{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T15:58:43Z","timestamp":1775145523442,"version":"3.50.1"},"reference-count":53,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,2,14]],"date-time":"2025-02-14T00:00:00Z","timestamp":1739491200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Digit. Health"],"abstract":"<jats:sec><jats:title>Purpose<\/jats:title><jats:p>Individuals with learning disabilities (LD) often face higher rates of premature mortality and prolonged hospital stays compared to the general population. Predicting the length of stay (LOS) for patients with LD and multiple long-term conditions (MLTCs) is critical for improving patient care and optimising medical resource allocation. However, there is limited research on the application of machine learning (ML) models to this population. Furthermore, approaches designed for the general population often lack generalisability and fairness, particularly when applied across sensitive groups within their cohort.<\/jats:p><\/jats:sec><jats:sec><jats:title>Method<\/jats:title><jats:p>This study analyses hospitalisations of 9,618 patients with LD in Wales using electronic health records (EHR) from the SAIL Databank. A Random Forest (RF) ML model was developed to predict hospital LOS, incorporating demographics, medication history, lifestyle factors, and 39 long-term conditions. To address fairness concerns, two bias mitigation techniques were applied: a post-processing threshold optimiser and an in-processing reductions method using an exponentiated gradient. These methods aimed to minimise performance discrepancies across ethnic groups while ensuring robust model performance.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The RF model outperformed other state-of-the-art models, achieving an area under the curve of 0.759 for males and 0.756 for females, a false negative rate of 0.224 for males and 0.229 for females, and a balanced accuracy of 0.690 for males and 0.689 for females. Bias mitigation algorithms reduced disparities in prediction performance across ethnic groups, with the threshold optimiser yielding the most notable improvements. Performance metrics, including false positive rate and balanced accuracy, showed significant enhancements in fairness for the male cohort.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>This study demonstrates the feasibility of applying ML models to predict LOS for patients with LD and MLTCs, while addressing fairness through bias mitigation techniques. The findings highlight the potential for equitable healthcare predictions using EHR data, paving the way for improved clinical decision-making and resource management.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fdgth.2025.1538793","type":"journal-article","created":{"date-parts":[[2025,2,14]],"date-time":"2025-02-14T07:01:03Z","timestamp":1739516463000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Equitable hospital length of stay prediction for patients with learning disabilities and multiple long-term conditions using machine learning"],"prefix":"10.3389","volume":"7","author":[{"given":"Emeka","family":"Abakasanga","sequence":"first","affiliation":[]},{"given":"Rania","family":"Kousovista","sequence":"additional","affiliation":[]},{"given":"Georgina","family":"Cosma","sequence":"additional","affiliation":[]},{"given":"Ashley","family":"Akbari","sequence":"additional","affiliation":[]},{"given":"Francesco","family":"Zaccardi","sequence":"additional","affiliation":[]},{"given":"Navjot","family":"Kaur","sequence":"additional","affiliation":[]},{"given":"Danielle","family":"Fitt","sequence":"additional","affiliation":[]},{"given":"Gyuchan Thomas","family":"Jun","sequence":"additional","affiliation":[]},{"given":"Reza","family":"Kiani","sequence":"additional","affiliation":[]},{"given":"Satheesh","family":"Gangadharan","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2025,2,14]]},"reference":[{"key":"B1","article-title":"A working definition of learning disabilities","author":"Emerson","year":""},{"key":"B2","article-title":"Data from: How common is learning disability?","year":""},{"key":"B3","article-title":"Data from: Health inequalities","year":""},{"key":"B4","article-title":"Learning from lives and deaths \u2013 people with a learning disability and autistic people (LeDeR) report for 2021 (Tech. rep.). King\u2019s College London (2022)","author":"White","year":""},{"key":"B5","doi-asserted-by":"publisher","first-page":"cmac135","DOI":"10.1093\/fampra\/cmac135","article-title":"Comparing