A Data-Driven Framework for Polypharmacy Optimization: Integrating Clinical Decision Support and Predictive Analytics to Reduce Risk and Simplify Regimens

Abstract

Polypharmacy is pervasive in outpatient care and increases the risk of adverse drug events (ADEs), drug–drug

interactions (DDIs), and nonadherence driven by regimen complexity and cost. This paper proposes an integrated

framework for polypharmacy optimization that couples evidence-based deprescribing, CDSS-enabled interaction

screening, and patient-centered counseling to simplify regimens while safeguarding outcomes. Using a mixed-

methods design, we evaluate changes in medication regimen complexity (MRCI), clinically significant DDI rates,

adherence by daily dose burden, and ADE incidence. Results show meaningful reductions in MRCI and DDI rates,

improved adherence when daily doses are reduced, and lower ADEs post-intervention. We conclude that aligning

deprescribing protocols (STOPP/START, Beers, MAI) with algorithmic checks and shared decision-making can

materially improve safety, adherence, and equity in outpatient pharmacotherapy.