King’s Daughters Medical Center Improves Patient Safety With AI-Powered Medication History

The Challenge

An estimated 66% of data from the nation’s largest medication history database is missing essential sig information—the important short-hand prescribing instructions for dosage, route, and timing of medications. To prevent adverse drug events, hospital staff and clinicians must confer with other providers and pharmacies to gather missing sig data or fill in missing sig information.

At King’s Daughters Medical Center, virtually all patient records had incomplete medication histories and thus required manual intervention by nurses at the point of care. Nurses had to manually transcribe sig information from the patient’s medication history into the current visit list in the EHR—a process that required extra time and was prone to error, potentially endangering patient safety. 

The Solution

The health system’s IT leaders chose DrFirst’s medication history, a patented AI-powered solution that uses natural language processing and machine learning to streamline the medication reconciliation process. By automating the transcription of sig data and codifying sigs into standard terminology, such as “by mouth” versus “oral,” the automated process helped staff resolve gaps by supplying alternative drug IDs for best-case drug matching and details for incomplete or uncommon sigs. Once medication history was normalized, it was clinically actionable and able to trigger safety checks for drug interactions or allergy alerts. 

The Results

Implementation of medication history and clinical-grade AI at King’s Daughters reduced the number of incomplete or error-filled patient medication records, which in turn minimized pharmacy  call-backs, workflow disruptions, and patient treatment delays. It also significantly reduced the average number of “clicks” required for medication reconciliation, resulting in additional time  and financial savings.

After implementing the tool, medication reconciliation required a total of 45,000 fewer clicks per month, compared with pre-implementation data. The resulting time savings of 34 hours per month for clinicians (404 hours/year) translates into more than $11,000 in recaptured nursing productivity over a 12-month period, based on 19,390 annual patient visits and an average of five medications per patient.

More significantly, the solution appears to have contributed to improved patient safety and  health outcomes. In the first seven months following implementation of medication history with  clinical-grade AI, King’s Daughters’ overall 30-day readmission rate fell by 11.3%, from 6.2%  prior to implementation to 5.5% post-implementation.  

“The team believes that the improved accuracy of medication dosage accounts for a significant portion of the decrease in readmissions, possibly due to a decline in post-discharge adverse drug reactions.”  
— Joe Farr, RN Clinical Applications Coordinator, King’s Daughters Medical Center