BMJ Health & Care Informatics最新文献

Introduction: This study seeks to determine incidence, comorbidities and drivers for new HIV infections to develop, test and validate a risk prediction model for screening for new cases of HIV.

Methods and analysis: The study has two components: a cross-sectional study to develop the prediction model using the HIV dataset from the Kenya AIDS and STI Control Programme and a 15-month prospective study for the validation of the model. Inferential analysis will be conducted using algorithms that perform best in disease prediction: Extreme Gradient Boosting (XGBoost) and Multilayer Perceptron. Model sensitivity and specificity will be examined using the receiver operating characteristic curve, and performance will be evaluated using metrics: accuracy, precision, recall and F1 score.

Ethics and dissemination: The study obtained ethical approval (JKU/ISERC/02321/1421) from the Jomo Kenyatta University of Agriculture and Technology Ethical and Research Board and a research licence (NACOSTI/P/24/414749) from the National Commission for Science, Technology and Innovation.

Objective: To evaluate the transferability of BERT (Bidirectional Encoder Representations from Transformers) to patient safety, we use it to classify incident reports characterised by limited data and encompassing multiple imbalanced classes.

Methods: BERT was applied to classify 10 incident types and 4 severity levels by (1) fine-tuning and (2) extracting word embeddings for feature representation. Training datasets were collected from a state-wide incident reporting system in Australia (n_type/severity=2860/1160). Transferability was evaluated using three datasets: a balanced dataset (type/severity: n_benchmark=286/116); a real-world imbalanced dataset (n_original=444/4837, rare types/severity<=1%); and an independent hospital-level reporting system (n_independent=6000/5950, imbalanced). Model performance was evaluated by F-score, precision and recall, then compared with convolutional neural networks (CNNs) using BERT embeddings and local embeddings from incident reports.

Results: Fine-tuned BERT outperformed small CNNs trained with BERT embedding and static word embeddings developed from scratch. The default parameters of BERT were found to be the most optimal configuration. For incident type, fine-tuned BERT achieved high F-scores above 89% across all test datasets (CNNs=81%). It effectively generalised to real-world settings, including rare incident types (eg, clinical handover with 11.1% and 30.3% improvement). For ambiguous medium and low severity levels, the F-score improvements ranged from 3.6% to 19.7% across all test datasets.

Discussion: Fine-tuned BERT led to improved performance, particularly in identifying rare classes and generalising effectively to unseen data, compared with small CNNs.

Conclusion: Fine-tuned BERT may be useful for classification tasks in patient safety where data privacy, scarcity and imbalance are common challenges.

Introduction: The second iteration of the National Early Warning Score has been adopted widely within the UK and internationally. It uses routinely collected physiological measurements to standardise the assessment and response to acute illness. Its use is associated with reduced mortality but has limited positive and negative predictive accuracy. There is a growing body of research demonstrating the effectiveness of artificial intelligence (AI) in predicting clinical deterioration, but there is limited evidence to show which aspect of AI is best suited to this task. This systematic review aims to establish which AI or machine learning algorithm is best suited to analysing physiological data sets to predict patient deterioration in a hospital setting.

Methods and analysis: A systematic review will be conducted in accordance with the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analysis) and the PICOS (Population, Intervention, Comparator, Outcome and Study) frameworks. Eight databases (PubMed, Embase, CINAHL, Cochrane Library, Web of Science, Scopus, IEEE Xplore and ACM Digital Library) will be used to search for studies published from 2007 to the present that meet the inclusion criteria. Two reviewers will screen the studies identified and extract data independently, with any discrepancies resolved by discussion. The review is expected to be completed by January 2026, and the results will be presented in publication by June 2026.

Ethics and dissemination: Ethical approval is not required as data will be obtained from published sources. Findings from this study will be disseminated via publication in a peer-reviewed journal.

Introduction: To address timely care in emergency departments, artificial neural networks (ANNs) with natural language processing will be applied to triage notes to predict patient disposition. This study will develop a predictive model that predicts disposition and type of admission.

Methods and analysis: This will include data preprocessing and quality enhancement, masked language modelling, ANN-based fusion network for prediction. Generative artificial intelligence, along with a medical dictionary, will be employed to augment and contextually reconstruct triage notes to disambiguate and improve linguistic quality. Text features will be extracted, and cluster analysis will be performed on the extracted topics and text features to identify distinct patterns.

