Beta- Blocker Efficacy in Acute Myocardial Infarction: A Machine Learning Approach Using the KAMIR-NIH Data Set

초록

Background Current guidelines recommend beta-blockers (BBs) for STEMI and NSTEMI because of mortality benefits, but patient variability is often overlooked. This study aimed to create a machine learning (ML) model to predict individualized mortality in AMI patients and assess BB benefits across diverse profiles to improve clinical outcomes. Methods We analyzed 12,599 AMI patients from the KAMIR-NIH data set, splitting them into a training set (n = 8,467) and a testing set (n = 4,132). Using our ML model, patients were categorized into four quartiles based on mortality risk differences. Quartiles Q1 and Q2 (low risk) showed smaller benefits from BB therapy, and Q3 and Q4 (high risk) showed larger benefits. Results Among various ML models, Binary GLM logistic regression performed best, with an AUC of 0.8428. Our analysis focused on patients with anemia, aged over 65, eGFR below 60, and eGFR below 90, because these factors showed the greatest information gain in the high-risk group. In the high-risk groups, patients on BB had a significant survival advantage (P = 0.009; P < 0.001; P = 0.003; P < 0.001), whereas no significant difference was noted in the low-risk group. Conclusions This study highlights the potential of ML to enhance personalized medicine in AMI management, particularly in optimizing BB treatment. This approach not only enhances the effectiveness of interventions but also embodies the principles of precision medicine, adapting treatment strategies to optimally suit each patient’s unique clinical profile.