NSF Grant to Rethink Drug-Drug Interaction Alerts for Better Compliance
February 25, 2014
Jon Duke, M.D., assistant professor at the IU School of Medicine and chief innovation officer at the Regenstrief Institute, and Davide Bolchini, PhD, assistant professor of human-centered computing at the IU School of Informatics and Computing at IUPUI have been awarded over $589,000 from the National Science Foundation(NSF) to rethink the role of drug-drug interaction alerts during medication prescribing.
The 3-year grant, awarded by the NSF through the NSF-NIH interagency program “Smart and Connected Health”, allows Drs. Duke and Bolchini to develop human-computer interaction research aimed at studying the physician’s interaction with drug-drug clinical alerts in hospital setting and reimagine the design of these critical components to enhance compliance and medication safety.
“Although physicians routinely receive drug-drug interaction (DDI) alerts during daily medication prescribing, the effectiveness of such alerts remains extremely low, with up to 96% of warnings being ignored by physicians on a daily basis,” Duke said. “There is often a disconnect between the trusted advice shared by peers in collaborative decision making, and the low compliance when individuals interact with computerized safety alerts from a computer. So rather than focusing on alerts themselves, we are instead looking at how to improve the trust between physician and computer.”
“Our goal is to transform drug safety alerts from oft-ignored warnings to trusted tools that advise physicians in daily decision making,” says Bolchini. “Our starting point to address this issue is looking at whom physicians do trust: their medical colleagues and mentors. Now three months into the project, we have started investigating principles for alert design that are based on what physicians consider important when taking advice from peers in their daily clinical work. A key aspect of the work is to generate alerts that are perceived as collaborating with the providers rather than critiquing every micro-decision.” The investigators, along with graduate students in human-computer interaction from the School of Informatics and Computing, are conducting formative field studies in a variety of clinical settings to identify key factors in sharing trusted advice among doctors and residents. They will then generate and iteratively evaluate novel designs for drug safety guidance that have the potential to elicit physician trust and maximize compliance.
The potential of this work is to generate a more complete understanding of what makes medical advice trustworthy, and how those principles can be extended to create a solid intellectual basis for the development of substantially better alerts in electronic medical record (EMR) systems.
The investigators will disseminate the project results through not only publications but real-world implementation and evaluation at Eskenazi Health System in Indianapolis. The team will also reach out to EMR vendors to promote the incorporation of their findings into current and next generation clinical systems.
Regenstrief Institute’s Drug Safety Informatics (DSI) Lab