AI Health Care Tool To Help Lower Patient Readmission Rates

An artificial intelligence (AI) tool being developed at West Virginia University (WVU) could lessen medication errors that send recently discharged patients back to the hospital.

A release from WVU Pharmacy stated at least 1.5 million people are harmed by medication errors every year, according to the Academy of Managed Care Pharmacy. They say the cost for treating these drug-related injuries occurring in hospitals alone is estimated at $3.5 billion annually.

At issue is the standard medication reconciliation clinicians perform before patients are discharged from the hospital. The prescription and treatment review is meant to develop a comprehensive but proper list of meds and treatments going forward.  

The problem is, with multiple charting inputs, the procedure often becomes error prone. WVU Pharmacy professors say the AI tool will go through each of the patient’s records for the medication reconciliation process, building an alert system that shows if the patient has a higher chance of getting readmitted.

“This is where 85 percent of the errors happen,” said project leader Abdullah Al-Mamun, assistant professor in the WVU School of Pharmacy Department of Pharmaceutical Systems and Policy. “During a patient’s time in the hospital, medications are changed to improve the outcome. The patient cannot go home with the same amounts of medications they were given in the hospital. There should be an adjustment.”

Mamun said the AI tool will go through each of the patient’s records for the medication reconciliation process, building an alert system that shows if the patient has a higher chance of getting readmitted.

In the release, Al-Mamun points to studies showing a 50 percent reduction in 30-day readmission rates when a transition-of-care pharmacist took over medication reconciliation. His project aims to make the pharmacist’s job more efficient and effective through this AI-driven tool.

“That’s where the AI comes in,” Mamun said. “It will pull all this data and using different algorithms will build a profile for the patient. That will make the process more accurate and much faster and improve medication safety.”

With grant funding, the research team will first develop an alert system prototype. The next step will be to integrate the tool into a hospital’s electronic data system and run a pilot test.