Electronic health records hold vast amounts of patient data — so much that clinicians often struggle to distill what truly matters at the point of care.
One of the most promising aspects of AI is its ability to help make sense of that data and deliver quick insights so that physicians can act sooner and with greater confidence, said Jeremy Cauwels, chief medical officer at Sanford Health, during an interview last month at Reuters’ Total Health conference in Chicago.
He noted that his health system is embedding AI into its EHR to automate evidence-based care recommendations. For instance, Sanford has deployed a chronic kidney disease module that tracks when a patient moves from one stage of the disease to another and automatically prompts primary care physicians with the correct labs based on National Kidney Foundation guidelines.
Cauwels noted that this tool even helped his own 76-year-old father stay on the right monitoring schedule.
“Within the last year, he switched over from chronic kidney disease stage two to chronic kidney disease stage three because of his age,” Cauwels explained. “Even with healthcare in his family, I wouldn’t have thought about it to ask and make the switch. This reminded us of how to improve quality without actually requiring our brain power to get it done.”
The model has doubled the number of diabetes patients receiving recommended chronic kidney disease tests, as well as tripled the rate of early diagnoses. This allows for earlier intervention and can help reduce costly dialysis — which is significant for rural patients who live far from dialysis centers, Cauwels pointed out.
He also described a new AI-powered colon cancer screening tool that Sanford plans to embed in its EHR come January.
Because current gastroenterology guidelines classify patients only as “normal” or “high-risk,” Sanford built a model using 85 different variables to generate a personalized risk score for each patient.
This lets clinicians tailor their conversations and recommendations, which is especially important in the Upper Midwest, where colon cancer rates are among the country’s highest, Cauwels explained.
“It’s absolutely fixable if you screen appropriately for it and to catch it — but it’s happening in younger and younger people, and if you don’t catch it on time, it’s an extremely fatal or life-shortening cancer,” he stated.
By translating complex data into clear and timely guidance, AI can help physicians catch disease earlier and tailor treatment to the individual patient — which improves quality of care without adding cognitive burden, Cauwels said.
Photo: Volha Rahalskaya, Getty Images
