BACKGROUND: Hypertrophic cardiomyopathy (HCM) is the leading cause of sudden cardiac death in athletes. However, preparticipation electrocardiogram (ECG) screening has been criticized for failing to meet cost-effectiveness thresholds, in part because of high false-positive rates. We sought to evaluate whether a highly automated software algorithm could be used for a high throughput, population-based screening program and address several of the limitations seen with population-based screening METHODS: A proprietary computed algorithm was created based on both voltage- as well as Seattle-based ECG criteria. Different cut points for Q-wave depth, Q-wave length, the degree of ST depression, the degree of T-wave inversion, and left ventricular voltage were analyzed for optimum sensitivity and specificity. After developing receiver operating characteristic curves for each criterion, different cut points were trialed together on our data set to obtain settings to optimize sensitivity and specificity. RESULTS: The automated algorithm was capable of identifying patients with HCM based on ECG with 88.6% sensitivity and 98% specificity, compared to a sensitivity of 90.2% and specificity of 96% when the ECGs were read by physicians according to the Seattle Criteria. Adding voltage criteria improved the sensitivity of the algorithm with a mild decrease in specificity. Optimum sensitivity with this automated software was 98%; optimum specificity was 96%. CONCLUSION: Computer-automated ECG screening for HCM is feasible. Evaluation of automated ECG algorithms in larger and more diverse populations is warranted.