본문 바로가기

Prediction of 1-Year Mortality from Acute Myocardial Infarction Using Machine Learning

문서 유형
연구출판물 · 학술지 논문
등재
SCIEScopus
저널 순위
JCR Q2Scopus Q1
저널
AMERICAN JOURNAL OF CARDIOLOGY133 · pp.23 · 2020
피인용
Web of Science 26Scopus 27
FWCI (Scopus)
0
JCR IF
JCR 2019 2.57
ISSN
0002-9149

저자

  1. 이한철제1저자aDepartment of Cardiology and Medical Research Institute, Pusan National University Hospital, Busan, South Korea
  2. 박진섭교신저자aDepartment of Cardiology and Medical Research Institute, Pusan National University Hospital, Busan, South Korea
  3. 최정천aDepartment of Cardiology and Medical Research Institute, Pusan National University Hospital, Busan, South Korea
  4. 안진희aDepartment of Cardiology and Medical Research Institute, Pusan National University Hospital, Busan, South Korea
  5. 이혜원aDepartment of Cardiology and Medical Research Institute, Pusan National University Hospital, Busan, South Korea
  6. 오준혁aDepartment of Cardiology and Medical Research Institute, Pusan National University Hospital, Busan, South Korea
  7. 최정현aDepartment of Cardiology and Medical Research Institute, Pusan National University Hospital, Busan, South Korea
  8. 차광수aDepartment of Cardiology and Medical Research Institute, Pusan National University Hospital, Busan, South Korea
  9. 홍택종aDepartment of Cardiology and Medical Research Institute, Pusan National University Hospital, Busan, South Korea
  10. Jeong, Myung HobDepartment of Cardiology, Chonnam National University Hospital, Gwangju, South Korea

초록

Risk stratification at hospital discharge could be instrumental in guiding postdischarge care. In this study, the risk models for 1-year mortality using machine learning (ML) were evaluated for guiding management of acute myocardial infarction (AMI) patients. From the Korea Acute Myocardial Infarction Registry (KAMIR) dataset, 22,182 AMI patients were selected. The 1-year all-cause mortality was recorded at 12-month follow-up periods. Anomaly detection was conducted for removing outliers; principal component analysis for dimensionality reduction, recursive feature elimination algorithm for feature selection. Model selection and training were conducted with 70% of the dataset after the creation and cross-validation of hundreds of models with decision trees, ensembles, logistic regressions, and deepnets algorithms. The rest of the dataset (30%) was used for comparison between the ML and KAMIR score-based models. The mean age of the AMI patients was 64 years, 71.8% were male, and 56.7% were eventually diagnosed with ST-elevation myocardial infarction. There were 1,332 patients suffering from all-cause mortality (6%) during a median 338 days of follow-up. The ML models for 1-year mortality were well calibrated (Hosmer-Lemeshow p >0.05) and showed good discrimination (area under the curve for test cohort: 0.918). Compared with the performance of the KAMIR score model, the ML model had a higher area under the curve, net reclassification improvement, and integrated discrimination improvement. The ML model for 1-year mortality was well-calibrated and had excellent discriminatory ability and higher performance. In a comprehensive clinical evaluation process, this model could support risk stratification and management in postdischarge AMI patients. (c) 2020 Elsevier Inc. All rights reserved.

키워드

CONGESTIVE-HEART-FAILUREACUTE CORONARY SYNDROMESST-ELEVATIONSYSTOLIC FUNCTIONRISKPROGNOSISOUTCOMESMARKERMODEL

식별자

Scopus EID
2-s2.0-85089460642
WoS UID
000577955800004