BMJ Health & Care Informatics最新文献

{"title":"Validation of ICD-10-CM algorithms for repeated eGFR-defined chronic kidney disease in the TriNetX network.","authors":"Chung-An Wang, Wei-Jie Wang, Jui-Yi Chen, Chung-Yi Cheng, Vin-Cent Wu","doi":"10.1136/bmjhci-2026-102413","DOIUrl":"10.1136/bmjhci-2026-102413","url":null,"abstract":"","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"33 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13663706/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149179296","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Grounded ophthalmic AI beyond the electronic health record trap: a critical narrative review.","authors":"Hitoshi Tabuchi, Mao Tanabe, Keita Kihara, Takaaki Moriguchi, Fumi Gomi","doi":"10.1136/bmjhci-2026-102293","DOIUrl":"10.1136/bmjhci-2026-102293","url":null,"abstract":"","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"33 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13663715/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149179298","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Performance of large language models in complex coronary artery disease decision-making and potential improvement strategy in a real-world cohort.","authors":"Zhixiang Zhang, Runze Chen, Shen Lin, Zhe Zheng","doi":"10.1136/bmjhci-2026-102072","DOIUrl":"10.1136/bmjhci-2026-102072","url":null,"abstract":"","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"33 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13663693/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149179245","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Clinical heterogeneity in performance of a commercial prediction model for clinical deterioration.","authors":"Sandra Taylor, Christine Williams, Sili Fan, Irene Cortes-Puch, Sarina Fazio, Anna Liu, Rachael Callcut, Bruce Hall, Jason Y Adams","doi":"10.1136/bmjhci-2026-102284","DOIUrl":"10.1136/bmjhci-2026-102284","url":null,"abstract":"","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"33 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13663712/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149179254","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Guiding and governing the complexities of digital allergy data integration and analysis: a critical national health priority for Australia.","authors":"Janet M Davies, Lesley Gray, Sach Jayasinghe, Sandra Vale, Kirsten P Perrett","doi":"10.1136/bmjhci-2026-102149","DOIUrl":"10.1136/bmjhci-2026-102149","url":null,"abstract":"","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"33 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13663731/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149179314","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Diagnostic performance of an open-source artificial intelligence model for detecting chest infections on after-hours emergency department chest radiographs in Singapore.","authors":"Ying Jie Toh, Samantha Ying Ying Tan, Chin Wah Eng, Boon Kee Lee, Praveen M Yogendra, Min On Tan","doi":"10.1136/bmjhci-2025-101958","DOIUrl":"10.1136/bmjhci-2025-101958","url":null,"abstract":"","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"33 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13663711/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149179239","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"How much do language and context affect the accuracy of AI health advice?","authors":"Prashant Garg, Thiemo Fetzer","doi":"10.1136/bmjhci-2026-102056","DOIUrl":"10.1136/bmjhci-2026-102056","url":null,"abstract":"","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"33 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13663759/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149179266","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Sex and gender bias in large language models: an old problem at a new scale.","authors":"Chiara Barbati, Virginia Casigliani, Caterina Rizzo, Anna Odone","doi":"10.1136/bmjhci-2026-102380","DOIUrl":"10.1136/bmjhci-2026-102380","url":null,"abstract":"<p><p>Patients are increasingly turning to large language models for health information, which makes the consistency of these systems' outputs across patient groups a public health concern. Demographic bias is harder to see than fabrication because it escapes accuracy benchmarks and shows up instead in the language the models produce. Gender bias is the form most consistently reported, with effects on clinical documentation and reasoning that often compound with ethnicity, socioeconomic status and other attributes. Drawing on evidence from gender medicine, we argue that it calls for sex- and gender-disaggregated evaluation, gender-medicine expertise in benchmark design and stratified monitoring after deployment. The methods needed for this already exist. What is still unsettled is whether gender equity will be treated as a design requirement or left until its consequences can no longer be ignored.