Predicting the mortality and readmission of in-hospital cardiac arrest patients with electronic health records:a machine learning approach
Journal
Journal of medical Internet research
Journal Volume
23
Journal Issue
9
Pages
e27798
Date Issued
2021-09-13
Author(s)
Ao, Shuang
Winkler, Adrian
Fu, Kuan-Chun
Xu, Jie
Soltani, Rohollah
Abstract
In-hospital cardiac arrest (IHCA) is associated with high mortality and health care costs in the recovery phase. Predicting adverse outcome events, including readmission, improves the chance for appropriate interventions and reduces health care costs. However, studies related to the early prediction of adverse events of IHCA survivors are rare. Therefore, we used a deep learning model for prediction in this study.
Subjects
30-day mortality; 30-day readmission; imbalanced dataset; in-hospital cardiac arrest; machine learning
30-day mortality; 30-day readmission; Imbalanced dataset; In-hospital cardiac arrest; Machine learning
SDGs
Other Subjects
adolescent; adult; aged; Article; autoencoder; cardiovascular mortality; child; cohort analysis; controlled study; deep learning; electronic health record; embedding; female; heart arrest; hospital readmission; hospitalization; human; in hospital cardiac arrest; in-hospital mortality; infant; long short term memory network; major clinical study; male; medical record review; middle aged; national health insurance; newborn; prediction; receiver operating characteristic; recurrent neural network; retrospective study; short term memory; survivor; time series analysis; traditional medicine; very elderly; young adult; electronic health record; heart arrest; hospital; hospital readmission; machine learning; Electronic Health Records; Heart Arrest; Hospitals; Humans; Machine Learning; Patient Readmission
Publisher
JMIR PUBLICATIONS, INC
Type
journal article