement, including 63.0% (17/27) with negative or neutral baseline perceptions of burnout. Qualitative feedback highlighted perceived improvements in documentation quality while also identifying current limitations of the technology, including challenges related to EHR integration, device compatibility, and customization.</p><p><strong>C","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"14 ","pages":"e89329"},"PeriodicalIF":5.0,"publicationDate":"2026-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13660865/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149186483","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated Lewis Score Estimation for Small Bowel Crohn Disease Using Capsule Endoscopy: Retrospective Cohort Study.","authors":"Yingying Meng, Min Gao, Jie Wu, Ying Huang","doi":"10.2196/92416","DOIUrl":"https://doi.org/10.2196/92416","url":null,"abstract":"<p><strong>Background: </strong>Small bowel capsule endoscopy (SBCE) is widely used to evaluate small bowel involvement in Crohn disease (CD); however, manual Lewis score calculation is time-consuming and susceptible to interobserver variability.</p><p><strong>Objective: </strong>This study aimed to develop and preliminarily validate a multitask deep learning system for automated Lewis score estimation in patients with small bowel CD undergoing SBCE.</p><p><strong>Methods: </strong>We developed Eval-Model, a multitask framework integrating You Only Look Once (YOLO)-style lesion detection and localization for ulcers and edema, a stenosis classification branch, and a long short-term memory-based temporal regression module. The primary dataset comprised SBCE examinations from 814 patients at the Children's Hospital of Fudan University. In this dataset, 725 (89.1%) cases were included for lesion-level annotation, and 89 (10.9%) cases with expert-consensus Lewis scores were used for scoring model development and internal testing. These 89 cases comprised 49 (55.1%) training cases and 40 (44.9%) internal test cases. All splits were performed at the patient level. A retrospective same-center temporal validation cohort of 20 consecutive cases from 2026 and 5 control cases were used for preliminary assessments of temporal robustness and specificity.</p><p><strong>Results: </strong>In the 40-case internal Lewis score test set, Eval-Model achieved a mean squared error of 14.693 (95% CI 8.72-22.15), root mean squared error of 3.833 (95% CI 2.95-4.71), mean absolute error of 2.9 (95% CI 2.1-3.8), R² of 0.82 (95% CI 0.70-0.90), and explained variance of 0.83 (95% CI 0.72-0.91). For lesion recognition, the model achieved an overall mean average precision of 0.94 with an inference time of 15 ms per frame. In the 20-case same-center temporal validation cohort, the mean squared error was 26.848 (95% CI 12.51-45.33), the root mean squared error was 5.182 (95% CI 3.54-6.73), the mean absolute error was 3.3 (95% CI 2.2-4.6), R² rounded to 1.00 (95% CI 0.98-1.00), and the explained variance rounded to 1.00 (95% CI 0.98-1.00). These temporal estimates require cautious interpretation because of the small, same-center cohort.</p><p><strong>Conclusions: </strong>Eval-Model demonstrated preliminary feasibility for automated Lewis score estimation from SBCE in small bowel CD. The system may serve as a standardized adjunct to expert review, but larger multicenter prospective validation with independent external annotation is required before clinical deployment.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"14 ","pages":"e92416"},"PeriodicalIF":5.0,"publicationDate":"2026-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149186447","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Interpretable Machine Learning-Derived Nomogram Model to Predict Population Health Literacy: Cross-Sectional Development and Validation Study.","authors":"Xuehai Zhang, Haojie Jin, Zhiming Xie, Yan Li, Zishuo Huang, Chenkai Zhang, Yue Xu, Dingming Yao, Xiujing Hu, Yuyang Zhu, Xuebo Zhu, Chishuang Wang, Chun Chen","doi":"10.2196/77654","DOIUrl":"https://doi.org/10.2196/77654","url":null,"abstract":"<p><strong>Background: </strong>Health literacy (HL) is a major factor associated with population health. However, no visualized predictive model has been developed to identify populations with low HL in a cost-effective manner.</p><p><strong>Objective: </strong>This study aims to identify key determinants of HL and develop a predictive nomogram model for population-level HL screening.