BMJ Health & Care Informatics最新文献

Objectives: To examine primary care physicians' attitudes regarding artificial intelligence (AI) use for administrative clinical tasks.

Methods: Web-based survey with US physicians in family medicine or internal medicine (N=420, response rate 5.13%). Two hypothetical AI tools for administrative clinical activities were described. We examined physicians' attitudes towards AI tools, and their associations with practice years, exposure to AI, use case and stakeholder type were evaluated using generalised estimating equations.

Results: Participants were on average 49.6 years (SD=12.5) and 56.7% men (238/420). Physicians with fewer practice years were more likely to endorse the tools' benefits (OR 1.70-1.96), the tools' benefits outweighing risks (OR 1.79-2.06) and their openness to use (OR 1.63-1.83), and were less likely to endorse disclosure of AI use (OR 0.60 (95% CI 0.36 to 0.998)). Physicians with AI exposure were more likely to agree the tools' benefits outweighed their risks (OR 1.51 (95% CI 1.06 to 2.16)). Physicians were more likely to endorse the tools' benefit to physicians (OR 4.94 (95% CI 4.16 to 5.86)) and physicians' openness to using them (OR 3.53 (95% CI 2.97 to 4.20)) than they were to endorse their benefit to patients and patients' openness. Physicians rated an AI tool for notes generation as more beneficial than one for billing assistance (OR 1.73 (95% CI 1.39 to 2.16)).

Discussion: Although the findings are preliminary, US primary care physicians' attitudes toward AI for clinical administration varied by practice years, prior exposure to AI, use case and stakeholder type.

Conclusion: Our findings highlight opportunities to develop training and implementation strategies in service of advancing safe and effective integration of administrative AI tools in primary care.

Objectives: Emergency department crowding refers to a complex state of congestion associated with a set of performance indicators such as occupation levels, waiting times and specific scores. Among current methods to model it, an objective gap exists between forecasting machine learning methods, focusing on prediction precision and queueing and simulation methods, focusing on capturing correctly the effect of decision variables for evaluation and optimisation purposes. The objective of the present analysis is to implement and numerically validate a novel data-driven queueing methodology that can bridge this gap and to show its applicability in a simulation case study.

Methods: A statistical modelling of the queueing processes, particularly patient departure rates and probabilities, is developed to cross the gap defined above. Using the data from a major emergency department of eastern France, the resultant data-driven queueing network model is validated and applied through a synchronous simulation algorithm.

Results: The model obtained considers the complex effects of patient arrivals and doctor and nurse allocations while offering an unbiased and accurate measure of long-term crowding. Its application with the case study quantifies the impact of the opening of new Unscheduled Care Services on emergency department crowding.

Discussion: The new data-driven queueing methodology is able to model and quantify complex crowding effects at a detailed level in an emergency department.

Conclusions: This study shows an alternative approach successfully bridging the modelling gap by establishing a model that can effectively predict system crowding dynamics under the influence of multiple key variables.

Objective: This paper explores the implementation of the Multi-Source Data Analytics and Triangulation (MSDAT) platform as a solution to Nigeria's health data challenges. By consolidating data from various sources into a centralised platform, MSDAT aims to improve data accessibility, interoperability and quality.

Methods: The MSDAT platform was developed using a modular, cloud-based architecture comprising data integration and analytics layers. Secondary health data from multiple standard sources such as District Health Information Software 2, Nigeria Demographic and Health Survey, WHO. Data was visualised using interactive dashboards. All processes adhered to the Nigeria Data Protection Act 2023, with data security maintained through encryption, role-based access control and routine system audits.

Results: The development of the MSDAT has led to increased use of health data in high-level health stakeholders' meetings, supporting the shift towards making data-driven decisions. Additionally, the platform is enhancing health data integrity in Nigeria by ensuring the availability of quality data.

Discussion: However, the adoption of this centralised system has faced challenges, including resistance to change and data migration complexities. Efforts to ensure collaboration between healthcare providers, policymakers and technical experts will be essential to overcome these barriers and fully realise the potential of the MSDAT platform in enhancing healthcare delivery and improving health outcomes.

Conclusion: The MSDAT platform demonstrated the value of integrated health data systems in improving data quality, accessibility and use for decision-making. Consequently, strengthening Nigeria's capacity for evidence-based planning, equitable resource allocation and performance monitoring is advancing progress toward a more responsive and data-driven health system.

Objectives: We aimed to compare sleep characteristics between patients with liver cirrhosis and healthy controls using a standardised protocol and portable electroencephalogram (EEG) devices.

Methods: We enrolled patients with early stage cirrhosis at low risk for sleep disorders (no apnoea, insomnia, alcohol use, pruritus or major portosystemic shunt; body mass index (BMI) ≤31 kg/m²). Using propensity score matching (age, sex, BMI), 18 patients with cirrhosis were compared with 18 healthy older adults from a 95-person cohort. Sleep was assessed at home using portable EEG devices measuring total sleep time, sleep latency, wake after sleep onset, sleep efficiency, sleep stages (N1-N3, rapid eye movement (REM)) and REM latency. Questionnaires were also administered.

