Healthcare providers are increasingly encouraged to improve their patients' adherence to chronic disease medications. Prediction of adherence can identify patients in need of intervention, but most prediction efforts have focused on using claims data, which may be unavailable to providers. Electronic health records (EHR) are readily available and may provide richer information with which to predict adherence than is currently available through claims. In this study using a linked database of complete Medicare Advantage claims and comprehensive EHR from a multi-specialty outpatient practice, we found that claims were highly predictive of patients in the worst adherence trajectory, but EHR data also provided good predictions.