BMJ Health & Care Informatics最新文献

Objectives: The adoption and subsequent implementation of telemonitoring across university hospital settings is a challenging task. This study provides insight into the perceived value of using a nationwide network to support scaling up telemonitoring in university hospitals.

Methods: A qualitative approach was used to evaluate the role of the National eHealth network 'Citrien eHealth programme Implementation and Upscaling (Citrien-2)'. In phase 1, an inventory questionnaire was used to identify successes and lessons learnt. Phase 2 consisted of a semi-structured group interview to develop a deeper understanding about the potential value of the network. Subsequently, we conducted a qualitative content analysis and results were organised into key themes of the non-adoption, abandonment, scale-up, spread and sustainability framework.

Results: In total, 20 participants responded to our questionnaire, and 7 participants participated in our semistructured group interview. Qualitative analysis revealed 28 themes. The network's key value is the collaboration and structured approach it promotes. This serves as a foundation for exchanging ideas, identifying both temporary and sustainable funding, and establishing a robust stakeholder position, all of which serve to act as a catalyst for implementation and scaling up of telemonitoring.

Discussion: Our findings align with known barriers to digital innovation, such as funding and legal issues. Our study shows the value of a nationwide network in overcoming these barriers.

Conclusions: The Citrien-2 nationwide network contributes to scaling up telemonitoring across university settings. Therefore, we recommend that governments and their funding agencies recognise and embrace the power of these nationwide networks in scaling up digital initiatives.

Objective: The aim of this study was to assess how different groups of health professionals evaluated the usability of a new electronic health record (EHR) and to investigate the association between the usability and burnout, insomnia and turnover intention.

Methods: This cross-sectional study included 1424 health professionals who worked at a Norwegian University Hospital. The usability was measured with the System Usability Scale (SUS) 6 months after the previous electronic record was replaced with a more comprehensive, sector-wide, patient-centred EHR in 2022.

Results: The median SUS score was 25 (IQR 12.5-37.5) out of 100 and ranged from 15 (IQR 7.5-25.0) among medical doctors to 40 (IQR 27.6-55.0) among laboratory technicians. Nurses reported a score of 25 (IQR 12.5-40.0). In clinical contexts, the median SUS score ranged from 15 (IQR 10.0-30.0) within radiology to 27.5 (IQR 15.0-42.5) within internal medicine, whereas laboratory medicine reported a score of 37.5 (IQR 27.5-55.0). In multivariable analyses using health professionals in the highest quarter of the SUS as the reference, those in the lowest quarter were more likely to report burnout (OR 3.05, 95% CI 1.86 to 5.00), insomnia (OR 1.72, 95% CI 1.18 to 2.50) and turnover intention (OR 2.35, 95% CI 1.53 to 3.64).

Conclusion: Most health professionals across all occupational groups and clinical contexts reported low usability of a new EHR 6 months after go-live. Those who reported the lowest usability were more likely to report burnout, insomnia and turnover intention.

Background: Chronic kidney disease (CKD) is a global health concern characterised by irreversible renal damage that is often assessed using invasive renal biopsy. Accurate evaluation of interstitial fibrosis and tubular atrophy (IFTA) is crucial for CKD management. This study aimed to leverage machine learning (ML) models to predict IFTA using a combination of ultrasonography (US) images and patient biomarkers.

Methods: We retrospectively collected US images and biomarkers from 632 patients with CKD across three hospitals. The data were subjected to pre-processing, exclusion of sub-optimal images, and feature extraction using a dual-path convolutional neural network. Various ML models, including XGBoost, random forest and logistic regression, were trained and validated using fivefold cross-validation.

Results: The dataset was divided into training and test datasets. For image-level IFTA classification, the best performance was achieved by combining US image features and patient biomarkers, with logistic regression yielding an area under the receiver operating characteristic curve (AUROC) of 99%. At the patient level, logistic regression combining US image features and biomarkers provided an AUROC of 96%. Models trained solely on US image features or biomarkers also exhibited high performance, with AUROC exceeding 80%.

Conclusion: Our artificial intelligence-based approach to IFTA classification demonstrated high accuracy and AUROC across various ML models. By leveraging patient biomarkers alone, this method offers a non-invasive and robust tool for early CKD assessment, demonstrating that biomarkers alone may suffice for accurate predictions without the added complexity of image-derived features.

Objectives: To develop a machine learning-based software as a medical device to predict the endurance and outcomes of peritoneal dialysis (PD) patients in real time using effluent-measured biomarkers of the mesothelial-to-mesenchymal transition (MMT).

Methods: Retrospective, longitudinal, triple blind study in two independent hospitals (Spain), designed under information-theoretical approaches for feature selection and machine learning-based modelling techniques. A total of 151 (train set) and 32 (validation) PD patients in 1979-2022 were included. PD outcomes were analysed in four categories (endurance, exit from PD, cause of PD end, technical failure) by using MMT biomarkers in effluents and clinical databases.

Results: MMT biomarkers and clinical data can predict PD with a mean absolute error of 16.99 months by using an Extra Tree (ET) regressor. Linear discriminant analysis (LDA) discerns among transfer to haemodialysis or death, predicts whether the cause of PD end is ultrafiltration failure (UFF) or cardiovascular disease (CVD) and anticipates the type of CVD (receiver operating characteristic curve under the area>0.71).

