A Stacking Ensemble Model to Predict Daily Number of Hospital Admissions for Cardiovascular Diseases

With lifestyle and environmental changes, the prevalence of cardiovascular diseases (CVDs) is trending upwards, putting pressure on the limited medical resources. Accurate forecasting of daily counts of hospital admissions (HAs) for CVDs is helpful to optimize medical resources. In this study, we pr...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhixu Hu, Hang Qiu, Ziqi Su, Minghui Shen, Ziyu Chen
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2020
Materias:	Cardiovascular diseases hospital admissions machine learning stacking ensemble model sequential forward floating selection direct prediction strategy Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/10c4a7c71c6e4c85b917bf094e2a989e
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:10c4a7c71c6e4c85b917bf094e2a989e
record_format	dspace
spelling	oai:doaj.org-article:10c4a7c71c6e4c85b917bf094e2a989e2021-11-20T00:00:32ZA Stacking Ensemble Model to Predict Daily Number of Hospital Admissions for Cardiovascular Diseases2169-353610.1109/ACCESS.2020.3012143https://doaj.org/article/10c4a7c71c6e4c85b917bf094e2a989e2020-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9149874/https://doaj.org/toc/2169-3536With lifestyle and environmental changes, the prevalence of cardiovascular diseases (CVDs) is trending upwards, putting pressure on the limited medical resources. Accurate forecasting of daily counts of hospital admissions (HAs) for CVDs is helpful to optimize medical resources. In this study, we proposed a stacking ensemble model with direct prediction strategy to predict the daily number of CVDs admissions using HAs data, air pollution data, and meteorological data. The sequential forward floating selection method with early stopping was applied for feature selection. Five machine learning models, including linear regression (LR), support vector regression (SVR), extreme gradient boosting (XGBoost), random forest (RF), and gradient boosting decision tree (GBDT), were utilized as base learners to construct the stacking model. We compared the performance of the proposed stacking model with the five base learners in three datasets. The experimental results indicated that our model performed best in three datasets under four evaluation criteria, including mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE), and coefficient of determination (R<sup>2</sup>). Particularly, in the CVDs dataset, the MAPE is 15.103 for LR, 11.862 for SVR, 10.571 for XGBoost, 10.378 for GBDT, 10.333 for RF, and 9.679 for the stacking model. Compared with the best base learner RF, the MAPE, RMSE, and MAE of the stacking model decreased by 6.3%, 7.4%, and 6.3%, respectively, and the R<sup>2</sup> improved by 1.7%. It is evident that the proposed stacking model can effectively forecast the daily number of hospitalizations for CVDs and provide decision support for hospital managers.Zhixu HuHang QiuZiqi SuMinghui ShenZiyu ChenIEEEarticleCardiovascular diseaseshospital admissionsmachine learningstacking ensemble modelsequential forward floating selectiondirect prediction strategyElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 8, Pp 138719-138729 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	Cardiovascular diseases hospital admissions machine learning stacking ensemble model sequential forward floating selection direct prediction strategy Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Cardiovascular diseases hospital admissions machine learning stacking ensemble model sequential forward floating selection direct prediction strategy Electrical engineering. Electronics. Nuclear engineering TK1-9971 Zhixu Hu Hang Qiu Ziqi Su Minghui Shen Ziyu Chen A Stacking Ensemble Model to Predict Daily Number of Hospital Admissions for Cardiovascular Diseases
description	With lifestyle and environmental changes, the prevalence of cardiovascular diseases (CVDs) is trending upwards, putting pressure on the limited medical resources. Accurate forecasting of daily counts of hospital admissions (HAs) for CVDs is helpful to optimize medical resources. In this study, we proposed a stacking ensemble model with direct prediction strategy to predict the daily number of CVDs admissions using HAs data, air pollution data, and meteorological data. The sequential forward floating selection method with early stopping was applied for feature selection. Five machine learning models, including linear regression (LR), support vector regression (SVR), extreme gradient boosting (XGBoost), random forest (RF), and gradient boosting decision tree (GBDT), were utilized as base learners to construct the stacking model. We compared the performance of the proposed stacking model with the five base learners in three datasets. The experimental results indicated that our model performed best in three datasets under four evaluation criteria, including mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE), and coefficient of determination (R<sup>2</sup>). Particularly, in the CVDs dataset, the MAPE is 15.103 for LR, 11.862 for SVR, 10.571 for XGBoost, 10.378 for GBDT, 10.333 for RF, and 9.679 for the stacking model. Compared with the best base learner RF, the MAPE, RMSE, and MAE of the stacking model decreased by 6.3%, 7.4%, and 6.3%, respectively, and the R<sup>2</sup> improved by 1.7%. It is evident that the proposed stacking model can effectively forecast the daily number of hospitalizations for CVDs and provide decision support for hospital managers.
format	article
author	Zhixu Hu Hang Qiu Ziqi Su Minghui Shen Ziyu Chen
author_facet	Zhixu Hu Hang Qiu Ziqi Su Minghui Shen Ziyu Chen
author_sort	Zhixu Hu
title	A Stacking Ensemble Model to Predict Daily Number of Hospital Admissions for Cardiovascular Diseases
title_short	A Stacking Ensemble Model to Predict Daily Number of Hospital Admissions for Cardiovascular Diseases
title_full	A Stacking Ensemble Model to Predict Daily Number of Hospital Admissions for Cardiovascular Diseases
title_fullStr	A Stacking Ensemble Model to Predict Daily Number of Hospital Admissions for Cardiovascular Diseases
title_full_unstemmed	A Stacking Ensemble Model to Predict Daily Number of Hospital Admissions for Cardiovascular Diseases
title_sort	stacking ensemble model to predict daily number of hospital admissions for cardiovascular diseases
publisher	IEEE
publishDate	2020
url	https://doaj.org/article/10c4a7c71c6e4c85b917bf094e2a989e
work_keys_str_mv	AT zhixuhu astackingensemblemodeltopredictdailynumberofhospitaladmissionsforcardiovasculardiseases AT hangqiu astackingensemblemodeltopredictdailynumberofhospitaladmissionsforcardiovasculardiseases AT ziqisu astackingensemblemodeltopredictdailynumberofhospitaladmissionsforcardiovasculardiseases AT minghuishen astackingensemblemodeltopredictdailynumberofhospitaladmissionsforcardiovasculardiseases AT ziyuchen astackingensemblemodeltopredictdailynumberofhospitaladmissionsforcardiovasculardiseases AT zhixuhu stackingensemblemodeltopredictdailynumberofhospitaladmissionsforcardiovasculardiseases AT hangqiu stackingensemblemodeltopredictdailynumberofhospitaladmissionsforcardiovasculardiseases AT ziqisu stackingensemblemodeltopredictdailynumberofhospitaladmissionsforcardiovasculardiseases AT minghuishen stackingensemblemodeltopredictdailynumberofhospitaladmissionsforcardiovasculardiseases AT ziyuchen stackingensemblemodeltopredictdailynumberofhospitaladmissionsforcardiovasculardiseases
_version_	1718419819360944128

A Stacking Ensemble Model to Predict Daily Number of Hospital Admissions for Cardiovascular Diseases

Ejemplares similares