Chronic polytherapy after myocardial infarction: the trade-off between hospital and community-based providers in determining adherence to medication

Background The benefits of chronic polytherapy in reducing readmissions and death after myocardial infarction (MI) have been clearly shown. However, real-world evidence shows poor medication adherence and large geographic variation, suggesting critical issues in access to optimal care. Our objectives were to measure adherence to polytherapy, to compare the amount of variation attributable to hospitals of discharge and to community-based providers, and to identify determinants of adherence to medications. Methods This is a population-based study. Data were obtained from the information systems of the Lazio and Tuscany Regions, Italy (9.5 million inhabitants). Patients hospitalized with incident MI in 2010-2014 were analyzed. The outcome measure was medication adherence, defined as a Medication Possession Ratio (MPR) >= 0.75 for at least 3 of the following drugs: antiplatelets, beta-blockers, ACEI/ARBs, statins. A 2-year cohort-study was performed. Cross-classified multilevel models were applied to analyze geographic variation. The variance components attributable to hospitals of discharge and community-based providers were expressed as Median Odds Ratio (MOR). Results A total of 32,962 patients were enrolled. About 63% of patients in the Lazio cohort and 59% of the Tuscan cohort were adherent to chronic polytherapy. Women and patients aged 85 years and over were most at risk of non-adherence. In both regions, adherence was higher for patients discharged from cardiology wards (Lazio: OR = 1.58, p < 0.001, Tuscany: OR = 1.59, p < 0.001) and for patients with a percutaneous coronary intervention during the index admission. Relevant variation between community-based providers was observed, though when the hospital of discharge was included as a cross-classified level, in both Lazio and Tuscany regions the variation attributable to hospitals of discharge was the only significant component (Lazio: MOR = 1.30, p = 0.001; Tuscany: MOR = 1.31, p = 0.001). Conclusion Adherence to best practice treatments after MI is not consistent with clinical guidelines, and varies between patient groups as well as within and between regions. The variation attributable to providers is affected by the hospital of discharge, up to two years from the acute episode. This variation is likely to be attributable to hospital discharge processes, and could be reduced through appropriate policy levers.