Predictive power of systolic function and congestive heart failure in patients with patients admitted for chest pain without ST elevation in the troponin era

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

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.

Hospital discharge risk score system for the assessment of clinical outcomes in patients with acute myocardial infarction (Korea Acute Myocardial Infarction Registry [KAMIR] score)

Assessment of risk at time of discharge could be a useful tool for guiding postdischarge management. The aim of this study was to develop a novel and simple assessment tool for better hospital discharge risk stratification. The study included 3,997 hospital-discharged patients with acute myocardial infarction who were enrolled in the nationwide prospective Korea Acute Myocardial Infarction Registry-1 (KAMIR-1) from November 2005 through December 2006. The new risk score system was tested in 1,461 hospital-discharged patients who were admitted from January 2007 through January 2008 (KAMIR-2). The new risk score system was compared to the Global Registry of Acute Coronary Events (GRACE) postdischarge risk model during a 12-month clinical follow-up. During 1-year follow-up, all-cause death occurred in 228 patients (5.7%) and 81 patients (5.5%) in the development and validation cohorts, respectively. The new risk score (KAMIR score) was constructed using 6 independent variables related to the primary end point using a multivariable Cox regression analysis: age, Killip class, serum creatinine, no in-hospital percutaneous coronary intervention, left ventricular ejection fraction, and admission glucose based on multivariate-adjusted risk relation. The KAMIR score demonstrated significant differences in its predictive accuracy for 1-year mortality compared to the GRACE score for the developmental and validation cohorts. In conclusion, the KAMIR score for patients with acute myocardial infarction is a simpler and better risk scoring system than the GRACE hospital discharge risk model in prediction of 1-year mortality.