BMJ Health & Care Informatics最新文献

Objectives: The study aims to evaluate the effectiveness of nature-based virtual reality (NBVR) interventions in alleviating physical symptoms (eg, pain, fatigue, nausea) and mental symptoms (eg, anxiety, depression, distress) in patients with cancer undergoing chemotherapy.

Methods: This systematic review protocol is developed in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. We will conduct a comprehensive electronic search of healthcare databases for studies published in English from 2012 to February 2025. The databases to be searched include PubMed, EMBASE, Web of Science, PsycINFO, Allied and Complementary Medicine, CINAHL Complete and Cochrane Library. We will include randomised controlled trials investigating NBVR aimed at improving the physical and psychological outcomes for patients with cancer during chemotherapy, compared with waitlist controls or traditional methods. The risk of bias will be systematically evaluated using the Cochrane Risk of Bias tool.

Results: As this is a protocol, no results are available yet. The review will present quantitative and qualitative syntheses of NBVR effects on physical and psychological outcomes in chemotherapy patients.

Discussion: By evaluating rigorously designed trials, this review will clarify the potential of NBVR as a supportive intervention for patients with cancer during chemotherapy. Findings are expected to inform clinical practice and guide future research directions in integrating immersive natural environments into cancer care.

Conclusion: This systematic review will provide comprehensive evidence on NBVR interventions for patients with cancer receiving chemotherapy, highlighting their potential benefits for physical symptom relief and mental health improvement.

Prospero registration number: CRD420251016213.

Background: Automatic analysis of free-text patient comments enables the efficient processing of large feedback volumes, reducing reliance on manual review. A 2021 review examined natural language processing (NLP) and sentiment analysis (SA) in patient experience research; however, recent advances in deep learning and generative artificial intelligence (AI) call for an updated synthesis.

Objectives: This scoping review aims to map and summarise recent studies applying SA to unstructured patient experience data related to healthcare services.

Methods: Following Joanna Briggs Institute methodology and PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines, we conducted a comprehensive search across Medline, CINAHL, Web of Science, Cochrane, Embase and APA PsycINFO. We included studies published from January 2020 to March 2024 in English or a Scandinavian language. Eligible studies analysed patient feedback using NLP techniques and described the development or validation of SA models. Two reviewers independently screened the studies and extracted data, which were presented in tables both tabular and narrative forms.

Results: 30 studies were included, primarily from the USA, Europe and Asia. Patient comments were mostly sourced from online platforms such as social media. Feedback largely concerned hospital care. 18 studies employed rule-based SA approaches, while 12 applied supervised machine learning (ML) and only 4 studies used deep learning models. Few addressed the visualisation or practical applications in healthcare.

Conclusion: Despite significant progress, modern methods like deep learning and generative AI remain underused in SA of patient-experience data. Limited focus on implementation restricts SA's role in quality improvement. Future research should assess advanced methods and their cost-effectiveness versus traditional ML.

Objective: Significant variations exist in computable phenotype definitions to identify patients with type 2 diabetes (T2D) using electronic health records (EHRs). These variations cause challenges in identifying T2D populations for clinical research. To address these challenges, this study compares the variations in common phenotypes in identifying patients with T2D using EHRs.

Methods: A retrospective data analysis was performed using clinical data extracted from EHRs of 207 813 adult patients captured 2017-2019. Multiple T2D phenotypes were used: (1) Surveillance, Prevention and Management of Diabetes Mellitus, (2) Centers for Medicare and Medicaid Services Chronic Conditions Data Warehouse (CCW), (3) eMERGE Northwestern Group, (4) Durham Diabetes Coalition (DDC) and (5) a definition developed by a panel of experts at Johns Hopkins.

Results: Each phenotype definition identified a different T2D population with a unique composition of demographics and clinical features. Although the identified patients overlapped across phenotypes, only 22.7% (47 326) of the population was commonly identified across all definitions. Of the phenotypes, DDC identified the greatest number of patients with T2D (139 832, 67.3%), while CCW had the highest mean age (65.3 years), the highest percentage of black patients (35%) and the highest mean Charlson comorbidity score of 2.96. DDC identified patients with T2D with the lowest means of inpatient (0.64) and emergency room (1.06) visits.

Conclusion: Our study highlights the complexity of computable T2D phenotypes in translating commonly agreed T2D clinical definitions when applied against retrospective EHR data. Our findings provide an understanding of using appropriate phenotypes to identify, enrol and analyse T2D populations of interest using EHR data.

Objectives: To develop a machine learning (ML)-based predictive model for assessing the risk of pre-eclampsia using routinely collected clinical data.

Methods: We retrospectively analysed data from 2444 pregnant women who delivered at Chi Mei Medical Center between 2015 and 2019, excluding patients under 20 years old. Pre-eclampsia was defined as blood pressure >140/90 mm Hg with proteinuria. Key features included gestational age, body weight, blood pressure and medical history. Five ML models were trained-logistic regression, random forest, light gradient boosting machine, extreme gradient boosting (XGBoost) and multilayer perceptron-using a 70/30 train-validation split. Synthetic minority oversampling technique was applied to address class imbalance. SHapley Additive exPlanations (SHAP) analysis was used for feature importance.

