JAMA+ AI Conversations Stumbling Toward AI in the Clinic
7 snips
Feb 12, 2026 A lively debate about studies on AI in clinical care and when machine learning can be helpful. A study on patient portal message delays raises questions about disparities and confounding. A comparison of EHR-based algorithms with in-person screening for youth suicide risk highlights limits of automated screening. A call to teach clinicians deeper critical thinking beyond pattern matching rounds out the conversation.
AI Snips
Chapters
Transcript
Episode notes
Portal Messaging Reveals Access Gaps
- Patient portal messaging shows measurable disparities by race, language, and insurance status in response timeliness.
- Large-scale digital data can reveal system inequities that deserve targeted investigation and remediation.
Continuously Monitor Portal Equity
- Actively monitor digital health tools to ensure equitable use as AI-assisted triage and messaging scale.
- Refine portal design and measure responses across subgroups to prevent reinforcement of existing gaps.
EHR Models Improve Risk Detection
- Machine learning on EHRs can detect more youths who later attempt suicide compared with standard screening.
- These models flag higher-risk groups but still struggle to pinpoint exactly who will attempt, like weather predicting storms not lightning.