the number and length of primary care consultations in people with and without intellectual disabilities and health needs: observational cohort study using electronic health records","volume":"41","author":"Tyrer","year":"2022","journal-title":"Fam Pract"},{"key":"B6","doi-asserted-by":"publisher","first-page":"6602","DOI":"10.3390\/ijerph19116602","article-title":"Health needs and their relationship with life expectancy in people with and without intellectual disabilities in England","volume":"19","author":"Tyrer","year":"2022","journal-title":"Int J Environ Res Public Health"},{"key":"B7","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1136\/jech-2021-216798","article-title":"Mortality disparities and deprivation among people with intellectual disabilities in England: 2000\u20132019","volume":"76","author":"Tyrer","year":"2022","journal-title":"J Epidemiol Community Health"},{"key":"B8","doi-asserted-by":"publisher","first-page":"102","DOI":"10.3109\/13668250.2020.1834946","article-title":"Mortality, predictors and causes among people with intellectual disabilities: a systematic narrative review supplemented by machine learning","volume":"46","author":"Tyrer","year":"2021","journal-title":"J Intellect Dev Disabil"},{"key":"B9","article-title":"Confidential inquiry into premature deaths of people with learning disabilities (CIPOLD) (Tech. rep.)","author":"Heslop","year":""},{"key":"B10","doi-asserted-by":"publisher","first-page":"e264","DOI":"10.3399\/bjgp16X684301","article-title":"Health characteristics and consultation patterns of people with intellectual disability: a cross-sectional database study in English general practice","volume":"66","author":"Carey","year":"2016","journal-title":"Br J Gen Pract"},{"key":"B11","article-title":"Data from: Learning disabilities observatory. People with learning disabilities in England in 2015: main report (2016)","author":"Hatton","year":""},{"key":"B12","doi-asserted-by":"publisher","first-page":"e0000017","DOI":"10.1371\/journal.pdig.0000017","article-title":"A systematic review of the prediction of hospital length of stay: towards a unified framework","volume":"1","author":"Stone","year":"2022","journal-title":"PLOS Digit Health"},{"key":"B13","doi-asserted-by":"publisher","first-page":"e3477","DOI":"10.1111\/hsc.13964","article-title":"\u201cWhy are we stuck in hospital?\u201d Understanding delayed hospital discharges for people with learning disabilities and\/or autistic people in long-stay hospitals in the UK","volume":"30","author":"Ince","year":"2022","journal-title":"Health Soc Care Community"},{"key":"B14","article-title":"Medical error reduction and prevention","author":"Rodziewicz","year":""},{"key":"B15","article-title":"Hospital discharge and readmission","author":"Alper","year":""},{"key":"B16","doi-asserted-by":"publisher","first-page":"137","DOI":"10.2147\/PRBM.S35061","article-title":"Discharged from a mental health admission ward: is it safe to go home? a review on the negative outcomes of psychiatric hospitalization","volume":"7","author":"Loch","year":"2014","journal-title":"Psychol Res Behav Manag"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1085178","DOI":"10.3389\/fneur.2023.1085178","article-title":"Risk factor identification and prediction models for prolonged length of stay in hospital after acute ischemic stroke using artificial neural networks","volume":"14","author":"Yang","year":"2023","journal-title":"Front Neurol"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1323849","DOI":"10.3389\/fdgth.2023.1323849","article-title":"Evaluation of different machine learning algorithms for predicting the length of stay in the emergency departments: a single-centre study","volume":"5","author":"Ricciardi","year":"2024","journal-title":"Front Digit Health"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12962-021-00322-3","article-title":"Neural networks and hospital length of stay: an application to support healthcare management with national benchmarks and thresholds","volume":"19","author":"Ippoliti","year":"2021","journal-title":"Cost Eff Resour Alloc"},{"key":"B20","doi-asserted-by":"publisher","first-page":"15784","DOI":"10.48550\/arXiv.2206.11104","article-title":"Openxai: towards a transparent evaluation of model explanations","volume":"35","author":"Agarwal","year":"2022","journal-title":"Adv Neural Inf Process Syst"},{"key":"B21","doi-asserted-by":"publisher","first-page":"719","DOI":"10.1038\/s41551-023-01056-8","article-title":"Algorithmic fairness in artificial intelligence for