BMJ Health & Care Informatics最新文献

{"title":"Enhancing the accuracy of a multivariable prediction model to identify medical patients suitable for same day emergency care services.","authors":"Catherine Atkin, Suzy Gallier, James Hodson, L Li, Felicity Evison, Vinay Reddy-Kolanu, Elizabeth Sapey","doi":"10.1136/bmjhci-2024-101382","DOIUrl":"10.1136/bmjhci-2024-101382","url":null,"abstract":"<p><strong>Objectives: </strong>To assess the performance of the Glasgow admission prediction score (GAPS) and ambulatory score (AmbS) for identifying emergency department (ED) attendances suitable for medical same day emergency care (SDEC) services and to derive and validate a novel tool for this purpose, the SDEC Triage Tool (SDEC-T).</p><p><strong>Methods: </strong>A retrospective diagnostic study using routine healthcare data from three hospitals in a diverse urban setting (Birmingham, UK). All unplanned ED attendances by adults requiring internal medicine assessment were included. The primary outcome was suitability for SDEC, defined as discharged alive with a length of stay under 12 hours (LOS<12). The SDEC-T was derived using multivariable analysis, informed by stakeholder workshops.</p><p><strong>Results: </strong>152 877 attendances were included (median age: 58 years; 54.3% female; 68.4% White ethnicity); LOS <12 was achieved in 45.0% (n=68 752). The GAPS and AmbS had moderate predictive accuracy, with areas under the receiver operating characteristic curve (AUROCs) of 0.741 (95% CI 0.738 to 0.744) and 0.733 (95% CI 0.730 to 0.736), respectively. The SDEC-T comprised elements of the GAPS, AmbS, National Early Warning Score 2 (NEWS2) and presenting complaint and achieved an AUROC of 0.850 (95% CI 0.845 to 0.854) on internal validation. Stakeholders considered the tool acceptable and suitable for deployment across settings.</p><p><strong>Discussion: </strong>The SDEC-T demonstrated improved discrimination using routinely available variables, balancing predictive performance with clinical practicality. Its design supports implementation across hospitals with varying digital maturity.</p><p><strong>Conclusions: </strong>In a diverse patient cohort, the SDEC-T outperformed existing tools for identifying patients suitable for medical SDEC services.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"33 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13475099/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148705254","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":"Caution against anthropomorphising the virtues.","authors":"Rachel A Katz, Daniel Z Buchman","doi":"10.1136/bmjhci-2026-102250","DOIUrl":"10.1136/bmjhci-2026-102250","url":null,"abstract":"","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"33 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13475464/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148705236","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":"Why integration, not innovation, is the real-world challenge facing digital health.","authors":"Amina Tariq, Sundresan Naicker, Usman Iqbal, Steven McPhail","doi":"10.1136/bmjhci-2026-102218","DOIUrl":"10.1136/bmjhci-2026-102218","url":null,"abstract":"","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"33 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13475105/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148705272","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":"Clinicians' and patients' views and experiences on virtual hospital care: a systematic review of qualitative evidence.","authors":"Riyaas A Mohamed, Márcia Rodrigues Franco, Stephanie Mathieson, Marie March, Alessandra Marcelo, Gustavo Machado, Manuela Ferreira","doi":"10.1136/bmjhci-2025-101753","DOIUrl":"10.1136/bmjhci-2025-101753","url":null,"abstract":"<p><strong>Objectives: </strong>To appraise and synthesise the literature on patient and clinician experiences with hospital-based virtual care services.</p><p><strong>Methods: </strong>We searched Medline, Embase, CINAHL and PsycINFO (via Ovid) in October 2023. An updated search was performed in January 2025, with alerts maintained until May 2025. We included qualitative or mixed-methods studies evaluating patient or clinician experiences of hospital-based virtual care.</p><p><strong>Results: </strong>Out of 15 434 identified articles, 19 studies involving 514 clinicians and 215 patients were included. The majority of the studies were from high-income countries. Our analysis identified five themes influencing virtual hospital care experiences: perceived value, confidence and readiness, digital and health literacy, therapeutic relationships, and infrastructure and system support.