BMJ Health & Care Informatics最新文献

Objectives: To develop and validate a tool for standardised quality assessment of data-driven algorithms in healthcare, focusing on the underlying data pipeline.

Methods: Data Assessment Tool for Algorithm Critical Appraisal and Robust Evidence (DATA-CARE) was iteratively developed from the established Quality In Prognosis Studies framework, selected after reviewing 10 existing quality assessment tools for observational and artificial intelligence studies. DATA-CARE evaluates five quality domains of the data pipeline: study population, data, algorithm, outcome and report transparency. Each domain comprises three to five quality criteria. With a total score of 75 points, study quality is categorised as low (<45), moderate (45-59) or high (≥60). DATA-CARE was validated during a systematic review on data-driven algorithms using continuous physiological monitoring data within the paediatric intensive care unit. Two independent reviewers performed quality assessment using DATA-CARE of included studies. Tool validation was evaluated using inter-rater agreement and intraclass correlation coefficient (ICC).

Results: DATA-CARE demonstrated robust inter-rater agreement (93.5%) with ICC 0.98 (95% CI 0.96 to 0.99). Of 3858 screened studies, 31 were reviewed in the use case, describing diverse algorithms. Studies were predominantly low (32.3%) to moderate (41.9%) and sporadically (25.8%) high quality.

Discussion: Predominance of low-to-moderate quality studies reveals critical barriers to clinical implementation of data-driven algorithms, including low quality data capture and processing, lacking validation strategies and non-transparent reporting of findings.

Conclusions: DATA-CARE allows standardised and reliable critical appraisal for a wide variety of algorithms, addressing current gaps in standardised and reproducible algorithm development.

Objectives: This study aims to assess electronic health record (EHR) use in physiotherapy, identify factors influencing its adoption and evaluate physiotherapists' perceptions of its relevance.

Methods: A cross-sectional study was conducted with 138 licensed physiotherapists recruited through digital platforms. EHR utilisation was evaluated using the RSEFisio scale, a validated instrument designed to capture multiple dimensions of EHR use in physiotherapy. Descriptive and inferential statistical analyses were applied to examine usage patterns and contextual factors. The study followed the Strengthening the Reporting of Observational Studies in Epidemiology guidelines.

Results: The EHR utilisation rate was 78.3%. Higher utilisation was significantly associated with adequate time allocated for documentation (p=0.001), systematic recording for all patients (p=0.013) and multi-professional access to records (p=0.043). The frequency of documentation was closely linked to the perceived clinical relevance of recorded items.

Discussion: Despite the high level of EHR utilisation, physiotherapy documentation remains incomplete and driven by perceived clinical relevance. Utilisation improves with adequate time, standardised recording and interprofessional access. Inconsistent data quality undermines continuity of care and limits secondary uses, including artificial intelligence integration. Strengthening documentation is essential to improve clinical workflows and support data-driven decision-making in physiotherapy.

Conclusion: Physiotherapists recognise the value of comprehensive documentation, but report limited time and incomplete records. The disconnect between awareness and practice highlights the need for practical, system-level strategies to support more consistent and effective EHR use in physiotherapy.

Surgical care is essential to achieving universal health coverage, yet many African low-income, lower-middle-income countries (LMICs) and upper-middle-income countries - including South Africa-struggle to harness healthcare data for surgical system strengthening. Despite global advocacy efforts and the adoption of surgical indicators such as perioperative mortality rate and surgical volume, fragmented routine health information systems, limited human resource capacity and siloed data architecture hinder effective, data-informed planning and policy. Drawing on a South African case study, this high-level perspective highlights institutional momentum for integrating routine perioperative data into strategic health planning, while also identifying key technical and operational challenges. The study demonstrated the inability of clinician-led initiatives to generate routine perioperative health information to guide practice at an institutional level. To close the implementation gap, a context-adapted approach, that includes participatory network weaving, stakeholder-driven data use cases and collaborative planning for interoperable data systems, is proposed. These elements are positioned within an implementation framework designed to support policy development, guide clinical practice and improve access to safe, high-quality surgical care across African countries. We propose taking advantage of opportunities for concurrent implementation assessment and adaptation of a clinical health information system module for South African surgical patients.

In this time of rapidly-changing science, technology, healthcare and society, the education of aspiring professionals and the training of seasoned practitioners must intentionally place human relationships at the centre of service delivery. Reflecting on our own experiences, gained over many years in practice, we argue that despite the proliferation of technology in every aspect of our lives, both patients and practitioners ultimately desire a human-centric approach. To consider the impact of such a paradigm on the future education needs of those working in data-driven and technology-enabled care, a multifactorial approach is required consisting of seven different dimensions: the changing nature of healthcare relationships; addressing disparities; human-centred design and innovation; effective digital technology education; prioritising professionals' wellbeing through systemic change; working with governments, institutions and other stakeholders; and the implications, ethics and stewardship of shared data. The authors examine each of these areas and propose specific steps that evolving healthcare systems can take to prioritise human relationships and optimise technology to support those relationships. We acknowledge that our gaze is somewhat tinted, reflecting our work in healthcare and the global north. Yet our aim is universal: to celebrate human connections and the art of caring in a digital age.

Objectives: Total hip and knee arthroplasty (THA and TKA, respectively) are effective procedures but are costly and resource intensive. As such, scheduling can have a significant impact on hospitals. The aim of this study was to evaluate the efficiency of a surgical schedule generated using machine learning (ML) and mathematical optimisation to current gold-standard scheduling practices.

