Zullig, Leah LJazowski, Shelley AWang, Tracy YHellkamp, AnneWojdyla, DanielThomas, LaineEgbuonu-Davis, LisaBeal, AnneBosworth, Hayden B2023-08-092023-08-092019-120017-91241475-6773https://hdl.handle.net/10161/28703<h4>Objective</h4>To compare predictive analytic approaches to characterize medication nonadherence and determine under which circumstances each method may be best applied.<h4>Data sources/study setting</h4>Medicare Parts A, B, and D claims from 2007 to 2013.<h4>Study design</h4>We evaluated three statistical techniques to predict statin adherence (proportion of days covered [PDC ≥ 80 percent]) in the year following discharge: standard logistic regression with backward selection of covariates, least absolute shrinkage and selection operator (LASSO), and random forest. We used the C-index to assess model discrimination and decile plots comparing predicted values to observed event rates to evaluate model performance.<h4>Data extraction</h4>We identified 11 969 beneficiaries with an acute myocardial infarction (MI)-related admission from 2007 to 2012, who filled a statin prescription at, or shortly after, discharge.<h4>Principal findings</h4>In all models, prior statin use was the most important predictor of future adherence (OR = 3.65, 95% CI: 3.34-3.98; OR = 3.55). Although the LASSO regression model selected nearly 90 percent of all candidate predictors, all three analytic approaches had moderate discrimination (C-index ranging from 0.664 to 0.673).<h4>Conclusions</h4>Although none of the models emerged as clearly superior, predictive analytics could proactively determine which patients are at risk of nonadherence, thus allowing for timely engagement in adherence-improving interventions.HumansMyocardial InfarctionHydroxymethylglutaryl-CoA Reductase InhibitorsLogistic ModelsRetrospective StudiesForecastingAgedAged, 80 and overMedicareInsurance Claim ReviewUnited StatesFemaleMaleMedication AdherenceJournal article2023-08-09