</p><p><strong>Methods: </strong>This study analyzed cross-sectional data from 56,340 residents (aged 15-69 y) in Zhejiang Province (2023) And used the Chinese Health Literacy Scale to measure HL. We used 3 complementary analytical approaches: logistic regression (LR) analysis to identify HL-associated factors, machine learning models (gradient boosting decision tree [GBDT], extreme gradient boosting [XGBoost], LR, and random forest [RF]) with Shapley additive explanations (SHAP) to quantify predictor importance, and nomogram development using 2023 data with external validation on 2024 data. In the nomogram, model 1 used all the predictive variables, while model 2 used the 5 core predictive variables determined through SHAP analysis. Model performance was evaluated using receiver operating characteristic curves, calibration plots, and decision curve analysis.</p><p><strong>Results: </strong>The nomogram models designed for predicting HL demonstrated robust stability, with good results in external validation. The area under the curve (AUC) values for both the test and validation sets of the machine learning models exceeded 0.75. At the 0.5 threshold, the sensitivities of the GBDT, XGBoost, LR, and RF test sets and validation sets were all >60%. The specificity of the test sets and validation sets of all 4 machine learning models was >75%. The positive predictive value (PPV) and negative predictive value (NPV) were both >60%. The AUC value of nomogram model 1 developed using the data from 2023 was 0.821, and the AUC value of the externally validated nomogram model 1 was 0.814. Similarly, nomogram model 2 had AUC values of 0.819 in the internal validation and 0.812 in the external validation. The PPV and NPV of both the internal validation model 1 and model 2 were all >60%. The integration of GBDT, XGBoost, LR, and RF models, along with the SHAP method, highlighted education level, age, annual household income, smoking, and occupation as the 5 most critical determinants.</p><p><strong>Conclusions: </strong>By using the GBDT, XGBoost, LR, RF, and nomogram models, a predictive model with substantial efficacy was effectively developed and validated for forecasting the HL levels of the population. This comprehensive model not only exhibits a commendable predictive capacity but also identifies the pivotal factors influencing HL. Such insights are crucial for shaping health policies and fostering healthier behaviors across the population.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"14 ","pages":"e77654"},"PeriodicalIF":5.0,"publicationDate":"2026-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13660971/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149185807","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automating Injury Severity Score Calculation From Free-Text Discharge Diagnoses Using Domain-Specific Retrieval-Augmented Large Language Models: Retrospective Validation Study.","authors":"Ying-Jia Lin, Kuan-Yueh Fang, Chien-Hung Liao, Chi-Tung Cheng","doi":"10.2196/93922","DOIUrl":"https://doi.org/10.2196/93922","url":null,"abstract":"<p><strong>Background: </strong>Trauma registries are crucial for evaluating the prognosis of injuries and the quality of trauma care. However, the calculation of Injury Severity Score (ISS) remains a predominantly manual process, which is labor-intensive, potentially error-prone, and difficult to scale. Automating this process is a critical step toward enhancing the efficiency and quality of trauma registry data.</p><p><strong>Objective: </strong>This study conducts a feasibility test on the use of large language models (LLMs) to automatically calculate ISS from free-text discharge diagnoses. We specifically investigate the efficacy of retrieval-augmented generation (RAG) to enhance LLM accuracy by incorporating knowledge from the Abbreviated Injury Scale. We compare the performance of baseline LLMs against models augmented with both a standard RAG and a novel, domain-specific RAG framework.</p><p><strong>Methods: </strong>In this retrospective validation study, we used deidentified, free-text discharge diagnoses from trauma patients at Chang Gung Memorial Hospital (Linkou, Taiwan) in 2022. Against a physician-verified gold standard, we compared the performance of three systems: (1) baseline LLMs, (2) LLMs with standard RAG, and (3) LLMs with domain-specific RAG, for which the retriever was fine-tuned on trauma-related ICD-10 (International Statistical Classification of Diseases, Tenth Revision) codes. Performance was evaluated on a physician-verified test set across exact ISS prediction, tolerance-based accuracy, and ISS severity categories.</p><p><strong>Results: </strong>Baseline state-of-the-art LLMs achieve modest exact-match (EM) accuracy, ranging from 47.3% to 64.7%. Standard RAG did not produce consistent gains (54.3% to 60.3%), whereas the domain-specific RAG substantially improved accuracy (62.7% to 75.3%). Performance gains were most pronounced in patients with moderate to severe injuries. GPT-4.1 with domain-specific RAG reached the highest EM accuracy (75.3%, 95% CI 66.1%-82.7%), compared with 70.0% for the deterministic International Classification of Diseases and R statistical software (ICDPIC-R) baseline. Tolerance-based and categorical analyses confirm substantial gains with the domain-specific RAG framework in clinically relevant ranges.