To identify electrocardiographic predictors of left ventricular enlargement or persistent dysfunction following a myocardial infarction. Baseline and predischarge 12-lead electrocardiograms (ECGs) from 272 patients with anterior myocardial infarction who were enrolled in the Healing and Early Afterload Reducing Therapy trial were evaluated and related to echocardiographic data obtained at baseline and day 90. ST-segment elevation, QRS score, and number of negative T waves were assessed at both time points. The majority of patients (87%; n = 237) received reperfusion therapy. Multivariate models were used to adjust for potential confounders, including maximal creatine kinase level and ejection fraction at baseline. None of the baseline electrocardiographic variables independently predicted ventricular enlargement or recovery of function. In contrast, the sum of ST- and maximum ST-segment elevation, and the number of leads with ST-segment elevation > or =1 mm in the predischarge ECG, were independent predictors of ventricular enlargement from baseline to day 90. Each lead with ST-segment elevation > or =1 mm was associated with 3.5 mL of ventricular enlargement (95% confidence interval [CI]: 1.6 to 5.5 mL; P <0.0001). Similarly, the sum of ST-segment elevation (odds ratio [OR] = 0.78; 95% CI: 0.69 to 0.89; P <0.0001), the maximum ST-segment elevation (OR = 0.25; 95% CI: 0.13 to 0.45; P <0.0001), and the number of leads with ST-segment elevation > or =1 mm (OR = 0.58; 95% CI: 0.45 to 0.74; P <0.0001) were independently associated with a lower likelihood of recovery of function at day 90. Predischarge ECG may be a useful tool for early identification of patients at risk of ventricular enlargement and persistent dysfunction following myocardial infarction.