You’re reading the web edition of STAT’s AI Prognosis newsletter, our subscriber-exclusive guide to artificial intelligence in health care and medicine. Sign up to get it delivered in your inbox every Wednesday.
Last call: If you haven’t yet, fill out your 2025 health AI bingo card (and/or 2026 predictions) by tonight!
As a thank you, here’s a video of a sasquatch playing saxophone in the woods (this is not a rickroll) (but it’s honor system that you don’t click until after you’ve filled out the bingo card) (there’s no other way to find out if it’s a rickroll).
Two epidemiologists and the hunt for the missing transcripts
Katherine Goodman and Daniel Morgan, both epidemiologists at the University of Maryland, are interested in studying lapses in clinical decision-making — is there information that patients say or phrase in a way that isn’t “heard” by clinicians? Are there subtle differences in the way that patients phrase symptoms that would help doctors catch conditions and act on them earlier?
To do such research, you need a patient’s own words. This would have been difficult in the past, but with the advent of ambient AI scribes, it’s become much more routine to record patient visits.
This article is exclusive to STAT+ subscribers
Unlock this article — plus in-depth analysis, newsletters, premium events, and news alerts.
Already have an account? Log in
