SCH: EXP: From Critique to Collaboration: A Fundamental Rethinking of Computerized Clinical Alerts

Indiana University, Bloomington IN

Investigators

Abstract

To prescribe safe medications, physicians use computerized physician order entry (CPOE) that routinely relies on drug-drug interaction (DDI) alerts. Despite the current attempts to reduce frequency and complexity of alerts, the effectiveness of such alerts remains extremely low, with up to 96% of warnings being ignored by physicians on a daily basis. The primary cause for this is alert fatigue, a state in which physicians, bombarded by numerous warnings, become desensitized. The goal of this project is to transform drug safety alerts from oft-ignored warnings to trusted tools that advise physicians in daily decision making. To accomplish this, the investigators are aiming beyond incremental improvement establishing novel principles for alert design that are based on what physicians consider important when taking advice from peers in their daily clinical work. The project is addressing this problem with a three prong approach: (1) determining principles that accompany trusted physician-to-physician advice regarding appropriate medication prescribing; formative studies will be conducted in a variety of clinical settings to identify key factors in sharing trusted advice among doctors and residents; (2) generating novel designs for drug safety guidance that elicit physician trust and maximize compliance and (3) evaluating the impact of novel designs on physician compliance to DDI warnings. Intellectual Merit: By investigating the question of why physicians trust each other, the project is leveraging a fundamental behavioral dynamics reconsidering the role of clinical alerts, and thus generating new principles to design effective computerized guidance that elicits similar notions of trust. A very important contribution of this research is a more complete understanding of what makes physician-to-physician advice trustworthy in the ecosystem of daily clinical activities provides a solid, long-term intellectual basis for the creation of substantially better alerts for a broad variety of CPOE systems. Key innovative aspect of this work is the departure from the mere optimization of alerts to focus rather on complex yet crucial dynamics by which trusted advice is shared among physicians. There are potentially transformative aspects of the proposed work, which if successful, could unleash a new generation of drug-drug interaction warnings that will substantially advance the level of adherence in daily medication prescribing. Broader Impacts: The outcomes from this project will potentially affect the over 600,000 physicians in the United States who spend the majority of their time in direct patient care, and who are exposed to dozens of DDI alerts on a daily basis. By reframing current alerting strategies, the project results are expected to substantially increase safe drug prescription in day-to-day clinical setting. The investigators are disseminating the project results through large-scale real-world CPOE deployments and live experimental evaluations available to hundreds of physicians. The team is also reaching out to CPOE vendors, to promote the incorporation of the ideas generated in the project in the current and next generation of products. Ultimately, this basic research in physician communication and human-computer interaction is providing the research basis to catalyze a change in industry practice, also facilitated by the PI's leadership of the EMR Innovations Summit, an annual meeting of national EMR vendors hosted by the Regenstrief Institute.