BACKGROUND: A recent large-scale clinical trial found that an initial invasive strategy does not improve cardiac outcomes beyond optimized medical therapy in patients with stable coronary artery disease. Novel methods to stratify at-risk patients may refine therapeutic decisions to improve outcomes. METHODS AND RESULTS: In a cohort of 815 consecutive patients referred for evaluation of myocardial ischemia, we determined the net reclassification improvement of the risk of cardiac death or nonfatal myocardial infarction (major adverse cardiac events) incremental to clinical risk models, using guideline-based low (<1%), moderate (1% to 3%), and high (>3%) annual risk categories. In the whole cohort, inducible ischemia demonstrated a strong association with major adverse cardiac events (hazard ratio=14.66; P<0.0001) with low negative event rates of major adverse cardiac events and cardiac death (0.6% and 0.4%, respectively). This prognostic robustness was maintained in patients with previous coronary artery disease (hazard ratio=8.17; P<0.0001; 1.3% and 0.6%, respectively). Adding inducible ischemia to the multivariable clinical risk model (adjusted for age and previous coronary artery disease) improved discrimination of major adverse cardiac events (C statistic, 0.81-0.86; P=0.04; adjusted hazard ratio=7.37; P<0.0001) and reclassified 91.5% of patients at moderate pretest risk (65.7% to low risk; 25.8% to high risk) with corresponding changes in the observed event rates (0.3%/y and 4.9%/y for low and high risk posttest, respectively). Categorical net reclassification index was 0.229 (95% confidence interval, 0.063-0.391). Continuous net reclassification improvement was 1.11 (95% confidence interval, 0.81-1.39). CONCLUSIONS: Stress cardiac magnetic resonance imaging effectively reclassifies patient risk beyond standard clinical variables, specifically in patients at moderate to high pretest clinical risk and in patients with previous coronary artery disease. CLINICAL TRIAL REGISTRATION URL: http://www.clinicaltrials.gov. Unique identifier: NCT01821924.