Coronary heart disease is the most common cause of death, and the number of individuals at risk is increasing. To better manage this pandemic, improved tool for risk prediction, including more accurate biomarkers are needed. The objective of this study was to assess the utility of circulating microRNAs (miRs) to predict future fatal acute myocardial infarction (AMI) in healthy participants. We performed a prospective nested case-control study with 10-year observation period and fatal AMI as endpoint. In total, 179 miRs were quantified by real-time polymerase chain reaction in serum of 112 healthy participants (40-70years) that either (1) suffered from fatal AMI within 10years [n=56], or (2) remained healthy [n=56, risk factor-matched controls]. Candidate miRs were validated in a separate cohort of healthy individuals (n=100). Twelve miRs were differently expressed in cases and controls in the derivation cohort (p<0.05). Among these, 10 miRs differed significantly between cases and controls in the validation cohort (p<0.05). We identified gender dimorphisms, as miR-424-5p and miR-26a-5p were associated exclusively with risk in men and women, respectively. The best model for predicting future AMI consisted of miR-106a-5p, miR-424-5p, let-7g-5p, miR-144-3p and miR-660-5p, providing 77.6% correct classification for both genders, and 74.1% and 81.8% for men and women, respectively. Adding these 5 miRs to the Framingham Risk Score, increased the AUC from 0.72 to 0.91 (p<0.001). In conclusion, we identified several miRs associated with future AMI, revealed gender-specific associations, and proposed a panel of 5 miRs to enhance AMI risk prediction in healthy individuals.