Methods: All primary and revision TKA and THA cases between April 2012 and February 2022 from a single institution were included (n=15 267). Data was split by year into training/validation and test sets. Procedure-specific models were trained for predicting operative time. Integer linear programming optimisation of operating room (OR) utilisation using these ML predictions was compared with historic scheduling (using surgeon-surgery-specific rolling average values). Weekly simulated schedules were generated and compared based on OR underutilisation, overtime and cases completed.

Results: The neural network models performed the best for all four procedures (median MSE: 594.6). This was a 7.1% improvement in 15 min buffer accuracy compared with rolling average times. The ML-predicted and optimised schedule reduced OR underutilisation (p<0.0001) and increased the number of cases (p<0.0001). OR underutilisation was reduced by 56.2% (13.3 minutes/day), while only increasing overtime by 17.2% (3.6 minutes/day), compared with the rolling mean. Overall, there was a 6.1% decrease (31 OR days) to complete the cases in the test set.

Discussion: ML-predicted operative times and optimisation has the potential to reduce idle OR time and improve patient throughput.

Conclusion: Approaches to surgical scheduling leveraging data maximises utilisation of existing resources.

Objectives: Chatbot-delivered treatments offer tremendous mental health benefits. This systematic review aimed at examining the effectiveness of using chatbots for improving mental health among people in Asia.

Methods: Randomised controlled trials (RCTs) on standalone chatbot interventions targeting mental health conditions, ranging from mental well-being to clinically relevant mental health symptoms (eg, depression, anxiety, stress, affect, distress, insomnia and psychological well-being), were included. Four electronic databases (PubMed, CINAHL, PsycINFO and Medline) were searched until 11 December 2024.

Results: A total of eight RCTs (n=921) were included. Our meta-analysis results by random-effects models showed that chatbot interventions reduced the severity of depressive symptoms by 0.46 (95% CI -0.76 to -0.16, p=0.002, I²=73%). In the subgroup analyses, chatbot interventions were effective in reducing depression in clinical populations by 0.54 (95% CI -1.02 to -0.07, p=0.02, I²=73%), among Chinese participants by 0.55 (95% CI -0.92 to -0.17, p=0.004, I²=81%), and when being compared with traditional bibliotherapy (eg, paperback books or e-book) by 0.47 (95% CI -0.76 to -0.18, p=0.001, I²=26%). Meanwhile, chatbot interventions were shown to reduce levels of negative affect by 1.95 (95% CI -3.46 to -0.44, p=0.01, I²=0%) versus no treatment. However, no significant effects were found for other mental health outcomes, including anxiety, positive affect and stress. Other relevant mental health outcomes included insomnia, attention deficit symptoms, panic disorder, social phobia, problem gambling and methamphetamine use disorder. No adverse events were reported.

Discussion and conclusion: Chatbot-assisted therapy is a clinically beneficial and safe modality for treating depressive symptoms in the Asian context.

Prospero registration number: CRD42024546316.

Objectives: Data standards and barcoding technologies are implemented in hospitals to uniquely identify objects, people and locations; streamline the management of supplies and inventories; improve efficiency; reduce waste and improve patient safety and quality of care. This study examined the implementation of the Scan4Safety programme at one NHS demonstrator site to understand the hospital experience of adopting these standards, barcoding and related technologies.

Methods: Exploratory case study design, informed by information infrastructure theory, at one Scan4Safety demonstrator site. Semi-structured interviews were conducted with internal and external stakeholders (n=19), and 67 documents related to the Scan4Safety programme were identified. Interview transcripts and documents underwent thematic analysis.

Results: Key enablers for Scan4Safety included allocated funding, government role/regulation, executive buy-in/wide stakeholder involvement, patient focus, agile/adaptive approach and data linkage. Challenges were both internal and external, mainly pertaining to data quality, work-as-done and trade-offs. Mechanisms of anticipated positive outcomes and potential risks were also identified.

Discussion: Scan4Safety benefits are delivered through tracking and tracing capabilities, and automating data capture, alerts and data linkages. For traceability of devices, the benefits depend on the extent to which items are tracked in inventory and consistent barcode scanning at the point of care.

Conclusions: Linked standards for identification of patients, products, places and procedures, across supplies and hospital processes, constitute a wide-ranging information infrastructure with the potential for significant value to patients and the whole health system.

The insights available from linking routine health data have transformative potential for understanding and improving population health and well-being. However, cross-sectoral data linkage in the UK remains challenging, with persistent barriers around governance, interoperability and data quality.This Perspective paper draws on the experiences of the Developing research resources And minimum data set for Care Homes Adoption and use (DACHA) study which linked administrative health and social care records with records from care home software providers for over 700 older adult care home residents, an underserved population in research, in England to build a proof-of-concept minimum dataset.From our learning, we make eight recommendations for researchers, research funders, data owners, data controllers and policymakers to strengthen future data linkage across health and social care. We recommend: (1) sharing metadata to support transparency and efficient reuse; (2) clarifying purposes for data sharing; (3) streamlining information governance processes; (4) recognising the health and social care system as a research partner; (5) resourcing data quality at the point of collection; (6) acknowledging the work needed to adapt routine data for research; (7) standardising core variables for interoperability; and (8) designing linkage for wider public benefit and safe data reuse.Implementing these recommendations would help create a more coherent, efficient and equitable data landscape, realising the potential of existing data to improve care quality, research capacity and population health.