</p><p><strong>Discussion: </strong>The potential of virtual care services is mediated by a complex relationship between personal, interpersonal and systemic factors. The acceptability of virtual hospital care is highly dependent on tailoring services to meet the individual needs of both patients and clinicians. The findings of this review demonstrate the need to improve clinician capacity and confidence through validated virtual tools and ongoing training.</p><p><strong>Conclusion: </strong>To ensure virtual hospital care is successful and equitable, the virtual health model must be co-designed with its end-users. In addition to addressing systemic barriers, emphasis must be placed on refining care delivery to support the needs of diverse patients and professions. Further research, particularly in low- and middle-income countries and through longitudinal studies, is critical for informing future health policy.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"33 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13422929/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148629501","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":"Machine learning-based prediction of shigellosis in children under five: development and internal validation of a prediction model.","authors":"Md Fuad Al Fidah, Md Ridwan Islam, Asg Faruque, Sharika Nuzhat, Mustafa Mahfuz","doi":"10.1136/bmjhci-2026-102115","DOIUrl":"10.1136/bmjhci-2026-102115","url":null,"abstract":"<p><strong>Objectives: </strong>Shigella remains a major cause of diarrhoea and mortality in children under five in low- and middle-income countries, where laboratory confirmation is often inaccessible and dysentery-based management lacks sensitivity. This study aimed to develop and internally evaluate machine learning models to predict microbiologically confirmed <i>Shigella</i> infection and secondarily to demonstrate the feasibility of translating the best-performing model into a prototype web-based decision-support application.</p><p><strong>Methods: </strong>We analysed data from 3356 children with diarrhoea enrolled in the Global Enteric Multicentre Study, excluding co-infections and non-diarrhoeal controls. Multiple machine learning algorithms were trained using 32 predictors and evaluated with 10-fold cross-validation. Performance was assessed using area under the receiver operating characteristic curve (AUC), recall and Brier score, with recall prioritised to minimise false negatives. The selected model was simplified using the 10 most informative predictors and integrated into a prototype web-based application. All analyses were restricted to internal validation.</p><p><strong>Results: </strong>Support vector machine (SVM) demonstrated the highest recall (0.64) with modest but potentially useful discrimination (AUC 0.74). The parsimonious SVM model achieved recall 0.67, AUC 0.77 and Brier score 0.16. A web-based prototype was developed to illustrate real-time model outputs for research purposes.</p><p><strong>Discussion: </strong>The model achieved moderate internal performance while prioritising recall, supporting its potential role as a research-stage risk stratification tool in settings with limited diagnostic capacity.</p><p><strong>Conclusion: </strong>This internally validated model shows potential for supporting risk stratification for shigellosis. External validation and impact evaluation are required before clinical or operational use.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"33 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13404616/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148577116","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":"Benchmarking large language models for de-identification of electronic health record notes.","authors":"Omkar Panchal, Nai-Wen Chang, Zi-Rui Zhao, Divyabharathy Ramesh Nadar, Hong-Jie Dai, Jitendra Jonnagaddala","doi":"10.1136/bmjhci-2025-101894","DOIUrl":"10.1136/bmjhci-2025-101894","url":null,"abstract":"<p><strong>Objectives: </strong>The rapid evolution of large language models (LLMs) and their growing application in clinical text processing have created an urgent need for reliable de-identification mechanisms. While LLMs show promise in identifying sensitive health information (SHI), their capabilities require rigorous evaluation. This study aims to conduct a comprehensive benchmarking analysis of various LLM-based, traditional rule-based and hybrid de-identification methods.</p><p><strong>Methods: </strong>Our benchmark analysis used five datasets (i2b2-2006, MIMIC-2008, i2b2-2014, i2b2-2016 and OpenDeID v1) from different countries. We developed three baseline and eight LLM-based models. The experimental setup encompassed nine different settings using various combinations of training and testing sets to assess model robustness and cross-dataset performance.