Discussion: Our combination of longitudinal PD datasets, attribute shrinkage and gold-standard algorithms with overfitting testing and class imbalance ensures robust predictions in PD. Biomarkers displayed proper mutual information and SHapley values, indicating that MMT processes may have a causal relationship in the development of UFF and CVD.

Conclusions: MMT biomarkers and clinical data may be associated in a causal manner with ultrafiltration failure (local effect) and cardiovascular events (systemic effect) in PD. The machine learning-based software MAUXI provides applicability of ET-LDA models with ≤38 variables to predict PD endurance and type of PD technique failure related to peritoneal membrane deterioration.

Objective: The study aimed to evaluate the top large language models (LLMs) in validated medical knowledge tests in Portuguese.

Methods: This study compared 31 LLMs in the context of solving the national Brazilian medical examination test. The research compared the performance of 23 open-source and 8 proprietary models across 399 multiple-choice questions.

Results: Among the smaller models, Llama 3 8B exhibited the highest success rate, achieving 53.9%, while the medium-sized model Mixtral 8×7B attained a success rate of 63.7%. Conversely, larger models like Llama 3 70B achieved a success rate of 77.5%. Among the proprietary models, GPT-4o and Claude Opus demonstrated superior accuracy, scoring 86.8% and 83.8%, respectively.

Conclusions: 10 out of the 31 LLMs attained better than human level of performance in the Revalida benchmark, with 9 failing to provide coherent answers to the task. Larger models exhibited superior performance overall. However, certain medium-sized LLMs surpassed the performance of some of the larger LLMs.

Objectives: Informed consent forms are important for assisting patients in making informed choices regarding medical procedures. Because of their lengthy nature, complexity and specialised terminology, consent forms usually prove challenging for the general public to comprehend. This pilot study aims to use Chat Generative Pretrained Transformer (ChatGPT), a large language model (LLM), to improve the readability and understandability of a consent form for vaccination.

Methods: The study was conducted in Italy, within the Central Tuscany Local Health Unit. Three different consent forms were selected and approved: the standard consent form currently in use (A), a new form totally generated by ChatGPT (B) and a modified version of the standard form created by ChatGPT (C). Healthcare professionals in the vaccination unit were asked to evaluate the consent forms regarding adequacy, comprehensibility and completeness and to give an overall judgement. The Kruskal-Wallis test and Dunn's test were used to evaluate the median scores of the consent forms across these variables.

Results: Consent forms A and C achieved the top scores in every category; consent form B obtained the lowest score. The median scores were 4.0 for adequacy on consent forms A and C and 3.0 on consent form B. Consent forms A and C received high overall judgement ratings with median scores of 4.0, whereas consent form B received a median score of 3.0.

Conclusions: The findings indicate that LLM tools such as ChatGPT could enhance healthcare communication by improving the clarity and accessibility of consent forms, but the best results are seen when these tools are combined with human knowledge and supervision.

Introduction: This protocol outlines a mixed methods study evaluating a new Digital Coordination Centre (DCC) at the Royal Melbourne Hospital (RMH), Melbourne, Australia. While coordination centres show potential for impact, evidence on effective implementation in the Australian context remains scarce. This study aims to address this gap.

Methods and analysis: The evaluation involves a two-stage approach: a process evaluation to clarify DCC design and identify implementation factors, and an initial outcome evaluation to assess short and medium term outcomes. A developmental approach will support continuous improvement, and implementation science theories applied to unpack change processes. Data sources will include interviews, project documentation and observations, with qualitative and quantitative analyses targeting metrics like emergency department boarding and length of stay.

Ethics and dissemination: This study has been approved by the RMH Human Research Ethics Committee (QA2023089). Findings will be shared through peer-reviewed publications and conference presentations.

Study objectives: This study evaluates the feasibility and accuracy of a pragmatic approach to predicting hospital bed occupancy for COVID-19-positive patients, using only simple methods accessible to typical health system teams.

Methods: We used an observational forecasting design for the study period 1st June 2021 to -21st January 2022. Evaluation data covered individuals registered with a general practitioner in North West London, through the Whole Systems Integrated Care deidentified dataset. We extracted data on COVID-19-positive tests, vaccination records and admissions to hospitals with confirmed COVID-19 within the study period. We used linear regression models to predict bed occupancy, using lagged, smoothed numbers of COVID-19 cases among unvaccinated individuals in the community as the predictor. We used mean absolute percentage error (MAPE) to assess model accuracy.

Results: Model accuracy varied throughout the study period, with a MAPE of 10.8% from 12 July 2021 to 18 October 2021, rising to 20.0% over the subsequent period to 15 December 2021. After that, model accuracy deteriorated considerably, with MAPE 110.4% from December 2021 to 21 January 2022. Model outputs were used by senior healthcare system leaders to aid the planning, organisation and provision of healthcare services to meet demand for hospital beds.

Conclusions: The model produced useful predictions of COVID-19-positive bed occupancy prior to the emergence of the Omicron variant, but accuracy deteriorated after this. In practice, the model offers a pragmatic approach to predicting bed occupancy within a pandemic wave. However, this approach requires continual monitoring of errors to ensure that the periods of poor performance are identified quickly.