Pharmacy faculty awarded $2.15M to prevent adverse drug events in ICU

Every year, 1.5 million Americans experience a serious drug event in intensive care units across the country. Two new grants totaling $2.15 million recently awarded to the University of Georgia hope to change that using artificial intelligence-based technology.

An adverse drug event occurs when someone is harmed by a medication, and they’re surprisingly common in ICUs and hospitals in general. In fact, nearly 5% of hospitalized patients will experience one, according to the Patient Safety Network, which makes them one of the most common medical errors in hospitals.

Andrea Sikora, a clinical associate professor in the College of Pharmacy, will lead the project with the focus of making health care safer and more affordable by developing an artificial intelligence-based tool. The new technology will provide adverse drug event predictions to clinicians in real time, hopefully reducing the risk of medical errors and adverse reactions to medications.

The grants are funded by the Agency for Healthcare Research and Quality, a division of the U.S. Department of Health and Human Services. The agency leads federal efforts to improve safety and quality of health care throughout the U.S.

“ICU patients suffer three times more adverse drug events and higher medication errors than any other patients because of their complex, high-risk drug regimens,” said Sikora. “But we have a solution for this: critical care pharmacists. Research indicates that critical care pharmacists integrated into the healthcare team reduce adverse drug events by 70% because they make preventative medication interventions.”

But not all ICU patients are seen by a critical care pharmacist. When a patient does have one assigned to their medical care team, their pharmacist is often responsible for an excessively high number of patients, making errors much more difficult to catch.

“To make patient care safer, more efficient and more equitably distributed, information technology strategies that optimize critical care pharmacy resources are needed,” Sikora said. “Artificial intelligence offers powerful analytical techniques capable of handling big data like that generated in the ICU. Those techniques have never been tested in the setting of improving medication safety through critical care pharmacist-driven interventions, and that is what we are setting out to do.”

Sikora and her team will evaluate a new data-driven health IT metric she developed called the Medication Regimen Complexity-Intensive Care Unit Scoring Tool. Evaluating the tool will be the first step in building the AI-based prediction model.

Susan Smith of the College of Pharmacy, Ye Shen of the College of Public Health, Sheng Li of the School of Computing and Tianming Liu of the School of Computing are co-investigators on the project.




Writer: Mickey Yongue, [email protected]

Contact: Andrea Sikora, 706-721-6760, [email protected]