It was a win-win. Hospitals needed to prevent patient deaths from sepsis, a complication of infection; and Epic, the nation’s largest seller of medical records, needed users for its new product — an algorithm that could predict which patients would develop the condition so doctors could intervene earlier.
Over the last few years, hundreds of hospitals have plugged in the algorithm without verifying its advertised 80% accuracy rate. Then a group of researchers at the University of Michigan started asking questions about its performance.
Their findings, published Monday in JAMA Internal Medicine, underscore the perils of allowing algorithms to run unchecked in U.S. health care: Epic’s sepsis predictor missed two-thirds of cases in the University of Michigan’s hospital system; its overall accuracy was about 63%, which is little better than a coin flip; and its high rate of false alarms meant clinicians would have to respond to 109 alerts to find a single patient with sepsis.
About the Author Reprints
To submit a correction request, please visit our Contact Us page.
STAT encourages you to share your voice. We welcome your commentary, criticism, and expertise on our subscriber-only platform, STAT+ Connect