BMJ Health & Care Informatics最新文献

{"title":"Digitalizing English-language CT Interpretation for Positive Haemorrhage Evaluation Reporting: the DECIPHER study.","authors":"Ben Bloom, Adrian Haimovich, Jason Pott, Sophie L Williams, Michael Cheetham, Sandra Langsted, Imogen Skene, Raine Astin-Chamberlain, Stephen H Thomas","doi":"10.1136/bmjhci-2025-101433","DOIUrl":"10.1136/bmjhci-2025-101433","url":null,"abstract":"<p><strong>Objectives: </strong>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).</p><p><strong>Methods: </strong>Primary objective: determine the diagnostic classification performance of the dichotomous categorisation of each of the three approaches.</p><p><strong>Secondary objective: </strong>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.</p><p><strong>Results: </strong>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.</p><p><strong>Discussion and conclusion: </strong>DECIPHER-LLM outperformed other tested free-text classification methods.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"32 1","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12306305/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144717429","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":"Development and evaluation of an agentic LLM based RAG framework for evidence-based patient education.","authors":"AlHasan AlSammarraie, Ali Al-Saifi, Hassan Kamhia, Mohamed Aboagla, Mowafa Househ","doi":"10.1136/bmjhci-2025-101570","DOIUrl":"10.1136/bmjhci-2025-101570","url":null,"abstract":"<p><strong>Objectives: </strong>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.</p><p><strong>Methods: </strong>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.</p><p><strong>Results: </strong>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.</p><p><strong>Discussion: </strong>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.</p><p><strong>Conclusion: </strong>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.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"32 1","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12306375/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144717428","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":"Exploring doctors' perspectives on generative-AI and diagnostic-decision-support systems.","authors":"Saba Esnaashari, Youmna Hashem, John Francis, Deborah Morgan, Anton Poletaev, Jonathan Bright","doi":"10.1136/bmjhci-2024-101371","DOIUrl":"10.1136/bmjhci-2024-101371","url":null,"abstract":"<p><p>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.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"32 1","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12306348/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144706292","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":"Impact of atrial fibrillation centre on the implementation of the atrial fibrillation better care holistic pathway in a Chinese large teaching hospital: an interrupted time series analysis.","authors":"Pengze Xiao, Zhongqiu Chen, Zhi Zeng, Shu Su, Sihang Chen, Yufu Li, Xinyue Li, Xian Yang, Haoxuan Zhang, Yuehui Yin, Yunlin Chen, Zhiyu Ling","doi":"10.1136/bmjhci-2024-101315","DOIUrl":"10.1136/bmjhci-2024-101315","url":null,"abstract":"<p><strong>Objectives: </strong>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.</p><p><strong>Methods: </strong>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).</p><p><strong>Results: </strong>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.</p><p><strong>Discussion: </strong>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.</p><p><strong>Conclusion: </strong>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.</p><p><strong>Trial registration number: </strong>MR-50-24-014759.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"32 1","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12306324/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144706293","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":"Utilisation of routine health information system and associated factors among health workers in public health institutions of Gofa zone, South Ethiopia regional state:a mixed-methods study.","authors":"Bedilu Kucho Doka, Abebaw Gebeyehu Worku, Keneni Gutema Negeri, Dejene Hailu Kassa","doi":"10.1136/bmjhci-2024-101142","DOIUrl":"10.1136/bmjhci-2024-101142","url":null,"abstract":"<p><strong>Objectives: </strong>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).</p><p><strong>Methods: </strong>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.</p><p><strong>Results: </strong>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.</p><p><strong>Discussion: </strong>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.</p><p><strong>Conclusion: </strong>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.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"32 1","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12306301/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144697552","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":"Improvement of medication adherence in osteoporosis through telemedicine combined with email: a patient-reported experience and outcome measure-based prospective study.","authors":"Gherardo Mazziotti, Benedetta Pongiglione, Flaminia Carrone, Michela Meregaglia, Alessandra Angelucci, Maria Laura Costantino, Andrea Aliverti, Andrea Gerardo Antonio Lania, Amelia Compagni","doi":"10.1136/bmjhci-2024-101338","DOIUrl":"10.1136/bmjhci-2024-101338","url":null,"abstract":"<p><strong>Objectives: </strong>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).</p><p><strong>Methods: </strong>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.</p><p><strong>Results: </strong>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.</p><p><strong>Discussion: </strong>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.</p><p><strong>Conclusions: </strong>Patients with osteoporosis need to be supported after drug prescription to guarantee optimal medication therapy.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"32 1","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12281328/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144688883","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":"Navigating data availability challenges in healthcare: assessing the added value of pulmonary function testing to the Care Assessment Need score for mortality risk.","authors":"Khalid A Ishani, Anders Westanmo, Amy Gravely, Meredith C McCormack, Arianne K Baldomero","doi":"10.1136/bmjhci-2024-101361","DOIUrl":"10.1136/bmjhci-2024-101361","url":null,"abstract":"<p><strong>Objectives: </strong>Pulmonary function testing (PFT) data, such as forced expiratory volume (FEV₁) has become increasingly siloed from the electronic health record (EHR). We hypothesised that FEV₁ %pred is independently associated with mortality risk, even after adjusting for the Care Assessment Needs (CAN) score, a validated method developed by the Veterans Health Administration (VA) to predict mortality. Additionally, we hypothesised that the integration of PFT data into the EHR has declined in recent years.