O'Sullivan LLM (cardiology)

A Large Language Model for Complex Cardiology Care

Paziente / Popolazione Intervento / Esposizione Confronto Esito

In 9 general cardiologists randomised to assess real-world complex cases of suspected genetic cardiomyopathy, including raw ECG, echocardiography, cardiac MRI and exercise-test data, assistance from AMIE, an LLM-based medical AI system improved blinded subspecialist-rated quality of triage, diagnosis and management compared with cardiologists working unassisted.

N
9
Disegno
RCT, cardiologists randomised, retrospective real-world case data, blinded subspecialist rating
Esito
Blinded subspecialist preference across a ten-domain rubric of triage, diagnosis and management quality
Rilevanza
2
RisultatoSubspecialists preferred AMIE-assisted assessments 46.7% vs 32.7% for cardiologists alone (P=0.02; 20.6% ties). Clinically significant errors 13.1% vs 24.3% (P=0.033); missing content 17.8% vs 37.4% (P=0.0021).
O'Sullivan JW, et al. Nat Med. 2026;32(2):616-623. 10.1038/s41591-025-04190-9
Discussione e critica

Extends the AMIE programme from simulated primary care (AMIE) into a subspecialty where expertise is scarce, with the LLM reading raw diagnostic data rather than text alone. Only nine cardiologists, retrospective cases from a single subspecialist practice, preference-based rubric scoring by three raters, and no patient outcomes — a signal for augmentation, not evidence of benefit.