Artificial intelligence is helping improve collaboration between physicians and nurses at Palo Alto, Calif.-based Stanford Health Care.
Stanford Hospital has been using an AI model to predict when patients are at risk of deterioration — scanning vital sign, lab and EHR data about every 15 minutes — then alerting the clinical team, according to a March study in JAMA Internal Medicine. It has been fostering communication among clinicians beyond just end-of-shift handoffs.
"The big question I want to answer is, 'How do we use AI to build a more resilient health system in high-stakes situations?'" said senior study author Ron Li, MD, Stanford's medical informatics director for digital health, in an April 15 news release. "There are many ways to do that, but one core characteristic for a resilient system is strong communication channels. This model is powered by AI, but the action it triggers, the intervention, is basically a conversation that otherwise may not have happened."
After rolling out the tool, the hospital experienced a 10.4% decline in deterioration events — transfers to the intensive care unit, rapid response team incidents, and codes — among 963 patients who were on the cusp of being considered high risk, the study found. Dr. Li said he hopes to improve the accuracy of the technology and thus reduce alert fatigue among providers.