</p><p><strong>Methods: </strong>We conducted a retrospective cohort study using national VA data on PFTs from 2013 to 2018. Using logistic regression adjusted for CAN scores, we assessed the associations between FEV1 percent predicted (%pred) and all-cause mortality at 1 year and 5 years.</p><p><strong>Results: </strong>While the number of PFTs performed has generally increased since 2000, the integration of PFT data into the EHR has declined since 2006. The CAN-adjusted odds of 1-year mortality were 2.94 (95% CI: 2.66 to 3.24) for those with FEV₁ %pred <35%, compared with those with FEV₁ %pred ≥70%, while 5-year mortality odds were 3.83 (95% CI: 3.58 to 4.09).</p><p><strong>Discussion: </strong>Our study shows that FEV₁ %pred is statistically significantly associated with increased risk of mortality, above and beyond the CAN score. However, the declining integration of PFT data into the VA EHR highlights a concerning trend of isolating critical test results from clinical care.</p><p><strong>Conclusion: </strong>Among people with FEV₁ recorded in the EHR, FEV₁ %pred is statistically significantly associated with increased risk of both 1-year and 5-year mortality, above and beyond the CAN score.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"32 1","pages":""},"PeriodicalIF":4.1,"publicationDate":"2025-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12278127/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144673840","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":"Proactive process evaluation of precision medicine platforms: a roadmap.","authors":"Kathrin Cresswell","doi":"10.1136/bmjhci-2025-101434","DOIUrl":"10.1136/bmjhci-2025-101434","url":null,"abstract":"<p><strong>Background: </strong>Precision and genomic medicine have significant potential to improve population health. However, despite rapid technological development and increasing data complexity, practical applications of precision medicine remain limited. There is also a lack of evaluation of unintended consequences and a failure to use theory-based implementation frameworks to manage risks and ensure sustainability.</p><p><strong>Methods: </strong>This work provides a conceptual overview of evaluation challenges related to precision medicine platforms, based on existing literature. It proposes a theory-informed proactive process evaluation framework to guide the development and assessment of these platforms.</p><p><strong>Results: </strong>The proposed framework considers infrastructural, socio-organisational and system-level factors. It raises key questions, such as: How will platforms integrate with existing infrastructures? How will they transform care pathways and the delivery of care across settings?</p><p><strong>Conclusions: </strong>Rapid technological advances challenge markets and regulatory environments. Agile evaluation approaches are crucial for building a sustainable innovation ecosystem for precision medicine platforms.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"32 1","pages":""},"PeriodicalIF":4.1,"publicationDate":"2025-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12278136/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144673841","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":"Development and implementation of cancer clinical trial patient screening using an electronic medical record-integrated trial matching system.","authors":"Nam Bui, Agnes Nika, Mateo Montoya, Andrea Lopez, Jasmine Newman, Mounica Vaddadi, Rahul Guli, Melissa Rodin, Ashley Robinson, Eben Rosenthal, Steven E Artandi, Sameer Ather, Yi Pang, Joel Neal","doi":"10.1136/bmjhci-2024-101295","DOIUrl":"10.1136/bmjhci-2024-101295","url":null,"abstract":"<p><strong>Objectives: </strong>Clinical trial enrolment is critical for the development and approval of novel cancer therapeutics, but patient identification and recruitment to clinical trials remains low and multiple trials accrue slowly or fail to meet accrual goals. Informatics solutions may facilitate clinical trial screening, ideally improving patient engagement and enrolment. Our objective is to develop and implement a system to efficiently screen queried patients for available clinical trials.</p><p><strong>Methods: </strong>At Stanford, we designed and implemented a personalised clinical trial matching system, integrating our electronic medical record, clinical trials management system and a third-party software-based solution to directly connect providers with clinical research coordinators and appropriate trials.</p><p><strong>Results: </strong>Over 3 years of a staged rollout, significant increases in clinical trial screening requests and subsequent enrolment have been observed. The total number of screening referrals increased from 20 in the first year to 236 in the third year. Enrolment related to screening referrals, the 'conversion rate', ranged from 16% to 26% of referred patients.</p><p><strong>Conclusion: </strong>Clinical trial matching systems can increase awareness of available trials and provide a mechanism to increase clinical trial accrual, especially when implemented at the point of care for easy access at treatment decision points. Here, we describe the process of creating and implementing a bespoke clinical trial matching software integrated into the electronic medical record. Having validated the utility of the platform, we will focus on further efforts to drive utilisation through software features.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"32 1","pages":""},"PeriodicalIF":4.1,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12273118/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144648465","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":"Mitigated deployment strategy for ethical AI in clinical settings.","authors":"Sahar Abdulrahman, Markus Trengove","doi":"10.1136/bmjhci-2024-101363","DOIUrl":"10.1136/bmjhci-2024-101363","url":null,"abstract":"<p><p>Clinical diagnostic tools can disadvantage subgroups due to poor model generalisability, which can be caused by unrepresentative training data. Practical deployment solutions to mitigate harm for subgroups from models with differential performance have yet to be established. This paper will build on existing work that considers a selective deployment approach where poorly performing subgroups are excluded from deployments. Alternatively, the proposed 'mitigated deployment' strategy requires safety nets to be built into clinical workflows to safeguard under-represented groups in a universal deployment. This approach relies on human-artificial intelligence collaboration and postmarket evaluation to continually improve model performance across subgroups with real-world data. Using a real-world case study, the benefits and limitations of mitigated deployment are explored. This will add to the tools available to healthcare organisations when considering how to safely deploy models with differential performance across subgroups.</p>","PeriodicalId":9050,"journal":{"name":"BMJ Health & Care Informatics","volume":"32 1","pages":""},"PeriodicalIF":4.1,"publicationDate":"2025-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12258279/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144636136","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}