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"33 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13629956/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149036367","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"From quality indicator to quality measurement: design and implementation of an automated audit and feedback tool for chronic kidney disease in Belgian primary care.","authors":"Justine Soetaert, Laurien Paredis, Bert Vaes, Ine Van den Wyngaert, Gijs Van Pottelbergh, Steve Van den Bulck","doi":"10.1136/bmjhci-2025-101931","DOIUrl":"10.1136/bmjhci-2025-101931","url":null,"abstract":"<p><strong>Objectives: </strong>To design and implement an automated audit and feedback (A&F) tool for Belgian Electronic Medical Record (EMR) systems to assess and improve the quality of primary care for chronic kidney disease (CKD).</p><p><strong>Methods: </strong>36 quality indicators (QIs) for primary CKD care were translated into conjugations and queries programmable within EMR systems. In the development phase, executable queries were constructed, taking into account technical constraints and the reliability of available data. The Intego database, a Belgian general practice-based morbidity registration network and A&F implementation laboratory, was used to test the feasibility and pilot the intervention. Visual feedback dashboards were designed using SAS Enterprise Guide and SAS Visual Analytics.</p><p><strong>Results: </strong>A final set of 80 queries that could be built into EMR systems was developed, allowing for an automated audit. The design of visual feedback and follow-up queries to make the feedback actionable was described. During the selection process 16 of the 36 indicators were excluded and 10 were adapted for the audit and/or feedback due to technical limitations or unreliable data. The final feedback included 14 indicators presented to clinicians through interactive dashboards.</p><p><strong>Discussion: </strong>This study describes the design of an automated A&F tool to improve the quality of primary CKD care in Belgium. Challenges included data accuracy within EMRs, the variability in data completeness and limitations in EMR query functionality. Future improvements in EMR systems and coding practices, such as the implementation of the Systematized Nomenclature of Medicine Clinical Terms (SNOMED CT) and improving feedback accessibility, could enhance the effectiveness of the tool.</p><p><strong>Conclusion: </strong>This study provides building blocks for implementing automated A&F interventions in Belgian EMR systems to improve primary CKD care quality. These building blocks could be applied internationally after validating the QIs.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"33 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13599950/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149001296","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Did you miss me? Making the most of digital phenotyping data by imputing missingness with point process models: observational study.","authors":"Imogen E Leaning, Andrea Costanzo, Raj Jagesar, Loran Knol, Sarah Tjeerdsma, Anna Tyborowska, Nessa Ikani, Lianne M Reus, Pieter Jelle Visser, Martien Jh Kas, Christian F Beckmann, Henricus G Ruhé, Andre F Marquand","doi":"10.1136/bmjhci-2026-102079","DOIUrl":"10.1136/bmjhci-2026-102079","url":null,"abstract":"<p><strong>Objectives: </strong>Smartphone-based digital phenotyping can provide low-burden behavioural measures for mental disorder monitoring. However, progress in making inferences from these data is challenged by the common occurrence of missing data. We propose a method to impute missingness using non-homogeneous Poisson point process models (PPPMs), where activities (overall phone, social media, communication app usage, outgoing/incoming calls) are modelled as 'points'.</p><p><strong>Methods: </strong>We evaluate personalised PPPMs for imputation and investigate their influence on downstream analysis. In a ground truth evaluation (in and out-of-sample), we evaluate time-varying covariates ('hour of the day', 'day of the week'; encoded using one-hot encoding and sine-cosine transformation) to model behavioural patterns in participants from SMARD (depression; n=26). We train a hidden Markov model (HMM) on data simulated by the PPPMs and compare this to a ground truth HMM. We then perform a replication of a prior HMM analysis in PRISM (Alzheimer's disease, schizophrenia, healthy controls; n=65) and Hersenonderzoek studies (Alzheimer's disease, memory complaints, healthy controls; n=283).</p><p><strong>Results: </strong>In the ground truth evaluation, 'hour' was consistently significant in in-sample likelihood ratio tests and 'day' was less commonly significant. PPPMs including one-hot encoded hour generally provided the highest out-of-sample likelihood. Using this PPPM variant, HMM properties were preserved, and prior findings were replicated.</p><p><strong>Discussion: </strong>Personalised PPPMs provide behavioural simulations that can be used for temporal imputation. These models capture average patterns and could be extended to include further temporal components.</p><p><strong>Conclusion: </strong>Non-homogeneous PPPMs are a promising imputation tool that may contribute to improved utility of digital phenotyping by providing realistic temporal imputations.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"33 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13636317/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149001223","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}