Using interpretable survival analysis to assess hospital length of stay

Abstract Accurate in-hospital length of stay prediction is a vital quality metric for hospital leaders and health policy decision-makers. It assists with decision-making and informs hospital operations involving factors such as patient flow, elective cases, and human resources allocation, while also...

Full description

Saved in:
Bibliographic Details
Main Authors: Yan Li, Trevor Hall, Fahad Razak, Amol Verma, Mark Chignell, Lu Wang
Format: Article
Language:English
Published: BMC 2025-05-01
Series:BMC Health Services Research
Subjects:
Online Access:https://doi.org/10.1186/s12913-025-12852-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849325877820653568
author Yan Li
Trevor Hall
Fahad Razak
Amol Verma
Mark Chignell
Lu Wang
author_facet Yan Li
Trevor Hall
Fahad Razak
Amol Verma
Mark Chignell
Lu Wang
author_sort Yan Li
collection DOAJ
description Abstract Accurate in-hospital length of stay prediction is a vital quality metric for hospital leaders and health policy decision-makers. It assists with decision-making and informs hospital operations involving factors such as patient flow, elective cases, and human resources allocation, while also informing quality of care and risk considerations. The aim of the research reported in this paper is to use survival analysis to model General Internal Medicine (GIM) length of stay, and to use Shapley value to support interpretation of the resulting model. Survival analysis aims to predict the time until a specific event occurs. In our study, we predict the duration from patient admission to discharge to home, i.e., in-hospital length of stay. In addition to discussing the modeling results, we also talk about how survival analysis of hospital length of stay can be used to guide improvements in the efficiency of hospital operations and support the development of quality metrics.
format Article
id doaj-art-2aff3a087ec4453f8750f66d719c2f25
institution Kabale University
issn 1472-6963
language English
publishDate 2025-05-01
publisher BMC
record_format Article
series BMC Health Services Research
spelling doaj-art-2aff3a087ec4453f8750f66d719c2f252025-08-20T03:48:18ZengBMCBMC Health Services Research1472-69632025-05-0125111210.1186/s12913-025-12852-0Using interpretable survival analysis to assess hospital length of stayYan Li0Trevor Hall1Fahad Razak2Amol Verma3Mark Chignell4Lu Wang5Department of Mechanical and Industrial Engineering, University of TorontoDepartment of Mechanical and Industrial Engineering, University of TorontoThe General Medicine Inpatient Initiative (GEMINI), Unity Health TorontoThe General Medicine Inpatient Initiative (GEMINI), Unity Health TorontoDepartment of Mechanical and Industrial Engineering, University of TorontoDepartment of Biomedical Engineering, University of HoustonAbstract Accurate in-hospital length of stay prediction is a vital quality metric for hospital leaders and health policy decision-makers. It assists with decision-making and informs hospital operations involving factors such as patient flow, elective cases, and human resources allocation, while also informing quality of care and risk considerations. The aim of the research reported in this paper is to use survival analysis to model General Internal Medicine (GIM) length of stay, and to use Shapley value to support interpretation of the resulting model. Survival analysis aims to predict the time until a specific event occurs. In our study, we predict the duration from patient admission to discharge to home, i.e., in-hospital length of stay. In addition to discussing the modeling results, we also talk about how survival analysis of hospital length of stay can be used to guide improvements in the efficiency of hospital operations and support the development of quality metrics.https://doi.org/10.1186/s12913-025-12852-0Interpretable machine learningSurvival analysisHospital length of stay
spellingShingle Yan Li
Trevor Hall
Fahad Razak
Amol Verma
Mark Chignell
Lu Wang
Using interpretable survival analysis to assess hospital length of stay
BMC Health Services Research
Interpretable machine learning
Survival analysis
Hospital length of stay
title Using interpretable survival analysis to assess hospital length of stay
title_full Using interpretable survival analysis to assess hospital length of stay
title_fullStr Using interpretable survival analysis to assess hospital length of stay
title_full_unstemmed Using interpretable survival analysis to assess hospital length of stay
title_short Using interpretable survival analysis to assess hospital length of stay
title_sort using interpretable survival analysis to assess hospital length of stay
topic Interpretable machine learning
Survival analysis
Hospital length of stay
url https://doi.org/10.1186/s12913-025-12852-0
work_keys_str_mv AT yanli usinginterpretablesurvivalanalysistoassesshospitallengthofstay
AT trevorhall usinginterpretablesurvivalanalysistoassesshospitallengthofstay
AT fahadrazak usinginterpretablesurvivalanalysistoassesshospitallengthofstay
AT amolverma usinginterpretablesurvivalanalysistoassesshospitallengthofstay
AT markchignell usinginterpretablesurvivalanalysistoassesshospitallengthofstay
AT luwang usinginterpretablesurvivalanalysistoassesshospitallengthofstay