</p><p><strong>Conclusions: </strong>This single-center feasibility study suggests that LLMs augmented with a domain-specific retriever can calculate the ISS from free-text discharge diagnoses with overall accuracy comparable to that of a deterministic coding tool, with the advantage concentrated in the most severe injuries. This approach may help alleviate the administrative burden of manual coding, enhance standardization, and improve the quality of trauma registry data. Future multi-institutional validation is needed to confirm these findings.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"14 ","pages":"e93922"},"PeriodicalIF":5.0,"publicationDate":"2026-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149186572","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Accessibility and Decision-Supportive Quality of Benign Breast Disease Articles on Chinese Hospital WeChat Public Accounts: Nationwide Cross-Sectional Study.","authors":"Jing Li, Chenxi He, Shi Wang, Lichi Ke, Hongfan Yu, Xing Wei, Cheng Lei, Dehua Hu, Zhiliang Zhang, Wen Zhou, Min Li, Wenlin Wu, Wei Xu, Jin Bai, Qiuling Shi","doi":"10.2196/95994","DOIUrl":"10.2196/95994","url":null,"abstract":"<p><strong>Background: </strong>Shared decision-making (SDM) is critical for managing clinically ambiguous conditions such as benign breast disease (BBD), requiring reliable health information. In China, WeChat public accounts (WPAs) run by hospitals serve as a major health information channel, yet their quality remains unevaluated.</p><p><strong>Objective: </strong>This study aimed to evaluate the quality of BBD-related articles on hospital WPAs in China.</p><p><strong>Methods: </strong>Using a multistage stratified random sampling approach, we conducted a nationwide survey examining the quality of articles published from January 2020 to November 2024. The articles were evaluated for accessibility (readability, image quality, and user-friendliness) and SDM readiness (credibility, balance, and decision relevance) using validated instruments and content analysis.</p><p><strong>Results: </strong>Among 276,617 articles from 158 sampled hospitals, 464 were related to BBD. Accessibility was generally good: 72.4% (336/464) were written at a junior high school reading level. Visual presentation was acceptable, although only 10.2% (42/410) had complete image labeling. The Patient Education Materials Assessment Tool for Printable Materials (PEMAT-P) scores showed moderate understandability (mean 73.6%, SD 17.3%) but limited actionability (mean 50%, SD 23.2%). For SDM readiness, the mean Quality Evaluation Scoring Tool (QUEST) score was 14.9 (SD 4.7) out of 28, with treatment-related articles scoring lower than prevention-related articles (<i>P</i><.001). In the balance evaluation, using Brief DISCERN, 84.3% (182/216) of articles were below the high-quality threshold, often lacking information on treatment risks and quality-of-life impacts. Decision relevance revealed variability in surgical recommendations, especially regarding excision criteria and pregnancy-related guidance.</p><p><strong>Conclusions: </strong>WPA articles on BBD showed good accessibility but substantial gaps in SDM support, particularly in information balance and decision relevance. Standardized guidelines and quality improvements are needed to enhance patient-centered online health services.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"14 ","pages":"e95994"},"PeriodicalIF":5.0,"publicationDate":"2026-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13652390/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149149267","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cybersecurity of Large Language Models Across the Deployment Life Cycle in Health Systems.","authors":"Chun Joo Goh, Haoran Liu, Nethum Devendra, Khoa Nguyen Cao","doi":"10.2196/101715","DOIUrl":"https://doi.org/10.2196/101715","url":null,"abstract":"<p><p>In this Viewpoint, we highlight the principal cybersecurity measures that should be implemented to facilitate safe and effective integration of large language models (LLMs) into health care and propose a conceptual, life cycle-based framework synthesizing evidence from security and clinical informatics literature. While LLMs offer significant potential for applications in clinical documentation, triage, and medical education, their deployment creates novel vulnerabilities that can compromise patient safety and data confidentiality. We argue that these vulnerabilities must be addressed across the entire deployment life cycle, with distinct threats arising before and after a model enters clinical use. Predeployment risks include data and model poisoning, where an LLM's training data or core parameters are maliciously corrupted to embed biases or backdoors. After deployment, LLMs are susceptible to inference attacks, such as prompt injection and adversarial inputs, which can be used to manipulate model behavior and extract sensitive information. Standard performance benchmarks are often insufficient to detect these sophisticated attacks. Therefore, we argue that a proactive, multilayered security framework combining technical safeguards, rigorous governance, and human-in-the-loop oversight is essential for the safe and trustworthy adoption of LLMs in clinical practice.