Objectives: Identifying whether there is a traumatic intracranial bleed (ICB+) on head CT is critical for clinical care and research. Free text CT reports are unstructured and therefore must undergo time-consuming manual review. Existing artificial intelligence classification schemes are not optimised for the emergency department endpoint of classification of ICB+ or ICB-. We sought to assess three methods for classifying CT reports: a text classification (TC) programme, a commercial natural language processing programme (Clinithink) and a generative pretrained transformer large language model (Digitalizing English-language CT Interpretation for Positive Haemorrhage Evaluation Reporting (DECIPHER)-LLM).

Methods: Primary objective: determine the diagnostic classification performance of the dichotomous categorisation of each of the three approaches.

Secondary objective: determine whether the LLM could achieve a substantial reduction in CT report review workload while maintaining 100% sensitivity.Anonymised radiology reports of head CT scans performed for trauma were manually labelled as ICB+/-. Training and validation sets were randomly created to train the TC and natural language processing models. Prompts were written to train the LLM.

Results: 898 reports were manually labelled. Sensitivity and specificity (95% CI)) of TC, Clinithink and DECIPHER-LLM (with probability of ICB set at 10%) were respectively 87.9% (76.7% to 95.0%) and 98.2% (96.3% to 99.3%), 75.9% (62.8% to 86.1%) and 96.2% (93.8% to 97.8%) and 100% (93.8% to 100%) and 97.4% (95.3% to 98.8%).With DECIPHER-LLM probability of ICB+ threshold of 10% set to identify CT reports requiring manual evaluation, CT reports requiring manual classification reduced by an estimated 385/449 cases (85.7% (95% CI 82.1% to 88.9%)) while maintaining 100% sensitivity.

Discussion and conclusion: DECIPHER-LLM outperformed other tested free-text classification methods.

Objectives: To develop and evaluate an agentic retrieval augmented generation (ARAG) framework using open-source large language models (LLMs) for generating evidence-based Arabic patient education materials (PEMs) and assess the LLMs capabilities as validation agents tasked with blocking harmful content.

Methods: We selected 12 LLMs and applied four experimental setups (base, base+prompt engineering, ARAG, and ARAG+prompt engineering). PEM generation quality was assessed via two-stage evaluation (automated LLM, then expert review) using 5 metrics (accuracy, readability, comprehensiveness, appropriateness and safety) against ground truth. Validation agent (VA) performance was evaluated separately using a harmful/safe PEM dataset, measuring blocking accuracy.

Results: ARAG-enabled setups yielded the best generation performance for 10/12 LLMs. Arabic-focused models occupied the top 9 ranks. Expert evaluation ranking mirrored the automated ranking. AceGPT-v2-32B with ARAG and prompt engineering (setup 4) was confirmed highest-performing. VA accuracy correlated strongly with model size; only models ≥27B parameters achieved >0.80 accuracy. Fanar-7B performed well in generation but poorly as a VA.

Discussion: Arabic-centred models demonstrated advantages for the Arabic PEM generation task. ARAG enhanced generation quality, although context limits impacted large-context models. The validation task highlighted model size as critical for reliable performance.

Conclusion: ARAG noticeably improves Arabic PEM generation, particularly with Arabic-centred models like AceGPT-v2-32B. Larger models appear necessary for reliable harmful content validation. Automated evaluation showed potential for ranking systems, aligning with expert judgement for top performers.

This research presents key findings from a project exploring UK doctors' perspectives on artificial intelligence (AI) in their work. Despite a growing interest in the use of AI in medicine, studies have yet to explore a representative sample of doctors' perspectives on, and experiences with, making use of different types of AI. Our research seeks to fill this gap by presenting findings from a survey exploring doctors' perceptions and experiences of using a variety of AI systems in their work. A sample of 929 doctors on the UK medical register participated in a survey between December 2023 and January 2024 which asked a range of questions about their understanding and use of AI systems.Overall, 29% of respondents reported using some form of AI in their practice within the last 12 months, with diagnostic-decision-support (16%) and generative-AI (16%) being the most prevalently used AI systems.We found that the majority of generative-AI users (62%) reported that these systems increase their productivity, and most diagnostic- decision-support users (62%) reported that the systems improve their clinical decision-making. More than half of doctors (52%) were optimistic about the integration of AI in healthcare, rising to 63% for AI users. Only 15% stated that advances in AI make them worried about their job security, with no significant difference between AI and non-AI users. However, there were relatively low reported levels of training, as well as understandings of risks and professional responsibilities, especially among generative-AI users. Just 12% of respondents agreed they have received sufficient training to understand their professional responsibilities when using AI, with this number decreasing to 8% for generative-AI users. We hope this work adds to the evidence base for policy-makers looking to support the integration of AI in healthcare.

