Equitable hospital length of stay prediction for patients with learning disabilities and multiple long-term conditions using machine learning

PurposeIndividuals 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...

Full description

Saved in:
Bibliographic Details
Main Authors: Emeka Abakasanga, Rania Kousovista, Georgina Cosma, Ashley Akbari, Francesco Zaccardi, Navjot Kaur, Danielle Fitt, Gyuchan Thomas Jun, Reza Kiani, Satheesh Gangadharan
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-02-01
Series:Frontiers in Digital Health
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fdgth.2025.1538793/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849721773269975040
author Emeka Abakasanga
Rania Kousovista
Georgina Cosma
Ashley Akbari
Francesco Zaccardi
Navjot Kaur
Navjot Kaur
Danielle Fitt
Gyuchan Thomas Jun
Reza Kiani
Satheesh Gangadharan
author_facet Emeka Abakasanga
Rania Kousovista
Georgina Cosma
Ashley Akbari
Francesco Zaccardi
Navjot Kaur
Navjot Kaur
Danielle Fitt
Gyuchan Thomas Jun
Reza Kiani
Satheesh Gangadharan
author_sort Emeka Abakasanga
collection DOAJ
description PurposeIndividuals 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.MethodThis 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.ResultsThe 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.ConclusionThis 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.
format Article
id doaj-art-a29abbdeacca4d3aa774892cb4bf3eda
institution DOAJ
issn 2673-253X
language English
publishDate 2025-02-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Digital Health
spelling doaj-art-a29abbdeacca4d3aa774892cb4bf3eda2025-08-20T03:11:33ZengFrontiers Media S.A.Frontiers in Digital Health2673-253X2025-02-01710.3389/fdgth.2025.15387931538793Equitable hospital length of stay prediction for patients with learning disabilities and multiple long-term conditions using machine learningEmeka Abakasanga0Rania Kousovista1Georgina Cosma2Ashley Akbari3Francesco Zaccardi4Navjot Kaur5Navjot Kaur6Danielle Fitt7Gyuchan Thomas Jun8Reza Kiani9Satheesh Gangadharan10Computer Science Department, School of Science, Loughborough University, Loughborough, United KingdomComputer Science Department, School of Science, Loughborough University, Loughborough, United KingdomComputer Science Department, School of Science, Loughborough University, Loughborough, United KingdomFaculty of Medicine, Health and Life Science, Swansea University, Swansea, United KingdomLeicester Real World Evidence Unit, Diabetes Research Centre, University of Leicester, Leicester, United KingdomLeicester Real World Evidence Unit, Diabetes Research Centre, University of Leicester, Leicester, United KingdomSchool of Design and Creative Arts, Loughborough University, Loughborough, United KingdomFaculty of Medicine, Health and Life Science, Swansea University, Swansea, United KingdomSchool of Design and Creative Arts, Loughborough University, Loughborough, United KingdomLearning Disability Service (Agnes Unit), Leicestershire Partnership NHS Trust, Leicester, United KingdomLearning Disability Service (Agnes Unit), Leicestershire Partnership NHS Trust, Leicester, United KingdomPurposeIndividuals 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.MethodThis 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.ResultsThe 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.ConclusionThis 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.https://www.frontiersin.org/articles/10.3389/fdgth.2025.1538793/fulllearning disabilitieslength of staybias mitigationthreshold optimiserexponentiated gradient
spellingShingle Emeka Abakasanga
Rania Kousovista
Georgina Cosma
Ashley Akbari
Francesco Zaccardi
Navjot Kaur
Navjot Kaur
Danielle Fitt
Gyuchan Thomas Jun
Reza Kiani
Satheesh Gangadharan
Equitable hospital length of stay prediction for patients with learning disabilities and multiple long-term conditions using machine learning
Frontiers in Digital Health
learning disabilities
length of stay
bias mitigation
threshold optimiser
exponentiated gradient
title Equitable hospital length of stay prediction for patients with learning disabilities and multiple long-term conditions using machine learning
title_full Equitable hospital length of stay prediction for patients with learning disabilities and multiple long-term conditions using machine learning
title_fullStr Equitable hospital length of stay prediction for patients with learning disabilities and multiple long-term conditions using machine learning
title_full_unstemmed Equitable hospital length of stay prediction for patients with learning disabilities and multiple long-term conditions using machine learning
title_short Equitable hospital length of stay prediction for patients with learning disabilities and multiple long-term conditions using machine learning
title_sort equitable hospital length of stay prediction for patients with learning disabilities and multiple long term conditions using machine learning
topic learning disabilities
length of stay
bias mitigation
threshold optimiser
exponentiated gradient
url https://www.frontiersin.org/articles/10.3389/fdgth.2025.1538793/full
work_keys_str_mv AT emekaabakasanga equitablehospitallengthofstaypredictionforpatientswithlearningdisabilitiesandmultiplelongtermconditionsusingmachinelearning
AT raniakousovista equitablehospitallengthofstaypredictionforpatientswithlearningdisabilitiesandmultiplelongtermconditionsusingmachinelearning
AT georginacosma equitablehospitallengthofstaypredictionforpatientswithlearningdisabilitiesandmultiplelongtermconditionsusingmachinelearning
AT ashleyakbari equitablehospitallengthofstaypredictionforpatientswithlearningdisabilitiesandmultiplelongtermconditionsusingmachinelearning
AT francescozaccardi equitablehospitallengthofstaypredictionforpatientswithlearningdisabilitiesandmultiplelongtermconditionsusingmachinelearning
AT navjotkaur equitablehospitallengthofstaypredictionforpatientswithlearningdisabilitiesandmultiplelongtermconditionsusingmachinelearning
AT navjotkaur equitablehospitallengthofstaypredictionforpatientswithlearningdisabilitiesandmultiplelongtermconditionsusingmachinelearning
AT daniellefitt equitablehospitallengthofstaypredictionforpatientswithlearningdisabilitiesandmultiplelongtermconditionsusingmachinelearning
AT gyuchanthomasjun equitablehospitallengthofstaypredictionforpatientswithlearningdisabilitiesandmultiplelongtermconditionsusingmachinelearning
AT rezakiani equitablehospitallengthofstaypredictionforpatientswithlearningdisabilitiesandmultiplelongtermconditionsusingmachinelearning
AT satheeshgangadharan equitablehospitallengthofstaypredictionforpatientswithlearningdisabilitiesandmultiplelongtermconditionsusingmachinelearning