Results: Questionnaires indicated no major sleep complaints. However, EEG revealed longer sleep latency, increased wakefulness and lower sleep efficiency in cirrhosis. N1 sleep time and percentage were higher, REM sleep was reduced and REM latency was prolonged.

Discussion: Traditional assessments rely on subjective reports, while polysomnography is often impractical. Our portable EEG approach revealed distinct disturbances-fragmented REM and delayed onset-undetectable by questionnaires alone.

Conclusion: Home EEG monitoring uncovered previously unrecognised sleep abnormalities in cirrhosis, suggesting utility for early detection and management.

Background: How user-centred prototyping is carried out to solve adult critical care issues depends on the unique characteristics of this context. This review aimed to characterise prototyping in the context of critical care in terms of the types of prototypes developed, activities used to generate prototypes and settings in which prototypes were generated.

Methods: Four databases (PubMed, CINAHL, SCOPUS and IEEExplore) were searched for articles published from inception to 25 September 2025, in English, that involved prototyping to address issues in adult critical care. Two reviewers independently screened the search results to identify eligible articles and reviewed retained articles.

Results: 22 of 860 articles met the eligibility criteria. Role, look and feel, implementation and integration prototype types which combined two or more of these prototypes were identified. Prototypes addressing both role and look and feel were most common. 10 prototyping activities were reported, namely sketching, storyboarding, interactivity simulation, digitalising and adapting paper-based forms, rank ordering, building a functional device model, survey for item selection, card sorting, adapting a predeveloped high-tech prototype to a low-tech version, and revising existing workflow. Six of 22 articles reported multiple activities. Sketching was the most often used activity, and the in-person hospital setting was the most reported.

Conclusions: Overall, there was a lack of reporting on the details of the prototyping processes. Such details could help future researchers anticipate the unique challenges of prototyping to develop solutions to solve adult critical care issues, learn from prior successful experiences and better plan strategies to address these challenges.

Objectives: To assess the performance of machine learning (ML) algorithms to predict the presence of germline BRCA1/2 pathogenic variants in ovarian cancer (OC) patients based on clinical-pathological features.

Methods: Clinical-pathological features of 648 patients with OC tested for BRCA1/2 were analysed using three supervised ML algorithms: random forest, boosting and support vector machine.

Results: In the 'test' sample, boosting proved to be the most effective algorithm (accuracy: 84.5%; precision: 80.0%; recall: 3.1%; area under the curve (AUC): 78.8%), followed by support vector machine (accuracy: 81.4%; precision: 72.7%; recall: 27.6%; AUC: 62.3%) and random forest (accuracy: 74.4%; precision: 55.6%; recall: 14.7%; AUC: 71.3%). In the 'validation' sample, accuracy was 79.8% for boosting, 81.7% for support vector machine, 80.8% for random forest.In the most effective algorithm (boosting), family history of OC showed the highest relative influence (52.9), followed by histotype (19.5), personal history of breast cancer (BC) (17.1), age at diagnosis (8.4) and family history of BC (2.2), while Federation of Gynecology and Obstetrics stage had no influence.

Discussion: We identified the predictive algorithm that best estimates the a priori likelihood of being a carrier of germline BRCA1/2 pathogenic variants in patients with OC. These findings support a role for ML approaches in predicting BRCA1/2 status in patients with OC, but accuracy and precision are still suboptimal for clinical use, suggesting the need for additional research.

Conclusions: Results support the selection of relevant clinical features for predictive purposes, which could have significant implications for the clinical management of patients with OC.

Objectives: This study aimed to develop and validate machine learning (ML) models to predict all-cause hospital admissions and 90-day readmissions using structured, patient-reported survey data.

Methods: A cross-sectional survey was conducted between 3 July 2021 and 18 December 2022, among US adults aged ≥18 years with at least one cardiovascular risk factor. Participants were recruited through social media, community pharmacies and outpatient clinics. The final sample included 1318 participants. Primary outcomes were any all-cause hospitalisation and readmission within 90 days. Eight supervised ML models were trained using an 80:20 train-test split and 10-fold cross-validation. Model performance was evaluated using area under the receiver operating characteristic curve (AUROC), precision, recall, F1 score and calibration metrics. SHapley Additive exPlanations (SHAP) values identified key predictors.

Results: Among 1318 participants, 35.0% reported at least one hospitalisation and 10.4% reported a 90-day readmission. The Extra Trees (ET) model demonstrated the best performance across both outcomes. For hospitalisation, ET achieved an AUROC of 0.93, precision of 0.83 and recall of 0.87. For readmission, AUROC was 0.99 with precision of 0.95 and recall of 0.96. SHAP analysis identified heart disease, medication burden, race/ethnicity, employment and insurance status as the most influential predictors.