Objectives: Atrial fibrillation (AF) requires comprehensive management due to its complex nature. The Atrial Fibrillation Better Care (ABC) pathway, introduced in the 2020 European Society of Cardiology Guidelines, has demonstrated clinical benefits, yet adherence remains suboptimal. This study evaluates the impact of establishing an Atrial Fibrillation Centre (AFC) on ABC pathway adherence in a Chinese teaching hospital.

Methods: This study employed an interrupted time series analysis to assess monthly ABC pathway adherence rates before and after AFC construction. The analysis focused on anticoagulation (A), better symptom control (B) and comorbidity management (C).

Results: Following AFC establishment, the hospital-wide ABC adherence rate increased by 11.82%, with a sustained monthly increase of 0.27%. Improvements were primarily observed in cardiology and internal medicine departments, whereas surgical departments showed minimal change. Anticoagulation and symptom control adherence improved significantly, while comorbidity management remained unchanged.

Discussion: The AFC improved ABC pathway adherence through standardised, multidisciplinary AF management. Significant gains in anticoagulation and symptom control were observed, but rhythm control and comorbidity management remained suboptimal. Barriers include limited ablation access and fragmented care. Future efforts should enhance interdisciplinary collaboration, expand procedural accessibility and integrate long-term cardiovascular risk management to optimise AF care.

Conclusion: Establishing an AFC significantly improved ABC pathway adherence, which proved effective in both stroke prevention and symptom management, particularly in cardiology and internal medicine departments. Future efforts should focus on enhancing rhythm control strategies and optimising comorbidity management to further improve integrated AF care.

Trial registration number: MR-50-24-014759.

Objectives: Using the routine health data in decision-making improves the health service delivery and health system performance. This study was aimed at identifying the level of information utilisation and associated factors in the Routine Health Information Systems (RHIS).

Methods: A concurrent triangulation design of a mixed-methods approach was applied from 1 to 30 April 2023. A sample of 304 health workers was randomly selected, and 18 informants were purposefully interviewed. Standardised Performance of Routine Information System Management tools were used. Multilevel linear mixed model regression and thematic analysis were conducted.

Results: The level of good information utilisation in RHIS was 52.0% (95% CI: 46.2%, 57.7%, p = 0.491). Data visualisation (β=0.053, 95% CI: 0.006, 0.101, p = 0.027), data quality assessment (β=0.054, 95% CI: 0.018, 0.090, p = 0.003), supervision (β=0.135, 95% CI: 0.072, 0.198, p < 0.001), management support (β=0.065, 95% CI: 0.001, 0.129, p = 0.045) and data management skills (β=0.070, 95% CI: 0.023, 0.118, p = 0.004) were significant positive predictors of information utilisation. Conversely, information utilisation decreased in health posts (β=-0.082, 95% CI: -0.160, -0.005, p = 0.037). This finding was further supported by the qualitative data.

Discussion: The level of information utilisation was consistent with other studies in Ethiopia, although previous studies excluded health posts. Data visualisation, institutional management support, type of health institution, conducting data quality assessment, supervision quality and data management skills were significant predictors of information utilisation in the RHIS. Differences in health worker skills and stronger district-level monitoring systems likely explained variation in information utilisation across different types of health institutions.

Conclusion: The utilisation of routine health information was lower. Providing quality supervision, improving the data management skills of health workers and conducting data quality assessments are essential and suggested interventions for enhancing information utilisation.

Objectives: To evaluate whether adherence to oral bisphosphonate in patients with osteoporosis may be improved by teleconsultation (TC) with or without combined use of email to contact the bone specialist on-demand (enhanced TC).

Methods: 103 naïve patients with osteoporosis were prescribed branded alendronate (70 mg weekly) and randomised to three service modalities (presence, TC and enhanced TC), and evaluated for medication adherence after 12 months of follow-up. Patients allocated to the enhanced TC were provided with the opportunity to contact the bone specialists by email without any restriction. Patient-reported outcome(PROMs) and experience measures (PREMs) were evaluated with respect to the service modality.

Results: Of 89 patients who were persistent to therapy, 66% displayed optimal medication adherence, with odds being 4.5 higher in patients receiving enhanced TC versus those receiving the other services. TC service modality was considered in general to be worse in quality than in presence visits, whereas the combination with email use as in enhanced TC was sufficient to compensate for the perceived decrease in quality of care. Enhanced TC did not have any impact on the perception of quality of life as assessed by PROMs.

Discussion: In patients with osteoporosis, TC did not provide any advantage over traditional in presence visits in terms of improvement of adherence to therapy. However, when TC was combined with email to contact the bone specialist on demand, there was a significant improvement in adherence to the prescribed drug.

Conclusions: Patients with osteoporosis need to be supported after drug prescription to guarantee optimal medication therapy.