Google Research·· 2026-03-12
Exploring the feasibility of conversational diagnostic AI in a real-world clinical study
Exploring the feasibility of conversational diagnostic AI in a real-world clinical study
AI summary
Google Research and Beth Israel Deaconess Medical Center conducted a prospective, single-centre feasibility study in which AMIE held text consultations with patients before outpatient primary care visits, under live physician supervision by video.
Selection record
Threshold 60Official, first-handFirst 71Second 71
AdmittedSum of both 142 ≥ twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：对话式医疗AI临床可行性研究
- Why it was chosen
- Tests conversational diagnostic AI’s feasibility and safety in real outpatient workflows, with blinded comparisons against primary care physicians.
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: Google Research · research.google