Personalized predictions of patient outcomes during and after hospitalization using artificial intelligence

Abstract Hospital systems, payers, and regulators have focused on reducing length of stay (LOS) and early readmission, with uncertain benefit. Interpretable machine learning (ML) may assist in transparently identifying the risk of important outcomes. We conducted a retrospective cohort study of hosp...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	C. Beau Hilton, Alex Milinovich, Christina Felix, Nirav Vakharia, Timothy Crone, Chris Donovan, Andrew Proctor, Aziz Nazha
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2020
Materias:	Computer applications to medicine. Medical informatics R858-859.7
Acceso en línea:	https://doaj.org/article/f597209c04d945e28c2088d6d39041c2
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:f597209c04d945e28c2088d6d39041c2
record_format	dspace
spelling	oai:doaj.org-article:f597209c04d945e28c2088d6d39041c22021-12-02T18:18:07ZPersonalized predictions of patient outcomes during and after hospitalization using artificial intelligence10.1038/s41746-020-0249-z2398-6352https://doaj.org/article/f597209c04d945e28c2088d6d39041c22020-04-01T00:00:00Zhttps://doi.org/10.1038/s41746-020-0249-zhttps://doaj.org/toc/2398-6352Abstract Hospital systems, payers, and regulators have focused on reducing length of stay (LOS) and early readmission, with uncertain benefit. Interpretable machine learning (ML) may assist in transparently identifying the risk of important outcomes. We conducted a retrospective cohort study of hospitalizations at a tertiary academic medical center and its branches from January 2011 to May 2018. A consecutive sample of all hospitalizations in the study period were included. Algorithms were trained on medical, sociodemographic, and institutional variables to predict readmission, length of stay (LOS), and death within 48–72 h. Prediction performance was measured by area under the receiver operator characteristic curve (AUC), Brier score loss (BSL), which measures how well predicted probability matches observed probability, and other metrics. Interpretations were generated using multiple feature extraction algorithms. The study cohort included 1,485,880 hospitalizations for 708,089 unique patients (median age of 59 years, first and third quartiles (QI) [39, 73]; 55.6% female; 71% white). There were 211,022 30-day readmissions for an overall readmission rate of 14% (for patients ≥65 years: 16%). Median LOS, including observation and labor and delivery patients, was 2.94 days (QI [1.67, 5.34]), or, if these patients are excluded, 3.71 days (QI [2.15, 6.51]). Predictive performance was as follows: 30-day readmission (AUC 0.76/BSL 0.11); LOS > 5 days (AUC 0.84/BSL 0.15); death within 48–72 h (AUC 0.91/BSL 0.001). Explanatory diagrams showed factors that impacted each prediction.C. Beau HiltonAlex MilinovichChristina FelixNirav VakhariaTimothy CroneChris DonovanAndrew ProctorAziz NazhaNature PortfolioarticleComputer applications to medicine. Medical informaticsR858-859.7ENnpj Digital Medicine, Vol 3, Iss 1, Pp 1-8 (2020)
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 C. Beau Hilton Alex Milinovich Christina Felix Nirav Vakharia Timothy Crone Chris Donovan Andrew Proctor Aziz Nazha Personalized predictions of patient outcomes during and after hospitalization using artificial intelligence
description	Abstract Hospital systems, payers, and regulators have focused on reducing length of stay (LOS) and early readmission, with uncertain benefit. Interpretable machine learning (ML) may assist in transparently identifying the risk of important outcomes. We conducted a retrospective cohort study of hospitalizations at a tertiary academic medical center and its branches from January 2011 to May 2018. A consecutive sample of all hospitalizations in the study period were included. Algorithms were trained on medical, sociodemographic, and institutional variables to predict readmission, length of stay (LOS), and death within 48–72 h. Prediction performance was measured by area under the receiver operator characteristic curve (AUC), Brier score loss (BSL), which measures how well predicted probability matches observed probability, and other metrics. Interpretations were generated using multiple feature extraction algorithms. The study cohort included 1,485,880 hospitalizations for 708,089 unique patients (median age of 59 years, first and third quartiles (QI) [39, 73]; 55.6% female; 71% white). There were 211,022 30-day readmissions for an overall readmission rate of 14% (for patients ≥65 years: 16%). Median LOS, including observation and labor and delivery patients, was 2.94 days (QI [1.67, 5.34]), or, if these patients are excluded, 3.71 days (QI [2.15, 6.51]). Predictive performance was as follows: 30-day readmission (AUC 0.76/BSL 0.11); LOS > 5 days (AUC 0.84/BSL 0.15); death within 48–72 h (AUC 0.91/BSL 0.001). Explanatory diagrams showed factors that impacted each prediction.
format	article
author	C. Beau Hilton Alex Milinovich Christina Felix Nirav Vakharia Timothy Crone Chris Donovan Andrew Proctor Aziz Nazha
author_facet	C. Beau Hilton Alex Milinovich Christina Felix Nirav Vakharia Timothy Crone Chris Donovan Andrew Proctor Aziz Nazha
author_sort	C. Beau Hilton
title	Personalized predictions of patient outcomes during and after hospitalization using artificial intelligence
title_short	Personalized predictions of patient outcomes during and after hospitalization using artificial intelligence
title_full	Personalized predictions of patient outcomes during and after hospitalization using artificial intelligence
title_fullStr	Personalized predictions of patient outcomes during and after hospitalization using artificial intelligence
title_full_unstemmed	Personalized predictions of patient outcomes during and after hospitalization using artificial intelligence
title_sort	personalized predictions of patient outcomes during and after hospitalization using artificial intelligence
publisher	Nature Portfolio
publishDate	2020
url	https://doaj.org/article/f597209c04d945e28c2088d6d39041c2
work_keys_str_mv	AT cbeauhilton personalizedpredictionsofpatientoutcomesduringandafterhospitalizationusingartificialintelligence AT alexmilinovich personalizedpredictionsofpatientoutcomesduringandafterhospitalizationusingartificialintelligence AT christinafelix personalizedpredictionsofpatientoutcomesduringandafterhospitalizationusingartificialintelligence AT niravvakharia personalizedpredictionsofpatientoutcomesduringandafterhospitalizationusingartificialintelligence AT timothycrone personalizedpredictionsofpatientoutcomesduringandafterhospitalizationusingartificialintelligence AT chrisdonovan personalizedpredictionsofpatientoutcomesduringandafterhospitalizationusingartificialintelligence AT andrewproctor personalizedpredictionsofpatientoutcomesduringandafterhospitalizationusingartificialintelligence AT aziznazha personalizedpredictionsofpatientoutcomesduringandafterhospitalizationusingartificialintelligence
_version_	1718378309512855552

Personalized predictions of patient outcomes during and after hospitalization using artificial intelligence

Ejemplares similares