Being able to identify prospectively patients who are less likely to adhere to the medication therapies would have important public health implications. It might allow one to tailor certain medications, treatment and follow-up strategies, or interventions to particular individuals that were at greatest risk of non-compliance.

Our analysis will be based on large data sets: hundreds of thousands of patients (health plan members) and thousands of attributes. We will compare the predictive power of thousands of predictors: Medical & RX claim-based Attributes, Socioeconomic Attributes … We tested whether adding information on compliance with other drugs used to treat chronic conditions would improve the predictive ability of administrative data to identify adherent individuals. We will discuss models for prediction of the medication possession ratio (MPR) of several drug classes (statins, ace arbs …).