AI Insight
This study used machine learning to analyze electronic health record data from 2,979 adults aged 65 and older to predict whether high-risk medications would be discontinued or dose-reduced. The best-performing model achieved only moderate predictive accuracy (67.71% positive predictive value), with provider EHR usage patterns being among the strongest predictors. The findings suggest that routine EHR data alone cannot reliably predict deprescribing decisions, indicating that important clinical factors influencing these decisions are not captured in standard electronic records.
Why it matters
Healthcare systems seeking to reduce inappropriate medication use in older adults currently lack evidence-based tools to identify which patients are most likely to benefit from deprescribing interventions. Understanding that provider behavior patterns and current EHR data have limited predictive power highlights the need for richer clinical data integration before implementing automated deprescribing support systems.
Understand the Science
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
Potentially inappropriate medications expose older adults to preventable harm, yet deprescribing remains difficult to implement consistently. Although electronic health record (EHR) interventions can reduce prescribing, health systems lack clear evidence about which routinely captured patient, primary care provider (PCP), and intervention-design factors predict medication discontinuation or dose tapering. Understanding these determinants is essential for targeting and scaling deprescribing support. In this study, we conducted the first machine-learning analysis of these trial data. We analyzed 2,979 adults aged 65 years or older and 158 structured EHR features spanning patient characteristics, PCP characteristics and EHR-use behaviors, and deprescribing-tool design. We compared eight models for predicting medication discontinuation or dose tapering and used SHAP to examine feature importance. TabPFN achieved the highest positive predictive value (67.71%), AUROC (74.30%), and AUPRC (60.95%), although overall predictability was moderate. Our findings show that even rich structured EHR data only moderately predict deprescribing, suggesting that important clinical determinants are not captured in routine fields. PCP EHR-use measures accounted for 19 of the 25 highest-ranked TabPFN features, although they also constituted most candidate predictors. The study provides the health system with an informative reference for predicting high-risk medication deprescribing. Future models should incorporate richer clinical context and undergo external validation before informing personalized deprescribing support.
Source: Predicting Deprescribing of High-Risk Medications Using Provider EHR Use and Patient Characteristics