Early diagnosis of AMI is crucial for improving patient outcomes, yet current clinical tools often lack the requisite sensitivity and specificity for reliable early detection. As neutrophils are the first innate immune responders mobilized following infarction, we employed an integrated multi-omics and machine learning approach to identify neutrophil-driven molecular signatures with diagnostic potential. By analyzing multiple peripheral blood transcriptomic datasets, we conducted differential expression and immune infiltration analyses, followed by machine learning-based feature selection to pinpoint key genes linked to neutrophil activity. Integration of these findings with single-cell transcriptomic data further clarified the neutrophil-specific expression patterns of candidate genes during AMI progression. Using a joint diagnostic model, we identified MCEMP1, NFE2, and AQP9 as the most informative predictors, with MCEMP1 emerging as the primary contributor. Experimental validation in a murine model of myocardial infarction (MI) confirmed rapid upregulation of MCEMP1 after injury, closely mirroring the kinetics of neutrophil infiltration. Collectively, these findings delineate a neutrophil-associated molecular profile of early AMI and highlight MCEMP1 as a promising noninvasive biomarker and a potential therapeutic target for modulating neutrophil-driven myocardial injury.