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"14 ","pages":"e101715"},"PeriodicalIF":5.0,"publicationDate":"2026-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149139410","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Digital Health-Enabled Prehospital Notification for Acute Stroke Using the Brain Saver Mobile App in Emergency Medical Transport in South Korea: Pilot Quasi-Experimental Study.","authors":"Eunah Kim, Jeongheon Kim, Dougho Park, Suhyun Park, Byungju Lee, Mi Sun Oh, Taehee Kim, Jinhyang Kim, Gahui Gim, Joongyub Lee, Ji-Yeob Choi, Daehee Kang","doi":"10.2196/92992","DOIUrl":"https://doi.org/10.2196/92992","url":null,"abstract":"<p><strong>Background: </strong>Timely access to stroke care is critical for patient prognosis. Despite the growing use of digital health strategies in stroke management, evidence supporting seamless and timely care coordination from the emergency medical services (EMS) to the emergency department (ED) remains limited. Brain Saver, a newly developed mobile app, addresses this gap by facilitating real-time data sharing between EMS personnel and ED clinicians during stroke transport.</p><p><strong>Objective: </strong>This study aimed to examine the potential of the Brain Saver protocol to improve existing EMS-ED workflows in emergency stroke transport by describing its functional components, implementing a pilot intervention in a real-world setting, and exploring its preliminary impact on treatment timeliness.</p><p><strong>Methods: </strong>Data were collected in Pohang, South Korea, from December 2023 to April 2024 through collaboration with 2 fire stations, eight 119 EMS and safety centers, 3 hospitals, and SEERS Technology. Preintervention training and postintervention surveys were conducted among EMS personnel (n=80) and clinicians (n=24). In this pilot, patients with stroke (ICD-10 [International Classification of Diseases, Tenth Revision] codes I60-I63) in the intervention group (n=34) were transported using ambulances equipped with the Brain Saver mobile app, while the comparison group (n=129) was transported by standard ambulances to the same hospitals during the study period. With \"needle\" defined as any parenteral treatment, onset-to-door time and door-to-needle time were compared by group. After exact matching on age, baseline stroke severity, stroke type, and destination hospital, intervention effects were estimated using generalized estimating equations.</p><p><strong>Results: </strong>Participants (N=163) had a mean age of 69.4 (SD 15.2) years, 50.3% (82/163) were male, and 65.6% (107/163) had ischemic stroke. No significant baseline differences, including stroke severity, were observed between groups. The median onset-to-needle time was shorter in the intervention group than in the comparison group (114 vs 204 minutes; P=.03). In the matched analytic sample (n=91), the intervention group showed significant reductions in onset-to-needle time (Exp(β)=0.49; P=.009) and door-to-needle time (Exp(β)=0.67; P=.04) compared with the comparison group.</p><p><strong>Conclusions: </strong>Integrating digital health into emergency stroke transport may improve care timeliness by supporting real-time prehospital notification and facilitating prompt in-hospital responses. The Brain Saver mobile app shows potential use for reducing onset-to-treatment time. Further larger-scale studies are needed to evaluate implementation fidelity and scalability.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"14 ","pages":"e92992"},"PeriodicalIF":5.0,"publicationDate":"2026-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149139390","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Business Associates' Involvement in US Health Care Data Breaches: Longitudinal Analysis.","authors":"Martin Ignatovski","doi":"10.2196/93588","DOIUrl":"10.2196/93588","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Health care organizations increasingly rely on business associates (BAs) to provide clinical, administrative, and technology services that require access to protected health information. While the Health Information Technology for Economic and Clinical Health (HITECH) Act and the Health Insurance Portability and Accountability Act (HIPAA) Omnibus Rule extended legal liability to BAs, the frequency and characteristics of data breaches involving BAs have not been systematically tracked across the entire post-HITECH reporting era. Understanding these trends is critical for health information managers and cybersecurity professionals who are directly responsible for managing third-party risk.