Using explainable machine learning to identify patients at risk of reattendance at discharge from emergency departments

Abstract Short-term reattendances to emergency departments are a key quality of care indicator. Identifying patients at increased risk of early reattendance could help reduce the number of missed critical illnesses and could reduce avoidable utilization of emergency departments by enabling targeted...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	F. P. Chmiel, D. K. Burns, M. Azor, F. Borca, M. J. Boniface, Z. D. Zlatev, N. M. White, T. W. V. Daniels, M. Kiuber
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/fafd5da22778482f80910c9eb4e6126f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:fafd5da22778482f80910c9eb4e6126f
record_format	dspace
spelling	oai:doaj.org-article:fafd5da22778482f80910c9eb4e6126f2021-11-08T10:49:05ZUsing explainable machine learning to identify patients at risk of reattendance at discharge from emergency departments10.1038/s41598-021-00937-92045-2322https://doaj.org/article/fafd5da22778482f80910c9eb4e6126f2021-11-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-00937-9https://doaj.org/toc/2045-2322Abstract Short-term reattendances to emergency departments are a key quality of care indicator. Identifying patients at increased risk of early reattendance could help reduce the number of missed critical illnesses and could reduce avoidable utilization of emergency departments by enabling targeted post-discharge intervention. In this manuscript, we present a retrospective, single-centre study where we created and evaluated an extreme gradient boosting decision tree model trained to identify patients at risk of reattendance within 72 h of discharge from an emergency department (University Hospitals Southampton Foundation Trust, UK). Our model was trained using 35,447 attendances by 28,945 patients and evaluated on a hold-out test set featuring 8847 attendances by 7237 patients. The set of attendances from a given patient appeared exclusively in either the training or the test set. Our model was trained using both visit level variables (e.g., vital signs, arrival mode, and chief complaint) and a set of variables available in a patients electronic patient record, such as age and any recorded medical conditions. On the hold-out test set, our highest performing model obtained an AUROC of 0.747 (95% CI 0.722–0.773) and an average precision of 0.233 (95% CI 0.194–0.277). These results demonstrate that machine-learning models can be used to classify patients, with moderate performance, into low and high-risk groups for reattendance. We explained our models predictions using SHAP values, a concept developed from coalitional game theory, capable of explaining predictions at an attendance level. We demonstrated how clustering techniques (the UMAP algorithm) can be used to investigate the different sub-groups of explanations present in our patient cohort.F. P. ChmielD. K. BurnsM. AzorF. BorcaM. J. BonifaceZ. D. ZlatevN. M. WhiteT. W. V. DanielsM. KiuberNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q F. P. Chmiel D. K. Burns M. Azor F. Borca M. J. Boniface Z. D. Zlatev N. M. White T. W. V. Daniels M. Kiuber Using explainable machine learning to identify patients at risk of reattendance at discharge from emergency departments
description	Abstract Short-term reattendances to emergency departments are a key quality of care indicator. Identifying patients at increased risk of early reattendance could help reduce the number of missed critical illnesses and could reduce avoidable utilization of emergency departments by enabling targeted post-discharge intervention. In this manuscript, we present a retrospective, single-centre study where we created and evaluated an extreme gradient boosting decision tree model trained to identify patients at risk of reattendance within 72 h of discharge from an emergency department (University Hospitals Southampton Foundation Trust, UK). Our model was trained using 35,447 attendances by 28,945 patients and evaluated on a hold-out test set featuring 8847 attendances by 7237 patients. The set of attendances from a given patient appeared exclusively in either the training or the test set. Our model was trained using both visit level variables (e.g., vital signs, arrival mode, and chief complaint) and a set of variables available in a patients electronic patient record, such as age and any recorded medical conditions. On the hold-out test set, our highest performing model obtained an AUROC of 0.747 (95% CI 0.722–0.773) and an average precision of 0.233 (95% CI 0.194–0.277). These results demonstrate that machine-learning models can be used to classify patients, with moderate performance, into low and high-risk groups for reattendance. We explained our models predictions using SHAP values, a concept developed from coalitional game theory, capable of explaining predictions at an attendance level. We demonstrated how clustering techniques (the UMAP algorithm) can be used to investigate the different sub-groups of explanations present in our patient cohort.
format	article
author	F. P. Chmiel D. K. Burns M. Azor F. Borca M. J. Boniface Z. D. Zlatev N. M. White T. W. V. Daniels M. Kiuber
author_facet	F. P. Chmiel D. K. Burns M. Azor F. Borca M. J. Boniface Z. D. Zlatev N. M. White T. W. V. Daniels M. Kiuber
author_sort	F. P. Chmiel
title	Using explainable machine learning to identify patients at risk of reattendance at discharge from emergency departments
title_short	Using explainable machine learning to identify patients at risk of reattendance at discharge from emergency departments
title_full	Using explainable machine learning to identify patients at risk of reattendance at discharge from emergency departments
title_fullStr	Using explainable machine learning to identify patients at risk of reattendance at discharge from emergency departments
title_full_unstemmed	Using explainable machine learning to identify patients at risk of reattendance at discharge from emergency departments
title_sort	using explainable machine learning to identify patients at risk of reattendance at discharge from emergency departments
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/fafd5da22778482f80910c9eb4e6126f
work_keys_str_mv	AT fpchmiel usingexplainablemachinelearningtoidentifypatientsatriskofreattendanceatdischargefromemergencydepartments AT dkburns usingexplainablemachinelearningtoidentifypatientsatriskofreattendanceatdischargefromemergencydepartments AT mazor usingexplainablemachinelearningtoidentifypatientsatriskofreattendanceatdischargefromemergencydepartments AT fborca usingexplainablemachinelearningtoidentifypatientsatriskofreattendanceatdischargefromemergencydepartments AT mjboniface usingexplainablemachinelearningtoidentifypatientsatriskofreattendanceatdischargefromemergencydepartments AT zdzlatev usingexplainablemachinelearningtoidentifypatientsatriskofreattendanceatdischargefromemergencydepartments AT nmwhite usingexplainablemachinelearningtoidentifypatientsatriskofreattendanceatdischargefromemergencydepartments AT twvdaniels usingexplainablemachinelearningtoidentifypatientsatriskofreattendanceatdischargefromemergencydepartments AT mkiuber usingexplainablemachinelearningtoidentifypatientsatriskofreattendanceatdischargefromemergencydepartments
_version_	1718442675722518528

Using explainable machine learning to identify patients at risk of reattendance at discharge from emergency departments

Ejemplares similares