BMJ Health & Care Informatics最新文献

{"title":"Artificial intelligence for predicting interstitial fibrosis and tubular atrophy using diagnostic ultrasound imaging and biomarkers.","authors":"Ting-Wei Chang, Chang-Yu Tsai, Zhen-Yi Tang, Cai-Mei Zheng, Chia-Te Liao, Chung-Yi Cheng, Mai-Szu Wu, Che-Chou Shen, Yen-Chung Lin","doi":"10.1136/bmjhci-2024-101192","DOIUrl":"https://doi.org/10.1136/bmjhci-2024-101192","url":null,"abstract":"<p><strong>Background: </strong>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.</p><p><strong>Methods: </strong>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.</p><p><strong>Results: </strong>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%.</p><p><strong>Conclusion: </strong>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.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"32 1","pages":""},"PeriodicalIF":4.1,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143647065","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Data's big three: how learning health systems, artificial intelligence and predictive analytics are transforming healthcare.","authors":"Kerryn Butler-Henderson, Salma Arabi, Wei Wang","doi":"10.1136/bmjhci-2024-101414","DOIUrl":"10.1136/bmjhci-2024-101414","url":null,"abstract":"","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"32 1","pages":""},"PeriodicalIF":4.1,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11907027/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143630107","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Biomarker and clinical data-based predictor tool (MAUXI) for ultrafiltration failure and cardiovascular outcome in peritoneal dialysis patients: a retrospective and longitudinal study.","authors":"Eva María Arriero-País, María Auxiliadora Bajo-Rubio, Roberto Arrojo-García, Pilar Sandoval, Guadalupe Tirma González-Mateo, Patricia Albar-Vizcaíno, Gloria Del Peso-Gilsanz, Marta Ossorio-González, Pedro Majano, Manuel López-Cabrera","doi":"10.1136/bmjhci-2024-101138","DOIUrl":"10.1136/bmjhci-2024-101138","url":null,"abstract":"<p><strong>Objectives: </strong>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).</p><p><strong>Methods: </strong>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.</p><p><strong>Results: </strong>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).</p><p><strong>Discussion: </strong>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.</p><p><strong>Conclusions: </strong>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.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"32 1","pages":""},"PeriodicalIF":4.1,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11873327/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143530876","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Benchmarking open-source large language models on Portuguese Revalida multiple-choice questions.","authors":"João Victor Bruneti Severino, Pedro Angelo Basei de Paula, Matheus Nespolo Berger, Filipe Silveira Loures, Solano Amadori Todeschini, Eduardo Augusto Roeder, Maria Han Veiga, Murilo Guedes, Gustavo Lenci Marques","doi":"10.1136/bmjhci-2024-101195","DOIUrl":"https://doi.org/10.1136/bmjhci-2024-101195","url":null,"abstract":"<p><strong>Objective: </strong>The study aimed to evaluate the top large language models (LLMs) in validated medical knowledge tests in Portuguese.</p><p><strong>Methods: </strong>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.</p><p><strong>Results: </strong>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.</p><p><strong>Conclusions: </strong>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.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"32 1","pages":""},"PeriodicalIF":4.1,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143499016","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Potential role of ChatGPT in simplifying and improving informed consent forms for vaccination: a pilot study conducted in Italy.","authors":"Claudia Cosma, Alessio Radi, Rachele Cattano, Patrizio Zanobini, Guglielmo Bonaccorsi, Chiara Lorini, Marco Del Riccio","doi":"10.1136/bmjhci-2024-101248","DOIUrl":"10.1136/bmjhci-2024-101248","url":null,"abstract":"<p><strong>Objectives: </strong>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.</p><p><strong>Methods: </strong>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.</p><p><strong>Results: </strong>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.</p><p><strong>Conclusions: </strong>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.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"32 1","pages":""},"PeriodicalIF":4.1,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11848659/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143476004","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluating the implementation of a digital coordination centre in an Australian hospital setting: a mixed method study protocol.","authors":"Sam Freeman, Colin Malone, Wynona Black, Daniel Capurro, Wendy W Chapman, Timothy N Fazio, Jana Gazarek, Meredith J Layton, Kayley Lyons, Laura Pumo, Samantha Plumb, Brad Astbury","doi":"10.1136/bmjhci-2024-101300","DOIUrl":"10.1136/bmjhci-2024-101300","url":null,"abstract":"<p><strong>Introduction: </strong>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.</p><p><strong>Methods and analysis: </strong>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.</p><p><strong>Ethics and dissemination: </strong>This study has been approved by the RMH Human Research Ethics Committee (QA2023089). Findings will be shared through peer-reviewed publications and conference presentations.