The Problem
Medication discrepancies across care settings can lead to errors, hospitalizations, and adverse drug events, especially in older adults. Despite EHRs, communication gaps exist. Medication reconciliation is a key safety goal but staffing shortages and fragmented data hinder consistent implementation. A Duke transition of care program revealed that 80% of participating patients lacked review at discharged, with 34% having discrepancies. Thus, strategies to improve med review is needed for safety.
Our Solution
The C.L.R (Check, Locate, Review) AI tool streamlines medication reconciliation by aggregating data across EHRs, identifying discrepancies, and highlighting adherence gaps. The AI generated summary will enable more informed and efficient patient interview by providing actionable insights to improve medication list accuracy, reduce errors, and enhance safety at all transition across care settings.
Anticipated Impact
The C.L.R directed AI technology introduces a novel approach by integrating multi-source data aggregation with clinically actionable guidance to support consistent, role-agnostic reviews, and comprehensive medication review across care settings. AI automation has the potential to improve staff efficiency, increase patients’ opportunities to receive medication reviews, minimize unintended med-related hospitalization, and demonstrate scalability across diverse health settings.