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;The author examined the longitudinal trends in BA involvement in health care data breaches reported to the US Department of Health and Human Services (HHS) Office for Civil Rights (OCR) from 2009 to 2025, including changes in frequency, breach mechanisms, breach locations, and severity profiles of BA-involved incidents across 3 regulatory periods.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;The author conducted a retrospective longitudinal analysis of health care data breaches (N=6612) reported to the HHS OCR breach portal between October 2009 and December 2025. The author operationalized BA involvement as breaches reported by BA entities or flagged as BA-related. Using logistic regression models, the author estimated annual trends in BA involvement, breach mechanism, and breach location. Chi-square tests assessed associations between BA status and breach characteristics across 3 regulatory periods: pre-Omnibus (2009-2013), post-Omnibus (2014-2019), and 2020-2025. Proportion tests compared BA-involvement rates across periods.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;BA-involved breaches accounted for 1950 of 6612 (29.5%) incidents and 285,718,494 (48.8%) of all affected individuals. The annual BA-involvement rate increased from 22.1% in the pre-Omnibus period to 36.6% in the 2020-2025 period (&lt;i&gt;z&lt;/i&gt; score=8.29, &lt;i&gt;P&lt;/i&gt;&lt;.001). Logistic regression confirmed an 8% annual increase in the odds of BA involvement (odds ratio [OR] 1.08, 95% CI 1.07-1.10; &lt;i&gt;P&lt;/i&gt;&lt;.001). Hacking/IT incidents shifted from a minority of incidents to the dominant breach mechanism (OR 1.41 per year, 95% CI 1.39-1.44; &lt;i&gt;P&lt;/i&gt;&lt;.001), and the odds of network server breaches increased by 29% per year (OR 1.29, 95% CI 1.26-1.31; &lt;i&gt;P&lt;/i&gt;&lt;.001). BA-involved breaches were significantly more concentrated in hacking (1282/1950, 65.7% vs 2351/4662, 50.4%) and network server locations (1084/1950, 55.6% vs 1435/4662, 30.8%) compared with non-BA breaches (&lt;i&gt;P&lt;/i&gt;&lt;.001). The proportion of mega breaches (≥100,000 individuals) also increased annually (OR 1.16, 95% CI 1.13-1.19; &lt;i&gt;P&lt;/i&gt;&lt;.001), with BA-involved breaches exhibiting a significantly higher rate of mega breaches (12.4% vs 8.2%; &lt;i&gt;χ&lt;/i&gt;&lt;sup&gt;2&lt;/sup&gt;&lt;sub&gt;1&lt;/sub&gt;=28.44; &lt;i&gt;P&lt;/i&gt;&lt;.001).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"14 ","pages":"e93588"},"PeriodicalIF":5.0,"publicationDate":"2026-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13641320/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119121","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploring the Role of Portable Ophthalmic Devices in Clinical and Nonclinical Settings: Qualitative Study of Ophthalmologists and Optometrists.","authors":"Jeremy Barton, Sarika Gopalakrishnan, Eric Singman, Michael E Rogers, Donald Fletcher","doi":"10.2196/87040","DOIUrl":"https://doi.org/10.2196/87040","url":null,"abstract":"<p><strong>Background: </strong>Access to eye care is a persistent challenge due to the high global burden of visual impairment and barriers to receiving eye care, such as transportation and cost. Conventional ophthalmic equipment is immobile and unsuitable for bedside or community use, and this limits timely diagnosis and care delivery. Portable ophthalmic devices, such as handheld slit-lamps and fundus cameras, offer the potential to extend diagnostic capabilities to nonclinical settings and improve accessibility of eye care.</p><p><strong>Objective: </strong>This study examined eye care professionals' perceptions and experiences with portable ophthalmic devices, focusing on their roles in both clinical and nonclinical settings.</p><p><strong>Methods: </strong>Thirty-one practicing eye care professionals (16 ophthalmologists, 15 optometrists; 16 female, 15 male) with 2 to 45 years of clinical experience (mean 20.5, SD 13.1 y) participated. Semistructured interviews were conducted in person or via videoconferencing. The interview included open-ended qualitative questions on current and past use, benefits, and desired features of portable devices, along with quantitative ratings of device attributes on a 1 to 10 scale. Transcripts were coded in NVivo using thematic analysis, and descriptive statistics were calculated for the quantitative data.