</p><p><strong>Results: </strong>In the baseline models, the approach trained on the combined corpus of all five datasets (setting 3) significantly outperformed the other settings, achieving a strict F1 micro-average score of 0.8172. Regarding LLM-based models, the supervised fine-tuning approach using the same combined configuration (setting 9) achieved the highest performance with a strict F1 score of 0.9447.</p><p><strong>Discussion: </strong>The harmonisation of corpora ensured standardised data formatting and SHI management across five diverse datasets, highlighting the necessity for uniform categorisation to enhance the reliability of de-identification results.</p><p><strong>Conclusions: </strong>Our findings indicate that while fine-tuned LLMs offer superior accuracy, the observed performance variability across heterogeneous electronic health record sources poses significant technical challenges. Real-world implementation must address these inconsistencies to overcome the ethical and technical hurdles associated with deploying LLMs for handling sensitive health data.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"33 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13410914/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148547763","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 well do we write for patients? Longitudinal analysis of the readability and complexity of 4.6 million ophthalmic clinical letters.","authors":"Ariel Yuhan Ong, Christine A Kiire, Siegfried K Wagner, Quang Nguyen, Peter B M Thomas, Pearse A Keane","doi":"10.1136/bmjhci-2026-102086","DOIUrl":"10.1136/bmjhci-2026-102086","url":null,"abstract":"<p><strong>Objectives: </strong>Effective clinician-patient communication is a fundamental pillar of high-quality clinical care and can influence patient engagement, treatment adherence and clinical outcomes. However, the extent to which clinical letters meet recommended readability standards remains largely unquantified. We aimed to benchmark this at scale in an ophthalmology setting-the highest-volume outpatient specialty in the United Kingdom (UK) healthcare service.</p><p><strong>Methods: </strong>Over 4.6 million outpatient clinic letters written for 804 986 patients across 17 subspecialty services were included. Standard readability scores (including Flesch Reading Ease (FRE), SMOG Index, Automated Readability Index) were calculated for letters written between 2013 and 2025 at Moorfields Eye Hospital Foundation Trust, UK. Complex linguistic features such as lexical density and type-token ratio were also evaluated, and rule-based measures were applied to identify letters addressed directly to patients. Using the FRE as the primary outcome, readability was compared across subspecialties, and temporal trends were evaluated.</p><p><strong>Results: </strong>The median FRE was 51.1 (IQR 41.9-58.5), indicating college-level readability which was substantially poorer than recommended for patient-facing materials. Overall, 95.3% of letters were less readable than recommended, and these patterns extended across all readability metrics evaluated. Readability varied across subspecialty services (p<0.001), with limited association with sociodemographic covariates such as age and ethnicity. There was a significant decline in FRE over the study period (-0.64 points/annum, p<0.001). Rate of change varied across subspecialty services and was more pronounced in some such as neuro-ophthalmology (-1.24 points/annum, p<0.001), with few being stable (optometry, p>0.05). The use of second person terms was very low (median 0 per 100 words, IQR 0.0-1.1). There was a small annual increase in the likelihood of letters being addressed directly to patients (OR 1.123, 95% CI 1.121 to 1.25), although the proportion remained low overall (2.25%).</p><p><strong>Discussion: </strong>Clinical correspondence across ophthalmology services remained well above recommended readability thresholds and has become more complex over time, with substantial variability across subspecialty services. These findings will provide an empirical basis for local quality improvement initiatives. We hope that the methodological framework will also serve as a valuable resource for other specialties.</p><p><strong>Conclusion: </strong>Our findings highlight a persistent gap between policy recommendations and real-world practice, underscoring the need for targeted interventions and innovative approaches to support clearer patient-centred communication to optimise patient outcomes.