Observing versus predicting: initial patterns of filling predict long-term adherence more accurately than high-dimensional modeling techniques
Despite the proliferation of databases with increasingly rich patient data, prediction of medication adherence remains poor. We proposed and evaluated approaches for improved adherence prediction. We identified Medicare beneficiaries who received prescription drug coverage through CVS Caremark and initiated a statin. A total of 643 variables were identified at baseline from prior claims and linked Census data. In addition, we identified three post-baseline predictors, indicators of adherence to statins during each of the first 3 months of follow-up. We estimated 10 models predicting subsequent adherence, using logistic regression and boosted logistic regression, a nonparametric data-mining technique. We found that observed adherence immediately after initiation predicted future adherence for patients whose initial dispensings were relatively short.