Kaiser AI system prevented 500 deaths

By Noah Schwartz for Becker’s Hospital Review

Oakland, Calif.-based Kaiser Permanente is using artificial intelligence to directly assist clinicians, such as a monitoring program that can predict deterioration risk, rather than just creating algorithms, the AMA reported Aug. 25.

The alert system identifies high-risk patients using EHR and clinical data. The tool has prevented 500 deaths, according to a study from Vincent Liu, a senior research scientist and regional medical director of augmented clinical intelligence at Kaiser.

Additionally, the tool has reduced high-risk readmissions by 10 percent.

“Over the past several years, we’ve used hundreds of millions of data points from our hospitalized patients and granular EHR data — things like lab values, vital signs, other key clinical data to develop a machine learning algorithm that worked with good accuracy to predict patients at risk for deterioration in the next 12 hours,” said Dr. Liu.