Epic’s machine learning model scans health records and alerts doctors automatically before patients need an ICU admission or other care intervention
One of the most challenging things about COVID-19 for healthcare providers is how quickly some cases of the disease become life-threatening. A predictive model from Epic is helping doctors intervene with life-saving care before hospitalized patients deteriorate.
“This is helping save lives. The model predicts which patients are getting worse and will need more care. It shows us if things are changing rapidly,” said Dr. Daniel David, Clinical Professor of Medicine at Confluence Health, an integrated healthcare organization serving North Central Washington.
Hundreds of hospitals are using the predictive model. It evaluates patients’ risk of getting sicker in real time by tracking thousands of pieces of data generated by heart rate, blood pressure, temperature, and other monitors. The model helps clinicians by rapidly analyzing data from these sources and notifying staff if things are getting worse. Notifications are displayed on screen, included in reporting dashboards, or pushed out to clinicians’ smartphones.
“Frontline healthcare workers are busy caring for patients. By keeping a watchful eye, the system helps clinicians direct their attention to patients who need it most,” said Seth Hain, Epic data scientist and Senior Vice President of Research and Development.