Comparison of machine learning models for the prediction of mortality of patients unplanned extubation in intensive with care units

doi:10.1038/s41598-018-35582-2

CNU IR > College of Sustainable Environment and Recreation > Dept. of Recreation and Health-Care Management > Periodical Articles > Item 310902800/32257

Please use this identifier to cite or link to this item: https://ir.cnu.edu.tw/handle/310902800/32257

Title:	Comparison of machine learning models for the prediction of mortality of patients unplanned extubation in intensive with care units
Authors:	Hsieh, Meng Hsuen Hsieh, Meng Ju Chen, Chin-Ming Hsieh, Chia-Chang Chao, Chien-Ming Lai, Chih-Cheng
Contributors:	Univ Calif Berkeley, Dept Elect Engn & Comp Sci Poznan Univ Med Sci, Dept Med Chia Nan Univ Pharm & Sci, Dept Recreat & Hlth Care Management Chi Mei Med Ctr, Dept Intens Care Med China Med Univ, Childrens Hosp, Dept Pediat
Keywords:	Artificial Neural-Networks Apache-Ii Endotracheal Extubation Prospective Multicenter Self-Extubations Scoring System Classification Icu Validation Outcomes
Date:	2018-11-20
Issue Date:	2019-11-15 15:47:06 (UTC+8)
Publisher:	NATURE PUBLISHING GROUP
Abstract:	Unplanned extubation (UE) can be associated with fatal outcome; however, an accurate model for predicting the mortality of UE patients in intensive care units (ICU) is lacking. Therefore, we aim to compare the performances of various machine learning models and conventional parameters to predict the mortality of UE patients in the ICU. A total of 341 patients with UE in ICUs of Chi-Mei Medical Center between December 2008 and July 2017 were enrolled and their demographic features, clinical manifestations, and outcomes were collected for analysis. Four machine learning models including artificial neural networks, logistic regression models, random forest models, and support vector machines were constructed and their predictive performances were compared with each other and conventional parameters. Of the 341 UE patients included in the study, the ICU mortality rate is 17.6%. The random forest model is determined to be the most suitable model for this dataset with F-1 0.860, precision 0.882, and recall 0.850 in the test set, and an area under receiver operating characteristic (ROC) curve of 0.910 (SE: 0.022, 95% CI: 0.867-0.954). The area under ROC curves of the random forest model was significantly greater than that of Acute Physiology and Chronic Health Evaluation (APACHE) II (0.779, 95% CI: 0.716-0.841), Therapeutic Intervention Scoring System (TISS) (0.645, 95% CI: 0.564-0.726), and Glasgow Coma scales (0.577, 95%: CI 0.497-0.657). The results revealed that the random forest model was the best model to predict the mortality of UE patients in ICUs.
???metadata.dc.relation.uri???:	http://dx.doi.org/10.1038/s41598-018-35582-2
Relation:	Nature Communications, v.8, 17116
Appears in Collections:	[Dept. of Recreation and Health-Care Management] Periodical Articles

Files in This Item:

File	Description	Size	Format
10.1038-s41598-018-35582-2.pdf		1105Kb	Adobe PDF	446	View/Open
index.html		0Kb	HTML	1896	View/Open

Loading...