AMA Update
Podcast Recap | AMA Update: How does AI help in health care? AI success stories: Cancer risk detection and ambient listening AI
In this AMA Update podcast, Dr. Jeremy Cauwels, Chief Medical Officer at Sanford Health, discusses two impactful applications of AI in clinical practice: predictive modeling for colon cancer risk and ambient AI for clinical documentation. These innovations are improving patient outcomes and streamlining workflows, particularly in rural health settings where resources are limited.
Length: 11 min.
Key takeaways
- Predictive AI models identify patients who are 5 to 6 times more likely to develop colon cancer, enabling earlier and more targeted screening.
- Targeted screening in high-risk regions is critical in areas like the Upper Midwest, where colorectal cancer rates are high and gastroenterology resources are limited. Sanford Health’s data analytics team uses 85 variables from electronic medical records to stratify patient risk, enabling more efficient screening without replacing physician judgment.
- Ambient AI tools capture and summarize physician-patient conversations in real time, significantly reducing the time clinicians spend on documentation. The response to these tools has been resoundingly positive—one doctor shared, "I haven't been home in time to do something between my office and dinner and doing charting at night for years, and I got home the other day at 5 o'clock."
- Workflow automation improves operational efficiency by streamlining repetitive administrative tasks and integrating AI-generated outputs directly into clinical systems. This allows physicians to spend more time on direct patient care, reduces burnout, and enhances the overall care experience for both providers and patients.
Source:
Unger, T. [Host] (2025, June 16). AMA Update. How does AI help in health care? AI success stories: Cancer risk detection and ambient listening AI [Podcast]. https://www.ama-assn.org/practice-management/digital-health/how-does-ai-help-health-care-ai-success-stories-cancer-risk