Machine learning for patient risk stratification: standing on, or looking over, the shoulders of clinicians?

Abstract Machine learning can help clinicians to make individualized patient predictions only if researchers demonstrate models that contribute novel insights, rather than learning the most likely next step in a set of actions a clinician will take. We trained deep learning models using only clinici...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Brett K. Beaulieu-Jones, William Yuan, Gabriel A. Brat, Andrew L. Beam, Griffin Weber, Marshall Ruffin, Isaac S. Kohane
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/151095ca45c745cbaf37ac11a1ed124a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:151095ca45c745cbaf37ac11a1ed124a
record_format	dspace
spelling	oai:doaj.org-article:151095ca45c745cbaf37ac11a1ed124a2021-12-02T13:27:04ZMachine learning for patient risk stratification: standing on, or looking over, the shoulders of clinicians?10.1038/s41746-021-00426-32398-6352https://doaj.org/article/151095ca45c745cbaf37ac11a1ed124a2021-03-01T00:00:00Zhttps://doi.org/10.1038/s41746-021-00426-3https://doaj.org/toc/2398-6352Abstract Machine learning can help clinicians to make individualized patient predictions only if researchers demonstrate models that contribute novel insights, rather than learning the most likely next step in a set of actions a clinician will take. We trained deep learning models using only clinician-initiated, administrative data for 42.9 million admissions using three subsets of data: demographic data only, demographic data and information available at admission, and the previous data plus charges recorded during the first day of admission. Models trained on charges during the first day of admission achieve performance close to published full EMR-based benchmarks for inpatient outcomes: inhospital mortality (0.89 AUC), prolonged length of stay (0.82 AUC), and 30-day readmission rate (0.71 AUC). Similar performance between models trained with only clinician-initiated data and those trained with full EMR data purporting to include information about patient state and physiology should raise concern in the deployment of these models. Furthermore, these models exhibited significant declines in performance when evaluated over only myocardial infarction (MI) patients relative to models trained over MI patients alone, highlighting the importance of physician diagnosis in the prognostic performance of these models. These results provide a benchmark for predictive accuracy trained only on prior clinical actions and indicate that models with similar performance may derive their signal by looking over clinician’s shoulders—using clinical behavior as the expression of preexisting intuition and suspicion to generate a prediction. For models to guide clinicians in individual decisions, performance exceeding these benchmarks is necessary.Brett K. Beaulieu-JonesWilliam YuanGabriel A. BratAndrew L. BeamGriffin WeberMarshall RuffinIsaac S. KohaneNature PortfolioarticleComputer applications to medicine. Medical informaticsR858-859.7ENnpj Digital Medicine, Vol 4, Iss 1, Pp 1-6 (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 Brett K. Beaulieu-Jones William Yuan Gabriel A. Brat Andrew L. Beam Griffin Weber Marshall Ruffin Isaac S. Kohane Machine learning for patient risk stratification: standing on, or looking over, the shoulders of clinicians?
description	Abstract Machine learning can help clinicians to make individualized patient predictions only if researchers demonstrate models that contribute novel insights, rather than learning the most likely next step in a set of actions a clinician will take. We trained deep learning models using only clinician-initiated, administrative data for 42.9 million admissions using three subsets of data: demographic data only, demographic data and information available at admission, and the previous data plus charges recorded during the first day of admission. Models trained on charges during the first day of admission achieve performance close to published full EMR-based benchmarks for inpatient outcomes: inhospital mortality (0.89 AUC), prolonged length of stay (0.82 AUC), and 30-day readmission rate (0.71 AUC). Similar performance between models trained with only clinician-initiated data and those trained with full EMR data purporting to include information about patient state and physiology should raise concern in the deployment of these models. Furthermore, these models exhibited significant declines in performance when evaluated over only myocardial infarction (MI) patients relative to models trained over MI patients alone, highlighting the importance of physician diagnosis in the prognostic performance of these models. These results provide a benchmark for predictive accuracy trained only on prior clinical actions and indicate that models with similar performance may derive their signal by looking over clinician’s shoulders—using clinical behavior as the expression of preexisting intuition and suspicion to generate a prediction. For models to guide clinicians in individual decisions, performance exceeding these benchmarks is necessary.
format	article
author	Brett K. Beaulieu-Jones William Yuan Gabriel A. Brat Andrew L. Beam Griffin Weber Marshall Ruffin Isaac S. Kohane
author_facet	Brett K. Beaulieu-Jones William Yuan Gabriel A. Brat Andrew L. Beam Griffin Weber Marshall Ruffin Isaac S. Kohane
author_sort	Brett K. Beaulieu-Jones
title	Machine learning for patient risk stratification: standing on, or looking over, the shoulders of clinicians?
title_short	Machine learning for patient risk stratification: standing on, or looking over, the shoulders of clinicians?
title_full	Machine learning for patient risk stratification: standing on, or looking over, the shoulders of clinicians?
title_fullStr	Machine learning for patient risk stratification: standing on, or looking over, the shoulders of clinicians?
title_full_unstemmed	Machine learning for patient risk stratification: standing on, or looking over, the shoulders of clinicians?
title_sort	machine learning for patient risk stratification: standing on, or looking over, the shoulders of clinicians?
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/151095ca45c745cbaf37ac11a1ed124a
work_keys_str_mv	AT brettkbeaulieujones machinelearningforpatientriskstratificationstandingonorlookingovertheshouldersofclinicians AT williamyuan machinelearningforpatientriskstratificationstandingonorlookingovertheshouldersofclinicians AT gabrielabrat machinelearningforpatientriskstratificationstandingonorlookingovertheshouldersofclinicians AT andrewlbeam machinelearningforpatientriskstratificationstandingonorlookingovertheshouldersofclinicians AT griffinweber machinelearningforpatientriskstratificationstandingonorlookingovertheshouldersofclinicians AT marshallruffin machinelearningforpatientriskstratificationstandingonorlookingovertheshouldersofclinicians AT isaacskohane machinelearningforpatientriskstratificationstandingonorlookingovertheshouldersofclinicians
_version_	1718393015896113152

Machine learning for patient risk stratification: standing on, or looking over, the shoulders of clinicians?

Ejemplares similares