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"33 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13475316/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148547747","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":"Streamlining elective surgical pathways using early digital screening with complexity grading: feasibility study of a co-designed innovation.","authors":"Tom Langford, Daveena Meeks, Deirdre Anderson, Lepalele Sepa, Stephanie Fraser, Pearl Okeke, Joseph Low, Polly Sinclair, Amanda Begley, Ramai Santhirapala","doi":"10.1136/bmjhci-2025-101743","DOIUrl":"10.1136/bmjhci-2025-101743","url":null,"abstract":"<p><strong>Objectives: </strong>To evaluate the feasibility, usability and validity of a co-designed digital questionnaire for early complexity screening in elective surgery patients.</p><p><strong>Methods: </strong>A mixed-methods feasibility study was conducted using operational data, patient interviews and surveys.</p><p><strong>Results: </strong>The average time to preoperative screening decreased from 3-4 weeks to 3.4 days. Of 244 patients, 44% were eligible for fast-tracking to low-complexity surgical hubs. A nurse-led validation process correctly identified 100% of medium-complexity and high-complexity cases. Most patients (97%) completed the questionnaire without assistance.</p><p><strong>Discussion: </strong>The tool proved feasible and user-friendly, enabling earlier identification of complexity and streamlining patient triage. It also holds promise for reducing cancellations and facilitating timely prehabilitation.</p><p><strong>Conclusions: </strong>This feasibility study supports the tool's feasibility, usability and validity. Further research will assess its clinical, operational and health economic impacts within redesigned surgical pathways.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"33 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13386080/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148535154","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":"Towards a framework for implementing artificial intelligence in clinical medicine.","authors":"Arjun Mahajan, Avery H LaChance, David W Bates","doi":"10.1136/bmjhci-2026-102068","DOIUrl":"10.1136/bmjhci-2026-102068","url":null,"abstract":"","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"33 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13374484/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148454346","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":"Prediction of in-hospital cardiac arrest on general wards using calibrated machine learning.","authors":"Wen-Ying Yu, Mei-Li Pan, Chung-Yu Chen","doi":"10.1136/bmjhci-2025-101893","DOIUrl":"10.1136/bmjhci-2025-101893","url":null,"abstract":"<p><strong>Objective: </strong>To identify time-windowed clinical predictors of in-hospital cardiac arrest (IHCA) and develop a temporally validated, calibrated machine-learning early warning for general wards.</p><p><strong>Methods: </strong>Retrospective matched case-control study at a tertiary hospital in Taiwan (2019-2021) including 115 IHCA cases and 115 controls matched on age and ward. Patients with do-not-resuscitate (DNR) orders were excluded. Demographics, comorbidities and laboratory results were extracted from electronic health records. Vital signs and level of consciousness were sampled in 16-24, 8-16 and 1-8-hour windows before the index time and summarised as the modified early warning score (MEWS). Models were trained with fivefold cross-validation and isotonic probability calibration and tested on a temporally held-out 2021 cohort.</p><p><strong>Results: </strong>Atrial fibrillation (OR 6.30), heart failure (OR 2.98), end-stage renal disease (OR 2.54), potassium (OR 1.81 per 1 mEq/L) and white blood count (OR 1.06 per 1 k/µL) were independent predictors. MEWS was associated with IHCA up to 16 hours, whereas in the final 8-hour lower SpO₂ predominated (OR 1.30 per 1% decrease; 95% CI 1.08 to 1.54). Calibrated XGBoost achieved Area Under the Receiver Operating Characteristic (AUROC) curve 0.89 and average precision (AP) 0.88; at sensitivity 0.95, specificity was 0.47 in the matched test set.</p><p><strong>Conclusions: </strong>Combining comorbidity burden, laboratory indices and time-windowed physiology enabled high-sensitivity IHCA warning. Because matching inflates event prevalence, AP, positive predictive value and calibration require recalibration to real-world prevalence; prospective multicentre validation is needed.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"33 1","pages":""},"PeriodicalIF":6.2,"publicationDate":"2026-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13347914/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148410450","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}