Prediction of ROSC After Cardiac Arrest Using Machine Learning
Journal
Studies in health technology and informatics
Journal Volume
270
Date Issued
2020-06-16
Author(s)
Liu, Nan
Ho, Andrew Fu Wah
Pek, Pin Pin
Khruekarnchana, Pairoj
Song, Kyoung Jun
Tanaka, Hideharu
Naroo, Ghulam Yasin
Gan, Han Nee
Koh, Zhi Xiong
Ong, Marcus
Abstract
Out-of-hospital cardiac arrest (OHCA) is an important public health problem, with very low survival rate. In treating OHCA patients, the return of spontaneous circulation (ROSC) represents the success of early resuscitation efforts. In this study, we developed a machine learning model to predict ROSC and compared it with the ROSC after cardiac arrest (RACA) score. Results demonstrated the usefulness of machine learning in deriving predictive models.
Subjects
Out-of-hospital cardiac arrest; ROSC; machine learning; random forest
SDGs
Other Subjects
Machine learning; Medical informatics; Medicine; Resuscitation; Cardiac arrest; Machine learning models; Predictive models; Survival rate; Predictive analytics; emergency health service; human; machine learning; out of hospital cardiac arrest; physiological process; resuscitation; retrospective study; survival rate; Cardiopulmonary Resuscitation; Emergency Medical Services; Humans; Machine Learning; Out-of-Hospital Cardiac Arrest; Physiological Phenomena; Retrospective Studies; Survival Rate
Type
conference paper