medicine and healthcare","volume":"7","author":"Chen","year":"2023","journal-title":"Nat Biomed Eng"},{"key":"B22","article-title":"A reductions approach to fair classification","author":"Agarwal","year":""},{"key":"B23","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1038\/s41746-023-00858-z","article-title":"Bias in AI-based models for medical applications: challenges and mitigation strategies","volume":"6","author":"Mittermaier","year":"2023","journal-title":"NPJ Digit Med"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1045","DOI":"10.1177\/17446295221107275","article-title":"A scoping review of clusters of multiple long-term conditions in people with intellectual disabilities and factors impacting on outcomes for this patient group","volume":"27","author":"Mann","year":"2023","journal-title":"J Intellect Disabil"},{"key":"B25","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-67285-9_1","article-title":"Cluster and trajectory analysis of multiple long-term conditions in adults with learning disabilities","author":"Abakasanga","year":""},{"key":"B26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3616865","article-title":"Fairness in machine learning: a survey","volume":"56","author":"Caton","year":"2024","journal-title":"ACM Comput Surv"},{"key":"B27","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1145\/3494672","article-title":"A review on fairness in machine learning","volume":"55","author":"Pessach","year":"2022","journal-title":"ACM Comput Surv"},{"key":"B28","article-title":"Equality of opportunity in supervised learning","volume-title":"Advances in Neural Information Processing Systems","author":"Hardt","year":"2016"},{"key":"B29","doi-asserted-by":"publisher","first-page":"201","DOI":"10.5009\/gnl230272","article-title":"Challenges in and opportunities for electronic health record-based data analysis and interpretation","volume":"18","author":"Kim","year":"2024","journal-title":"Gut Liver"},{"key":"B30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1472-6947-9-3","article-title":"The SAIL databank: linking multiple health and social care datasets","volume":"9","author":"Lyons","year":"2009","journal-title":"BMC Med Inform Decis Mak"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1472-6963-9-157","article-title":"The SAIL databank: building a national architecture for e-health research and evaluation","volume":"9","author":"Ford","year":"2009","journal-title":"BMC Health Serv Res"},{"key":"B32","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1016\/j.healthplace.2011.09.006","article-title":"Protecting health data privacy while using residence-based environment and demographic data","volume":"18","author":"Rodgers","year":"2012","journal-title":"Health Place"},{"key":"B33","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1016\/j.jbi.2014.01.003","article-title":"A case study of the secure anonymous information linkage (SAIL) gateway: a privacy-protecting remote access system for health-related research and evaluation","volume":"50","author":"Jones","year":"2014","journal-title":"J Biomed Inform"},{"key":"B34","doi-asserted-by":"publisher","first-page":"173","DOI":"10.14236\/jhi.v19i3.811","article-title":"The history of the read codes: the inaugural james read memorial lecture 2011","volume":"19","author":"Benson","year":"2011","journal-title":"Inform Prim Care"},{"key":"B35","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1089\/wound.2013.0478","article-title":"ICD-9-CM to ICD-10-CM codes: what? why? how?","volume":"2","author":"Cartwright","year":"2013","journal-title":"Adv Wound Care"},{"key":"B36","article-title":"Health and care of people with learning disabilities, experimental statistics: 2018 to 2019 [pas] (Tech. rep.). NHS (2020)","year":""},{"key":"B37","article-title":"WIMD indicator data from 2019 (Tech. rep.). StatsWales (2019)","year":""},{"key":"B38","doi-asserted-by":"publisher","first-page":"766","DOI":"10.1016\/j.ejim.2015.09.019","article-title":"Social deprivation and hospital admission rates, length of stay and readmissions in emergency medical admissions","volume":"26","author":"Cournane","year":"2015","journal-title":"Eur J Intern Med"},{"key":"B39","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1093\/pubmed\/fdt100","article-title":"Socio-economic deprivation and risk of emergency readmission and inpatient mortality in people with sickle cell disease in england: observational study","volume":"35","author":"AlJuburi","year":"2013","journal-title":"J Public