</p><p><strong>Results: </strong>Participants described portable devices as essential in settings where conventional equipment is impractical, including hospital rooms, emergency departments, nursing homes, and outreach. They emphasized utility for patients with mobility challenges and cognitive impairments. Key benefits included earlier disease detection and support for screening and referrals. Challenges involved image quality and device stabilization. Quantitative ratings of portable device attributes showed the highest scores for speed (median 8, IQR 6-8) and ease of use (median 8, IQR 6-8).</p><p><strong>Conclusions: </strong>Portable ophthalmic devices expand access to eye care beyond standard clinics and accommodate patients underserved by traditional equipment. Addressing technical and usability challenges and enhancing training opportunities will strengthen their integration into routine and outreach care.</p>","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"14 ","pages":"e87040"},"PeriodicalIF":5.0,"publicationDate":"2026-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13637025/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119157","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Participatory Design of AI-Based Clinical Decision Support Systems: Scoping Review.","authors":"Tabea Rambach, Patricia Gleim, Carolin Heizmann, Philipp Kellmeyer, Christophe Kunze","doi":"10.2196/88368","DOIUrl":"10.2196/88368","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;AI-based clinical decision support systems (CDSS) can improve diagnostics and treatment decisions, but they are rarely implemented in practice. Barriers include limited integration into clinical workflows, lack of transparency, and insufficient involvement of end users in system design. Participatory and user-centered approaches offer ways to address these challenges by aligning development processes with the needs and routines of clinical staff. However, systematic evidence on how such approaches are applied in the development of AI-based CDSS remains limited.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Objective: &lt;/strong&gt;Our study examined how participatory approaches are used in the development, piloting, and implementation of AI-based CDSS. We analyzed which user perspectives were included, which participatory methods were applied, how they contributed to technical design, and which ethical, legal, and social implications were addressed.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;This scoping review followed the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guideline, with a protocol published in advance. A systematic search was conducted in MEDLINE, ACM Digital Library, CINAHL, and PsycInfo for studies published from 2012 onward, complemented by snowballing and manual searches. Primary studies in English or German were included if they involved clinical staff in the development, piloting, implementation, or evaluation of AI-based CDSS. Moreover, 3 independent reviewers conducted screening and data extraction, resolving disagreements by consensus. Data analysis followed JBI methodology and focused on the scope of participation, theoretical and methodological foundations, and reported impacts of participatory approaches.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Of 4318 identified records, 37 met the inclusion criteria. The studies showed broad variation in terminology and methods, most often describing user-centered or iterative processes and less frequently co-design. Physicians were involved in nearly all studies, nurses frequently, and other professional groups only occasionally. Participation mainly supported requirements analysis, adaptation of models to clinical workflows, and the design of explainable interfaces. In several projects, it also influenced data selection, annotation, and visualization. Common barriers included time constraints, limited continuity of participation, and uncertainty toward AI. Ethical, legal, and social aspects were addressed implicitly through themes such as autonomy, responsibility, and traceability, while fairness and bias were rarely discussed.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;Participatory processes in AI-based CDSS development should extend across all stages of system design and address not only usability but also data quality, bias, and broader ethical, legal, and social issues. Equal inclusion of nursing and therapeutic expertise is essential to reflect","PeriodicalId":56334,"journal":{"name":"JMIR Medical Informatics","volume":"14 ","pages":"e88368"},"PeriodicalIF":5.0,"publicationDate":"2026-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13637979/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149119150","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}