Predicting adverse outcomes due to diabetes complications with machine learning using administrative health data

Abstract Across jurisdictions, government and health insurance providers hold a large amount of data from patient interactions with the healthcare system. We aimed to develop a machine learning-based model for predicting adverse outcomes due to diabetes complications using administrative health data...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Mathieu Ravaut, Hamed Sadeghi, Kin Kwan Leung, Maksims Volkovs, Kathy Kornas, Vinyas Harish, Tristan Watson, Gary F. Lewis, Alanna Weisman, Tomi Poutanen, Laura Rosella
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Computer applications to medicine. Medical informatics R858-859.7
Acceso en línea:	https://doaj.org/article/618f79c514f043dc8f26ffb41f8e1df6
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:618f79c514f043dc8f26ffb41f8e1df6
record_format	dspace
spelling	oai:doaj.org-article:618f79c514f043dc8f26ffb41f8e1df62021-12-02T16:06:10ZPredicting adverse outcomes due to diabetes complications with machine learning using administrative health data10.1038/s41746-021-00394-82398-6352https://doaj.org/article/618f79c514f043dc8f26ffb41f8e1df62021-02-01T00:00:00Zhttps://doi.org/10.1038/s41746-021-00394-8https://doaj.org/toc/2398-6352Abstract Across jurisdictions, government and health insurance providers hold a large amount of data from patient interactions with the healthcare system. We aimed to develop a machine learning-based model for predicting adverse outcomes due to diabetes complications using administrative health data from the single-payer health system in Ontario, Canada. A Gradient Boosting Decision Tree model was trained on data from 1,029,366 patients, validated on 272,864 patients, and tested on 265,406 patients. Discrimination was assessed using the AUC statistic and calibration was assessed visually using calibration plots overall and across population subgroups. Our model predicting three-year risk of adverse outcomes due to diabetes complications (hyper/hypoglycemia, tissue infection, retinopathy, cardiovascular events, amputation) included 700 features from multiple diverse data sources and had strong discrimination (average test AUC = 77.7, range 77.7–77.9). Through the design and validation of a high-performance model to predict diabetes complications adverse outcomes at the population level, we demonstrate the potential of machine learning and administrative health data to inform health planning and healthcare resource allocation for diabetes management.Mathieu RavautHamed SadeghiKin Kwan LeungMaksims VolkovsKathy KornasVinyas HarishTristan WatsonGary F. LewisAlanna WeismanTomi PoutanenLaura RosellaNature PortfolioarticleComputer applications to medicine. Medical informaticsR858-859.7ENnpj Digital Medicine, Vol 4, Iss 1, Pp 1-12 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Computer applications to medicine. Medical informatics R858-859.7
spellingShingle	Computer applications to medicine. Medical informatics R858-859.7 Mathieu Ravaut Hamed Sadeghi Kin Kwan Leung Maksims Volkovs Kathy Kornas Vinyas Harish Tristan Watson Gary F. Lewis Alanna Weisman Tomi Poutanen Laura Rosella Predicting adverse outcomes due to diabetes complications with machine learning using administrative health data
description	Abstract Across jurisdictions, government and health insurance providers hold a large amount of data from patient interactions with the healthcare system. We aimed to develop a machine learning-based model for predicting adverse outcomes due to diabetes complications using administrative health data from the single-payer health system in Ontario, Canada. A Gradient Boosting Decision Tree model was trained on data from 1,029,366 patients, validated on 272,864 patients, and tested on 265,406 patients. Discrimination was assessed using the AUC statistic and calibration was assessed visually using calibration plots overall and across population subgroups. Our model predicting three-year risk of adverse outcomes due to diabetes complications (hyper/hypoglycemia, tissue infection, retinopathy, cardiovascular events, amputation) included 700 features from multiple diverse data sources and had strong discrimination (average test AUC = 77.7, range 77.7–77.9). Through the design and validation of a high-performance model to predict diabetes complications adverse outcomes at the population level, we demonstrate the potential of machine learning and administrative health data to inform health planning and healthcare resource allocation for diabetes management.
format	article
author	Mathieu Ravaut Hamed Sadeghi Kin Kwan Leung Maksims Volkovs Kathy Kornas Vinyas Harish Tristan Watson Gary F. Lewis Alanna Weisman Tomi Poutanen Laura Rosella
author_facet	Mathieu Ravaut Hamed Sadeghi Kin Kwan Leung Maksims Volkovs Kathy Kornas Vinyas Harish Tristan Watson Gary F. Lewis Alanna Weisman Tomi Poutanen Laura Rosella
author_sort	Mathieu Ravaut
title	Predicting adverse outcomes due to diabetes complications with machine learning using administrative health data
title_short	Predicting adverse outcomes due to diabetes complications with machine learning using administrative health data
title_full	Predicting adverse outcomes due to diabetes complications with machine learning using administrative health data
title_fullStr	Predicting adverse outcomes due to diabetes complications with machine learning using administrative health data
title_full_unstemmed	Predicting adverse outcomes due to diabetes complications with machine learning using administrative health data
title_sort	predicting adverse outcomes due to diabetes complications with machine learning using administrative health data
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/618f79c514f043dc8f26ffb41f8e1df6
work_keys_str_mv	AT mathieuravaut predictingadverseoutcomesduetodiabetescomplicationswithmachinelearningusingadministrativehealthdata AT hamedsadeghi predictingadverseoutcomesduetodiabetescomplicationswithmachinelearningusingadministrativehealthdata AT kinkwanleung predictingadverseoutcomesduetodiabetescomplicationswithmachinelearningusingadministrativehealthdata AT maksimsvolkovs predictingadverseoutcomesduetodiabetescomplicationswithmachinelearningusingadministrativehealthdata AT kathykornas predictingadverseoutcomesduetodiabetescomplicationswithmachinelearningusingadministrativehealthdata AT vinyasharish predictingadverseoutcomesduetodiabetescomplicationswithmachinelearningusingadministrativehealthdata AT tristanwatson predictingadverseoutcomesduetodiabetescomplicationswithmachinelearningusingadministrativehealthdata AT garyflewis predictingadverseoutcomesduetodiabetescomplicationswithmachinelearningusingadministrativehealthdata AT alannaweisman predictingadverseoutcomesduetodiabetescomplicationswithmachinelearningusingadministrativehealthdata AT tomipoutanen predictingadverseoutcomesduetodiabetescomplicationswithmachinelearningusingadministrativehealthdata AT laurarosella predictingadverseoutcomesduetodiabetescomplicationswithmachinelearningusingadministrativehealthdata
_version_	1718385092418600960

Predicting adverse outcomes due to diabetes complications with machine learning using administrative health data

Ejemplares similares