Cardiovascular disease, particularly acute myocardial infarction (AMI), is a major global health concern. Current diagnostic methods for AMI lack sensitivity and specificity, necessitating novel biomarkers for early detection. In this study, we analyzed AMI gene expression datasets from the GEO database, employing Differential Gene Expression Analysis and WGCNA to identify key genes and co-expression modules. Lactylation-related genes (LRGs) from the MSigDB database were examined to identify those linked to AMI. Unsupervised consensus clustering classified AMI into subtypes, and machine learning models were developed for diagnosis. Immune cell infiltration was assessed using CIBERSORT, xCell, and MCPcounter, focusing on monocyte activation-related LRGs. We identified four LRGs (AMPD2, PYGL, SLC7A7, SAT1) significantly expressed in AMI, validated through in vitro experiments with primary cardiomyocytes from Sprague-Dawley rats. Our findings highlight LRGs as potential early AMI biomarkers and provide insights into myocardial repair mechanisms mediated by histone lactylation and monocytes.