Results: Among the five models, XGBoost showed the best performance with the highest accuracy, sensitivity, specificity and an area under the receiver operating characteristics curve of 0.921. SHAP analysis identified diastolic blood pressure, systolic blood pressure and urine glucose as top predictors.

Discussion: Our findings demonstrate that ML, particularly XGBoost, can effectively predict the risk of pre-eclampsia using standard clinical data. This approach avoids the need for expensive tests while maintaining high accuracy.

Conclusion: The XGBoost model offers a cost-effective and accurate method for pre-eclampsia risk prediction, enabling real-time assessment and supporting early intervention. Future studies will focus on larger data sets and clinical integration.

Objectives: Rapid discrimination of infections caused by Mycobacterium tuberculosis (MTB) and non-tuberculous mycobacteria (NTM) is crucial in clinical settings. Despite overlapping clinical and radiological features, the two require markedly different therapeutic approaches and public health responses. Current laboratory methods are time-consuming and complex, underscoring the urgent need for a simple and efficient diagnostic tool to inform public health decision-making.

Methods: Demographic, haematological and biochemical data were collected from two hospitals in Jiangsu province, China, between December 2018 and October 2024. A total of 400 patients were included in the training cohort, with 66 patients used for external validation. Six machine learning models were developed using routine laboratory features, and their performance was evaluated using multiple metrics.

Results: The random forest (RF) model outperformed others using 49 routine lab features, achieving 82.71% accuracy in the internal cohort and 87.69% in external validation. SHapley Additive exPlanations (SHAP) model identified the top 10 critical features influencing model decisions, namely, chloride, sodium, gender, prealbumin, high-density lipoprotein, procalcitonin, albumin, globulin, total protein and creatine. Based on these indicators, an interactive web-based tool was developed (https://mtb-ntm.streamlit.app).

Discussion: The features identified by the model align with established clinical parameters and existing studies. Certain previously underestimated variables, such as Cl and Na, exhibited substantial importance in distinguishing between MTB and NTM, offering valuable insights for the development of decision-support tools.

Conclusion: Routine laboratory indicators coupled with the RF model demonstrated potential capacity as an auxiliary diagnostic tool for discriminating MTB and NTM disease, offering effective medical support in resource-limited and remote settings.

Objectives: To describe the implementation of a multidisciplinary, ethically grounded hackathon as a model to develop and evaluate generative AI (GenAI) solutions for real-world clinical challenges within a hospital setting.

Methods: The GenAI Health Hackathon (GAHH) organised at Hospital Clínic de Barcelona included 13 challenges were selected via an internal call based on clinical impact, feasibility and data availability. Participants accessed anonymised real-world data through a secure cloud environment. Teams employed large language models and retrieval-augmented generation to build prototypes addressing tasks such as clinical text structuring, decision support and workflow automation. Human-in-the-loop validation, explainability and regulatory safeguards were emphasised.

Results: The hackathon yielded multiple AI prototypes tested on real data. Results varied: entity recognition reached 90.5% accuracy, summarisation >90% clinician concordance and nutritional models achieved F1 scores of 0.75-0.93. Lower scores (F1<0.52, Jaccard Index <0.4) were seen in complex reasoning or multilingual tasks. Bias was explored in 10 projects, with mitigations such as stratified sampling, prompt tuning, disclaimers and expert oversight. A transferable framework was proposed to replicate responsible GenAI hackathons in clinical contexts.

Discussion: Interdisciplinary collaboration and real-world testing proved essential for aligning GenAI with clinical needs. The hackathon revealed challenges in bias, evaluation and integration but offered a transferable framework for responsible innovation under General Data Protection Regulation and the European Union Artificial Intelligence Act.

Conclusions: The GAHH demonstrated that GenAI can be safely and effectively applied in healthcare with rigorous governance and interdisciplinary collaboration, offering a scalable model for responsible AI innovation.

Objectives: Antimicrobial resistance is a critical public health threat. Large language models (LLMs) show great capability for providing health information. This study evaluates the effectiveness of LLMs in providing information on antibiotic use and infection management.

Methods: Using a mixed-method approach, responses to healthcare expert-designed scenarios from ChatGPT 3.5, ChatGPT 4.0, Claude 2.0 and Gemini 1.0, in both Italian and English, were analysed. Computational text analysis assessed readability, lexical diversity and sentiment, while content quality was assessed by three experts via DISCERN tool.

Results: 16 scenarios were developed. A total of 101 outputs and 5454 Likert-scale (1-5) scores were obtained for the analysis. A general positive performance gradient was found from ChatGPT 3.5 and 4.0 to Claude to Gemini. Gemini, although producing only five outputs before self-inhibition, consistently outperformed the other models across almost all metrics, producing more detailed, accessible, varied content and a positive overtone. ChatGPT 4.0 demonstrated the highest lexical diversity. A difference in performance by language was observed. All models showed a median score of 1 (IQR=2) regarding the domain addressing antimicrobial resistance.

