Hong-Jae Choi, Changhee Lee, JinHo Chun, Roma Seol, Yun Mi Lee, Youn-Jung Son
{"title":"Development of a Predictive Model for Survival Over Time in Patients With Out-of-Hospital Cardiac Arrest Using Ensemble-Based Machine Learning.","authors":"Hong-Jae Choi, Changhee Lee, JinHo Chun, Roma Seol, Yun Mi Lee, Youn-Jung Son","doi":"10.1097/CIN.0000000000001145","DOIUrl":null,"url":null,"abstract":"<p><p>As of now, a model for predicting the survival of patients with out-of-hospital cardiac arrest has not been established. This study aimed to develop a model for identifying predictors of survival over time in patients with out-of-hospital cardiac arrest during their stay in the emergency department, using ensemble-based machine learning. A total of 26 013 patients from the Korean nationwide out-of-hospital cardiac arrest registry were enrolled between January 1 and December 31, 2019. Our model, comprising 38 variables, was developed using the Survival Quilts model to improve predictive performance. We found that changes in important variables of patients with out-of-hospital cardiac arrest were observed 10 minutes after arrival at the emergency department. The important score of the predictors showed that the influence of patient age decreased, moving from the highest rank to the fifth. In contrast, the significance of reperfusion attempts increased, moving from the fourth to the highest rank. Our research suggests that the ensemble-based machine learning model, particularly the Survival Quilts, offers a promising approach for predicting survival in patients with out-of-hospital cardiac arrest. The Survival Quilts model may potentially assist emergency department staff in making informed decisions quickly, reducing preventable deaths.</p>","PeriodicalId":50694,"journal":{"name":"Cin-Computers Informatics Nursing","volume":"42 5","pages":"388-395"},"PeriodicalIF":1.3000,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cin-Computers Informatics Nursing","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1097/CIN.0000000000001145","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 0
Abstract
As of now, a model for predicting the survival of patients with out-of-hospital cardiac arrest has not been established. This study aimed to develop a model for identifying predictors of survival over time in patients with out-of-hospital cardiac arrest during their stay in the emergency department, using ensemble-based machine learning. A total of 26 013 patients from the Korean nationwide out-of-hospital cardiac arrest registry were enrolled between January 1 and December 31, 2019. Our model, comprising 38 variables, was developed using the Survival Quilts model to improve predictive performance. We found that changes in important variables of patients with out-of-hospital cardiac arrest were observed 10 minutes after arrival at the emergency department. The important score of the predictors showed that the influence of patient age decreased, moving from the highest rank to the fifth. In contrast, the significance of reperfusion attempts increased, moving from the fourth to the highest rank. Our research suggests that the ensemble-based machine learning model, particularly the Survival Quilts, offers a promising approach for predicting survival in patients with out-of-hospital cardiac arrest. The Survival Quilts model may potentially assist emergency department staff in making informed decisions quickly, reducing preventable deaths.
期刊介绍:
For over 30 years, CIN: Computers, Informatics, Nursing has been at the interface of the science of information and the art of nursing, publishing articles on the latest developments in nursing informatics, research, education and administrative of health information technology. CIN connects you with colleagues as they share knowledge on implementation of electronic health records systems, design decision-support systems, incorporate evidence-based healthcare in practice, explore point-of-care computing in practice and education, and conceptually integrate nursing languages and standard data sets. Continuing education contact hours are available in every issue.