Discussion: Patient-reported data reflecting behavioural, social and clinical factors can predict hospitalisations with high accuracy, complementing traditional EHR-based models.

Conclusions: Integrating such patient-reported and behavioural data into electronic health records could enable earlier identification of high-risk individuals and support targeted, preventive interventions to improve healthcare outcomes.

Objectives: To evaluate provider-level variability across the full perioperative workflow using a computer vision-based artificial intelligence (AI) system that automatically detects and timestamps operating room events.

Methods: A cross-sectional study of total knee arthroplasty cases performed between September 2022 and March 2025 at a regional health system was conducted. An ambient surgical platform equipped with wall-mounted cameras continuously captured perioperative activity. A YOLO-based model identified patients, staff and equipment, and a transformer-based event detector predicted key perioperative events in real time. Detected events were used to segment cases into eight workflow phases: anaesthesia induction, patient preparation, final preparation, active procedure, postoperation, patient exit, room cleanup and room setup. Provider-level variability in segment durations was evaluated after adjusting for case characteristics, daily surgical volume and team composition.

Results: The computer vision event detection system achieved high agreement with ground truth annotations. Across 2502 surgical cases, significant provider-level variability was observed in all workflow segments except for room exit. Active procedure showed the greatest variation among surgeons (F=28.4, p<0.001; β IQR=-20.9 to 8.8 min) followed by room setup among circulating nurses (F=1.3, p<0.001; β IQR=-5.2 to 4.4 min) and room setup among scrub nurses (F=1.4, p<0.001; β IQR=-3.7 to 3.2 min).

Conclusions: Automated workflow segmentation using computer vision provides a scalable method to evaluate perioperative efficiency with greater granularity. Broader case segmentation may support more targeted and effective surgical quality improvement initiatives.

Objective: This study aims to develop an algorithm to detect steatotic liver disease (SLD) risk in low-resource settings without requiring imaging.

Methods: This retrospective cohort study included 826 measurements from 444 participants aged 45-60 years who participated in the MAUCO+ study. Data included ultrasound, vibration-controlled transient elastography (VCTE), anthropometrics and biomarkers. Logistic multivariable regression was used to develop two predictive models for SLD risk, with and without ultrasound, using VCTE as gold standard. Missing data were minimal and retained in the analysis, as their proportion was not statistically relevant. Predictive performance (sensitivity, specificity, positive predictive value and negative predictive value) was compared with the clinically used Fatty Liver Index (FLI).

Results: The algorithm without ultrasound achieved a sensitivity of 81.1% (95% CI 71.7% to 88.4%) and specificity of 71.4% (95% CI 57.9% to 80.4%). The model with ultrasound demonstrated a sensitivity of 91.5% (95% CI 84.1% to 95.6%) and specificity of 70% (95% CI 59.9% to 80.7%). FLI showed an area under the curve (AUC) of 0.762, while our models achieved higher AUCs: 0.878 (with ultrasound) and 0.794 (without ultrasound).

Discussion: Our models offer screening tools for SLD in low-resource primary care. The model without ultrasound outperformed FLI, making it a feasible alternative where imaging is unavailable. The ultrasound-based model demonstrated higher performance, underscoring the value of ultrasound when it is accessible. Integrating these algorithms into preventive programmes could improve early diagnosis, especially in populations with a high burden of obesity and diabetes.

Conclusions: We developed two predictive models for SLD screening in a Chilean cohort. Both showed strong performance and potential for implementation in primary care to support early detection and better disease management.

Objectives: Little research focuses on mechanisms underlying the well-recognised relationship between mental and physical health, or its potential to influence adherence and response to treatments. This short report summarises results of the National Institute for Health and Care Research-funded 'Core Mental Health Data Set (CMHDS)' study to embed a digital tool for routine collection of mental health data in physical health studies.

Methods: Four chief investigators of physical health trials were approached to embed the CMHDS into their study. Two trials, one for people receiving specialist cystic fibrosis (CF) care, and the established Salford Kidney Study (SKS) successfully managed to embed CMHDS.

Results: A combined 478 participants from both studies were invited to complete the CMHDS. Of those approached, 88% agreed to complete CMHDS; 44% completed it. In the SKS, people who completed CMHDS were significantly younger and had higher estimated glomerular filtration rates and were from least deprived areas. In the CF study, there was no significant difference in characteristics of participants who did or did not complete the tool.

Discussion: It was feasible, and researchers and participants considered it acceptable, to embed the CMHDS in physical health studies as part of routine data collection.

Conclusion: Future studies should embed the CMHDS routinely and encourage completion to minimise bias and optimise the added value of having mental health covariates or predictor variables in physical health studies.