Discussion: The study highlights a positive performance gradient towards Gemini, which showed superior content quality, accessibility and contextual awareness, although acknowledging its smaller dataset. Generating appropriate content to address antimicrobial resistance proved challenging.

Conclusions: LLMs offer great promise to provide appropriate medical information. However, they should play a supporting role rather than representing a replacement option for medical professionals, confirming the need for expert oversight and improved artificial intelligence design.

Objectives: To evaluate the impact of implementing a multidisciplinary integrated telehealth platform in central Taiwan on healthcare accessibility, emergency response and chronic disease management.

Methods: We analysed data from 26 institutions within a central Taiwan telehealth network between 2022 and 2024. The study evaluated the use and benefits of teleconsultation, artificial intelligence-assisted ECG monitoring during prehospital ambulance transfers and outcomes in patients with cryptogenic stroke following the platform integration. Satisfaction surveys were performed.

Results: By 2024, more than 300 teleconsultations were performed across 26 partner facilities. Non-emergent referral rates fell from 30% in 2022 to 10% in 2024 following teleconsultations. Emergent stroke teleconsultations allowed thrombolytic therapy within the golden hour in 83% of cases. At-home ECG monitoring helped detect atrial fibrillation in 25% of cryptogenic stroke patients within 2 weeks, ensuring timely recall and initiation of appropriate antiarrhythmic therapy to prevent recurrent stroke. Surveys indicated that 83% of healthcare providers and patients were satisfied with telehealth services.

Discussion: The single-centre study showcases a multidisciplinary integrated telehealth model. However, confounders existed, including changes in the healthcare system, selection bias and technology disparities. Satisfaction data may be biased. The short timeframe precludes long-term analysis, underscoring the need for broader, controlled studies to assess the sustained impact of telehealth.

Conclusion: The integrated telehealth centre model provides a scalable and replicable approach for healthcare delivery. Studies for long-term benefits and outcomes will help improve telehealth models.

Study objectives: Chronic wounds represent a significant economic and personal burden. For their successful treatment, the causes must be known and treated. Wounds caused by pyoderma gangrenosum (PG), a rare inflammatory skin disease, are often misdiagnosed. This study, therefore, aims to develop a machine learning model capable of differentiating PG from other wound types, focusing on chronic leg wounds to address this diagnostic challenge.

Methods: We used 3674 wound photographs from three specialised wound centres with the four most common types of foot and leg ulcers and the rare inflammatory differential diagnosis PG. The convolutional neural network classifier ConvNeXt 'B' was pretrained on LAION2B, ImageNet12k and ImageNet 1k before being trained and fine-tuned on an 85:15 train, validation split.

Results: The model achieved an overall high accuracy in multiclass classification of the chronic wounds (unbalanced accuracy 90%, balanced accuracy 87%). The sensitivity for identifying PG was 94%, while the sensitivity forother chronic wound types was 97% for diabetic foot ulcers (DFU), 92% for venous leg ulcers (VLU), 78% for mixed leg ulcers and 74% for arterial leg ulcers.

Discussion: The machine learning model effectively differentiates PG from the most common leg and foot ulcers and was very accurate for classifying DFU and VLU. A higher rate of misclassifications occurred for the other vascular ulcers, that is, mixed and arterial leg ulcers. This aligns with the challenges in clinical practice.

Conclusion: Despite the limited number of wound images, this novel multiclass wound classification model accurately identified PG and differentiated leg and foot ulcer subtypes, providing a foundation for a diagnostic support system.

Objective: The increasing burden of hypertension in Africa underscores the need to embrace digital health innovations to improve delivery and access to quality hypertension care. This review aimed at (1) identifying barriers and facilitators to the implementation and uptake of digital health tools and (2) examining the scope and use of digital health tools based on the Practical Reviews in Self-Management Support (PRISMS) taxonomy.

Materials and methods: We searched PubMed, CINAHL (Medline) and HINARI from inception to June 2024. The Joanna Briggs Institute (Population, Concept, and Context (PCC)) framework guided the formulation of research questions, and the PRISMS taxonomy was used to analyse the functions of digital tools.

Results: Sixteen studies (k=16) across three African regions were included. Common digital health tools were mobile Health (mHealth) or electronic Health applications and short message service (SMS)-based interventions. Supported self-management functions included medication adherence (k=10), lifestyle counselling (k=12) and home blood pressure monitoring (k=9). Implementation strategies included prior training (k=10), continuous digital support (k=10) and provision of resources including BP devices and data credit (k=11). Targeted users were healthcare workers (k=8), patients (k=11) or both (k=3). Barriers included limited digital literacy, poor communication among healthcare workers, privacy concerns and weak internet infrastructure. Facilitators included competency-based training, contextual adaptations, continuous technical support and enhanced user experience through effective feedback systems between users.

Conclusion: Digital health tools, particularly mHealth apps and SMS, support key hypertension self-management tasks in African settings. Addressing technological and contextual barriers while reinforcing training and support systems is critical to successful implementation and scale-up.