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"32 1","pages":""},"PeriodicalIF":4.1,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11804194/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143363483","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Biodesign in the generative AI era: enhancing innovation and equity with NLP and LLM tools.","authors":"Jowy Tani","doi":"10.1136/bmjhci-2024-101409","DOIUrl":"10.1136/bmjhci-2024-101409","url":null,"abstract":"","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"32 1","pages":""},"PeriodicalIF":4.1,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11800217/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143363480","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluation of a pragmatic approach to predicting COVID-19-positive hospital bed occupancy.","authors":"Derryn Lovett, Thomas Woodcock, Jacques Naude, Julian Redhead, Azeem Majeed, Paul Aylin","doi":"10.1136/bmjhci-2024-101055","DOIUrl":"10.1136/bmjhci-2024-101055","url":null,"abstract":"<p><strong>Study objectives: </strong>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.</p><p><strong>Methods: </strong>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.</p><p><strong>Results: </strong>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.</p><p><strong>Conclusions: </strong>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.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"32 1","pages":""},"PeriodicalIF":4.1,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11800226/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143363487","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Engaging with patients with diabetes: the role of social media in low-income healthcare organisations.","authors":"Andrea Cano, Mohy Uddin, Fernanda Caceres, José Rodriguez, Shabbir Syed-Abdul","doi":"10.1136/bmjhci-2024-101193","DOIUrl":"10.1136/bmjhci-2024-101193","url":null,"abstract":"<p><strong>Background: </strong>Type 2 diabetes is the fastest-growing global health concern, and its global prevalence is projected to affect 643 million individuals by 2030. Social media platforms, like Facebook, have become crucial channels for healthcare organisations to engage with the public to promote prevention and disease management, especially in low-resource settings like Honduras. This study aims to perform a retrospective analysis of Honduran healthcare organisations' Facebook posts to understand how effectively they engage diabetes-related content with their followers.</p><p><strong>Methods: </strong>The top 10 followed healthcare organisations' Facebook pages were taken as a sample. Data were retrieved from October 2023 to March 2024. Diabetic-related posts were identified using keywords and categorised based on their contents and features.</p><p><strong>Results: </strong>Findings reveal significant disparities in the frequencies of posts and public engagement among different types of organisations. The majority of posts were classified under the miscellaneous category and text+image feature. Recipes and food-related posts were liked and shared the most among the followers.</p><p><strong>Conclusion: </strong>The results of the study found that patients' engagement with diabetes-related content was low in social media. The gap between patients' participation and engagement highlights the need for reassessment and refinement of social media communication strategies for healthcare organisations to empower patients with diabetes through social media and increase public engagement.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"32 1","pages":""},"PeriodicalIF":4.1,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11795404/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143188268","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ConciliaMed: an interactive mobile and web tool to reconcile chronic medications of patients undergoing elective surgery.","authors":"Pablo Ciudad-Gutiérrez, Paloma Suárez-Casillas, Eva Rocío Alfaro-Lara, Maria Dolores Santos-Rubio, Bernardo Santos-Ramos, Ana Belén Guisado-Gil","doi":"10.1136/bmjhci-2024-101256","DOIUrl":"10.1136/bmjhci-2024-101256","url":null,"abstract":"<p><strong>Objective: </strong>The last decade has seen exponential growth in electronic health tools. However, only a limited number of electronic medication reconciliation tools have been developed and implemented in healthcare settings. Here, we present ConciliaMed, a mobile and web-based tool for healthcare professionals to reconcile the chronic medications of patients undergoing elective surgery.</p><p><strong>Methods: </strong>A research team of pharmacists and internists worked together with a technology company to design and develop ConciliaMed. Evidence-based guidelines were collected for inclusion in the tool. A group of experts conducted a simulation with a preliminary version of ConciliaMed to identify bugs and technical improvements and to assess their satisfaction with the application. The final prototype of the tool was disseminated through clinical meetings and the Google Store.</p><p><strong>Results: </strong>Four easy-to-use and interactive modules can be used to reconcile chronic medications through the app, while the web platform is designed for consultation and learning. A higher level of satisfaction with the tool was achieved by the test participants (4.67±0.58). The triggering of dose and duplication alerts for users or the integration of ConciliaMed with electronic prescription systems were some of the more requested adaptations by the test participants.</p><p><strong>Discussion: </strong>The ability to generate an editable reconciliation report or transfer information between users are some of the features of ConciliaMed that encourage its use. The integration of ConciliaMed into the healthcare workflow is expected.</p><p><strong>Conclusion: </strong>The web platform is freely available online (https://conciliamed.chronic-pharma.com), as is the mobile application through the Google Store, making it easily accessible to healthcare professionals.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"32 1","pages":""},"PeriodicalIF":4.1,"publicationDate":"2025-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11784385/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143063661","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}