Abstract Background Stroke is the third most common cause of disability and second most common cause of death worldwide. Greater levels of medication adherence after stroke or transient ischemic attack are associated with improved survival. Very few medication adherence prediction models are available and are not validated using external data. Objectives To evaluate the predictive performance of a previously published model for statin and antiplatelet adherence in patients post-stroke/ transient ischemic attack. Methods Adherence was measured by Proportion of Days Covered (PDC) using prescription-filling data. Model performance was evaluated using the following metrics: R2 (proportion of variance explained), Difference between mean observed and mean predicted PDC, and root mean squared error (RMSE). Results In the external validation dataset, 2369 were included in the statin cohort and 2147 patients were included in antiplatelet cohort. R2 was 0.67 and 0.559, for statin and antiplatelet models, respectively. Difference between mean observed and mean predicted PDC was -3.7% and -2.5% for statin and antiplatelet models, respectively. RMSE was 22.9% and 25.5% for statin and antiplatelet models, respectively. Conclusions We performed an external validation of a previously published model for the prediction of 1-year PDC of statins and antiplatelet drugs. The model performed well on a new patient population comprised of post stroke patients. Moreover, our results provide further evidence that simple models based on first 90 days adherence data provide well-calibrated prediction and low bias.