Health"},{"key":"B40","doi-asserted-by":"crossref","DOI":"10.1101\/2022.11.28.22282810","article-title":"Developing a research ready population-scale linked data ethnicity-spine in wales","author":"Akbari","year":""},{"key":"B41","doi-asserted-by":"publisher","first-page":"e25976","DOI":"10.1097\/MD.0000000000025976","article-title":"Racial\/ethnic and socioeconomic variations in hospital length of stay: a state-based analysis","volume":"100","author":"Ghosh","year":"2021","journal-title":"Medicine"},{"key":"B42","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1093\/epirev\/mxs009","article-title":"Multimorbidity in older adults","volume":"35","author":"Salive","year":"2013","journal-title":"Epidemiol Rev"},{"key":"B43","doi-asserted-by":"publisher","first-page":"e1002695","DOI":"10.1371\/journal.pmed.1002695","article-title":"Predicting the risk of emergency admission with machine learning: development and validation using linked electronic health records","volume":"15","author":"Rahimian","year":"2018","journal-title":"PLoS Med"},{"key":"B44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12916-020-01581-2","article-title":"Development and validation of a multivariable prediction model for infection-related complications in patients with common infections in UK primary care and the extent of risk-based prescribing of antibiotics","volume":"18","author":"Mistry","year":"2020","journal-title":"BMC Med"},{"key":"B45","doi-asserted-by":"publisher","first-page":"1453828","DOI":"10.3389\/fendo.2024.1453828","article-title":"Analysis of risk factors for autoimmune thyroid disease based on blood indicators and urinary iodine concentrations","volume":"15","author":"Liu","year":"2024","journal-title":"Front Endocrinol"},{"key":"B46","doi-asserted-by":"publisher","first-page":"11781","DOI":"10.3390\/ijerph182211781","article-title":"Effects of alcohol consumption and smoking on the onset of hypertension in a long-term longitudinal study in a male workers\u2019 cohort","volume":"18","author":"Nagao","year":"2021","journal-title":"Int J Environ Res Public Health"},{"key":"B47","doi-asserted-by":"publisher","first-page":"1179226","DOI":"10.3389\/frai.2023.1179226","article-title":"Machine learning-based prediction of hospital prolonged length of stay admission at emergency department: a gradient boosting algorithm analysis","volume":"6","author":"Zeleke","year":"2023","journal-title":"Front Artif Intell"},{"key":"B48","doi-asserted-by":"publisher","first-page":"9517029","DOI":"10.1155\/2022\/9517029","article-title":"Length of stay prediction model of indoor patients based on light gradient boosting machine","volume":"2022","author":"Zeng","year":"2022","journal-title":"Comput Intell Neurosci"},{"key":"B49","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1016\/j.ijcard.2019.01.046","article-title":"Predictors of in-hospital length of stay among cardiac patients: a machine learning approach","volume":"288","author":"Daghistani","year":"2019","journal-title":"Int J Cardiol"},{"key":"B50","article-title":"Focus on: people with mental ill health and hospital use (Tech. rep.). QualityWatch (2015)","author":"Dorning","year":""},{"key":"B51","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1186\/s12913-018-3316-2","article-title":"Hospital length of stay variation and comorbidity of mental illness: a retrospective study of five common chronic medical conditions","volume":"18","author":"Siddiqui","year":"2018","journal-title":"BMC Health Serv Res"},{"key":"B52","article-title":"Data from: Reducing length of stay","year":""},{"key":"B53","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3310\/hsdr05250","article-title":"An evaluation of the effectiveness of annual health checks and quality of health care for adults with intellectual disability: an observational study using a primary care database","volume":"5","author":"Carey","year":"2017","journal-title":"Health Serv Deliv Res"}],"container-title":["Frontiers in Digital Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2025.1538793\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,14]],"date-time":"2025-02-14T07:01:07Z","timestamp":1739516467000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2025.1538793\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,14]]},"references-count":53,"alternative-id":["10.3389\/fdgth.2025.1538793"],"URL":"https:\/\/doi.org\/10.3389\/fdgth.2025.1538793","relation":{},"ISSN":["2673-253X"],"issn-type":[{"value":"2673-253X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,14]]},"article-number":"1538793"}}