Success Stories: How AI Is Improving Medication Management for 3 Healthcare Providers

Based on the buzz, it might be easy to believe that AI is a miracle cure for all that ails healthcare. But look beyond the headlines, and you may notice something’s missing: tangible, real-world results showing true time savings and improvements in patient care.   

With escalating costs and tighter financial margins, hospitals and health systems need technology that goes beyond hype to deliver true ROI. See how three healthcare providers are powering their medication management workflows with AI to avoid errors, save time, and meet key quality initiatives. 

Avoiding Medication Errors 

McLean Hospital, a leader in psychiatric care and affiliate of Harvard Medical School, developed a study to measure how accurate medication history data combined with pharmacist expertise might reduce medication errors during care transitions. PSQH recently interviewed the study’s authors, and PLOS ONE published the study here.  

“Having up-to-date, complete, accurate medication history data is a powerful tool to help reconcile a patient’s medication regimen,” said study authors Victoria Vargas, PharmD, BCPS, Assistant Director of Pharmacy and Carol Aboud, PharmD, Chief Pharmacy Officer at McLean Hospital. They note that patients often have inaccurate accounts of their medication history and current medication list, resulting in clinicians calling pharmacies and caregivers or relying on patients to bring a bag of their medications to get a better sense of their medication regimen.  

For the study, prescribers had access to the Fuzion by DrFirst medication history solution to inform prescribing decisions. Clinical-grade AI improves the usability of medication data by translating free text and safely inferring missing prescription instruction (sig) data, streamlining medication workflows in a way that frees clinicians from time-consuming, routine tasks. 

When the patient transitioned from the ED to inpatient care, pharmacy staff used the solution to identify discrepancies between the prior-to-admission medications and inpatient medication orders. Using a novel method to categorize errors and predict the severity of ADEs, the researchers found 82 medication errors among 72 patients in the six-month study period. The most frequent medication errors were categorized as:  

• Dose (33%)  

• Omission (26%)  

• Frequency (19%)  

• Formulation (12%)  

Researchers also found that a significant majority of these errors (88%) may have harmed patients if they had not been corrected by pharmacists.  

Because omissions represent the second-largest category of medication history errors, which the study pharmacists corrected with information from Fuzion by DrFirst, the authors conclude this underscores the importance of the AI-powered medication history resource for transition-of-care pharmacists. They state that otherwise closing gaps in patient medication lists “remains cumbersome and challenging due to long hours spent calling pharmacies, incomplete pharmacy claims data, and laborious interviews with patients and caregivers.”  

Saving Clinicians From Millions of Clicks and Keystrokes  

Medication reconciliation is a vital process to protect patient safety—but it also can be incredibly tedious. That’s because imported medication history often arrives with data gaps that need to be filled manually. 

At Baptist Health in Jacksonville, Florida, nurses and pharmacy technicians were spending a lot of time making phone calls and conducting patient interviews to gather missing information. Then, they had to transcribe that data into their Epic electronic health record (EHR) system by keying in or choosing details from dropdown menus for prescription instructions such as, “Take 1 tablet twice daily for 30 days.”    

In an interview with Bill Russell of This Week Health, Stacey Johnston, M.D., M.H.A., VP and Chief Applications Officer, explained the impact of AI-driven process improvements using Fuzion by DrFirst. 

“We did some studies, and found out that after seven months, we received an additional 23,000 medications that would not have been input into our system without DrFirst,” she said. “And we did a time-motion study that showed the AI saved us 7 million clicks.” 

Watch the video to hear how the health system’s clinicians are spending less time on clicks and keystrokes. 

Achieving Key Quality Measures 

Emory Healthcare was importing medication history data into their Epic EHR via an industry-standard feed. When information was missing from a patient record, clinicians filled the gaps by calling pharmacies to gather and confirm a patient’s medication list, then entered that information manually, which is time-consuming and can increase the likelihood of human error.   

“Sharing high-quality data across our health system is more than a matter of efficiency: It’s also vital to our Epic EHR’s ability to trigger critical safety checks, such as drug interactions and allergy alerts that can help reduce adverse drug events,” said Alistair Erskine, M.D., Chief Information and Digital Officer at Emory, in an interview with Healthcare IT News. 

To address the interconnected challenges of reduced staff productivity and risks to patient safety, the health system turned to the Fuzion by DrFirst medication history solution with clinical-grade AI.  

Previously, when patient medication records were imported into the Epic EHR, prescription instructions, or sigs, often arrived as unstructured free text, with missing pieces of information and using a variety of terms for the same instructions. Using a clinical-grade AI engine to convert that data into the EHR automatically, clinicians have more complete data at the point of care, and pharmacists save time on medication reconciliation. Now, the health system also can track fill rates for these patients, pinpoint gaps in adherence, and identify those who may be at risk of readmission.  

“Actual metrics vary across hospital sites,” said Dr. Erskine, “but initial results show our focus on best possible medication history with the new system has resulted in a 13% improvement in home medications being directly imported into our Epic EHR within 24 hours of admission, saving staff time and reducing the potential for keyboard errors. 

“The AI is enhancing medication history data for 81% of all available home medications so our patient records contain fewer gaps,” he continued. “We also are gathering medication history data for 92% of our patient population age 65 and older, which supports our medication reconciliation initiatives regarding high-risk patients.” 

Putting the ROI of AI Within Reach 

These success stories demonstrate that the right implementation of AI can help health systems move beyond the hype and achieve real, measurable results. Talk to us today to start significantly enhancing your medication management, leading to fewer errors, more efficient workflows, and better patient care.