Geriatrician warns doctors to scrutinize AI tools for older patients
James Deardorff of the University of California San Francisco argues that artificial intelligence models used in geriatrics require careful review by clinicians.
Algorithm performance varies by group
Doctors increasingly use AI models to predict risks like sepsis and falls for patients. These predictions are often embedded directly into electronic health records where their accuracy can be taken for granted. James Deardorff developed several models specifically aiming to make predictions for older adults regarding mortality and nursing home care needs.
Context matters for high stakes
Deardorff wrote a commentary on a large analysis of Epic's proprietary end-of-life prediction model published in JAMA Network Open. He noted that using a one-year mortality prediction to start a conversation about care goals has few downsides. However, using the same data to inform decisions like transplant priority could have profound impacts.
Reported by one outlet
Only one outlet has published this. Nothing here has been checked against a second report, so read it as that outlet's account and follow the link below for the original.
Reported by
1 independent outlet. Headline as published. Links open the original report.