Comparison of deep learning with traditional models to predict preventable acute care use and spending among heart failure patients

Abstract Recent health reforms have created incentives for cardiologists and accountable care organizations to participate in value-based care models for heart failure (HF). Accurate risk stratification of HF patients is critical to efficiently deploy interventions aimed at reducing preventable util...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Maor Lewis, Guy Elad, Moran Beladev, Gal Maor, Kira Radinsky, Dor Hermann, Yoav Litani, Tal Geller, Jesse M. Pines, Nathan l. Shapiro, Jose F. Figueroa
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/f374a3edbdbc4699a647b014e2baa60d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:f374a3edbdbc4699a647b014e2baa60d
record_format	dspace
spelling	oai:doaj.org-article:f374a3edbdbc4699a647b014e2baa60d2021-12-02T14:12:08ZComparison of deep learning with traditional models to predict preventable acute care use and spending among heart failure patients10.1038/s41598-020-80856-32045-2322https://doaj.org/article/f374a3edbdbc4699a647b014e2baa60d2021-01-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-80856-3https://doaj.org/toc/2045-2322Abstract Recent health reforms have created incentives for cardiologists and accountable care organizations to participate in value-based care models for heart failure (HF). Accurate risk stratification of HF patients is critical to efficiently deploy interventions aimed at reducing preventable utilization. The goal of this paper was to compare deep learning approaches with traditional logistic regression (LR) to predict preventable utilization among HF patients. We conducted a prognostic study using data on 93,260 HF patients continuously enrolled for 2-years in a large U.S. commercial insurer to develop and validate prediction models for three outcomes of interest: preventable hospitalizations, preventable emergency department (ED) visits, and preventable costs. Patients were split into training, validation, and testing samples. Outcomes were modeled using traditional and enhanced LR and compared to gradient boosting model and deep learning models using sequential and non-sequential inputs. Evaluation metrics included precision (positive predictive value) at k, cost capture, and Area Under the Receiver operating characteristic (AUROC). Deep learning models consistently outperformed LR for all three outcomes with respect to the chosen evaluation metrics. Precision at 1% for preventable hospitalizations was 43% for deep learning compared to 30% for enhanced LR. Precision at 1% for preventable ED visits was 39% for deep learning compared to 33% for enhanced LR. For preventable cost, cost capture at 1% was 30% for sequential deep learning, compared to 18% for enhanced LR. The highest AUROCs for deep learning were 0.778, 0.681 and 0.727, respectively. These results offer a promising approach to identify patients for targeted interventions.Maor LewisGuy EladMoran BeladevGal MaorKira RadinskyDor HermannYoav LitaniTal GellerJesse M. PinesNathan l. ShapiroJose F. FigueroaNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-10 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Maor Lewis Guy Elad Moran Beladev Gal Maor Kira Radinsky Dor Hermann Yoav Litani Tal Geller Jesse M. Pines Nathan l. Shapiro Jose F. Figueroa Comparison of deep learning with traditional models to predict preventable acute care use and spending among heart failure patients
description	Abstract Recent health reforms have created incentives for cardiologists and accountable care organizations to participate in value-based care models for heart failure (HF). Accurate risk stratification of HF patients is critical to efficiently deploy interventions aimed at reducing preventable utilization. The goal of this paper was to compare deep learning approaches with traditional logistic regression (LR) to predict preventable utilization among HF patients. We conducted a prognostic study using data on 93,260 HF patients continuously enrolled for 2-years in a large U.S. commercial insurer to develop and validate prediction models for three outcomes of interest: preventable hospitalizations, preventable emergency department (ED) visits, and preventable costs. Patients were split into training, validation, and testing samples. Outcomes were modeled using traditional and enhanced LR and compared to gradient boosting model and deep learning models using sequential and non-sequential inputs. Evaluation metrics included precision (positive predictive value) at k, cost capture, and Area Under the Receiver operating characteristic (AUROC). Deep learning models consistently outperformed LR for all three outcomes with respect to the chosen evaluation metrics. Precision at 1% for preventable hospitalizations was 43% for deep learning compared to 30% for enhanced LR. Precision at 1% for preventable ED visits was 39% for deep learning compared to 33% for enhanced LR. For preventable cost, cost capture at 1% was 30% for sequential deep learning, compared to 18% for enhanced LR. The highest AUROCs for deep learning were 0.778, 0.681 and 0.727, respectively. These results offer a promising approach to identify patients for targeted interventions.
format	article
author	Maor Lewis Guy Elad Moran Beladev Gal Maor Kira Radinsky Dor Hermann Yoav Litani Tal Geller Jesse M. Pines Nathan l. Shapiro Jose F. Figueroa
author_facet	Maor Lewis Guy Elad Moran Beladev Gal Maor Kira Radinsky Dor Hermann Yoav Litani Tal Geller Jesse M. Pines Nathan l. Shapiro Jose F. Figueroa
author_sort	Maor Lewis
title	Comparison of deep learning with traditional models to predict preventable acute care use and spending among heart failure patients
title_short	Comparison of deep learning with traditional models to predict preventable acute care use and spending among heart failure patients
title_full	Comparison of deep learning with traditional models to predict preventable acute care use and spending among heart failure patients
title_fullStr	Comparison of deep learning with traditional models to predict preventable acute care use and spending among heart failure patients
title_full_unstemmed	Comparison of deep learning with traditional models to predict preventable acute care use and spending among heart failure patients
title_sort	comparison of deep learning with traditional models to predict preventable acute care use and spending among heart failure patients
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/f374a3edbdbc4699a647b014e2baa60d
work_keys_str_mv	AT maorlewis comparisonofdeeplearningwithtraditionalmodelstopredictpreventableacutecareuseandspendingamongheartfailurepatients AT guyelad comparisonofdeeplearningwithtraditionalmodelstopredictpreventableacutecareuseandspendingamongheartfailurepatients AT moranbeladev comparisonofdeeplearningwithtraditionalmodelstopredictpreventableacutecareuseandspendingamongheartfailurepatients AT galmaor comparisonofdeeplearningwithtraditionalmodelstopredictpreventableacutecareuseandspendingamongheartfailurepatients AT kiraradinsky comparisonofdeeplearningwithtraditionalmodelstopredictpreventableacutecareuseandspendingamongheartfailurepatients AT dorhermann comparisonofdeeplearningwithtraditionalmodelstopredictpreventableacutecareuseandspendingamongheartfailurepatients AT yoavlitani comparisonofdeeplearningwithtraditionalmodelstopredictpreventableacutecareuseandspendingamongheartfailurepatients AT talgeller comparisonofdeeplearningwithtraditionalmodelstopredictpreventableacutecareuseandspendingamongheartfailurepatients AT jessempines comparisonofdeeplearningwithtraditionalmodelstopredictpreventableacutecareuseandspendingamongheartfailurepatients AT nathanlshapiro comparisonofdeeplearningwithtraditionalmodelstopredictpreventableacutecareuseandspendingamongheartfailurepatients AT joseffigueroa comparisonofdeeplearningwithtraditionalmodelstopredictpreventableacutecareuseandspendingamongheartfailurepatients
_version_	1718391821154910208

Comparison of deep learning with traditional models to predict preventable acute care use and spending among heart failure patients

Ejemplares similares