Artificial Intelligence for Direct-to-Physician Reporting of Ambulatory Electrocardiography

Johnson, L. S.

doi:10.1038/s41591-025-03516-x

DeepRhythmAI

Artificial Intelligence for Direct-to-Physician Reporting of Ambulatory Electrocardiography

Patient / Population Intervention / Exposure Comparison Outcome

In 14,606 ambulatory ECG recordings annotated beat by beat, AI interpretation reported directly to the physician improved sensitivity for critical arrhythmias against cardiologist consensus panels compared with certified ECG technicians.

N

14,606patients

Design

Non-randomised diagnostic-accuracy comparison against 17 cardiologist consensus panels

Endpoint

Sensitivity for critical arrhythmias versus cardiologist consensus-panel annotation

Relevance

3Supporting — context rather than must-know.

ResultSensitivity for critical arrhythmias 98.6% (95% CI 97.7–99.4) vs 80.3% (95% CI 77.3–83.3) for 167 technicians; false negatives 3.2 vs 44.3 per 1,000 patients (relative risk of a missed diagnosis 14.1 for technicians, 95% CI 10.4–19.0); false positives 12 vs 5 per 1,000 patient-days.

Johnson LS, et al. Nat Med. 2025;31(3):925-931. 10.1038/s41591-025-03516-x

Discussion & critique

The largest head-to-head of AI against human technicians for ambulatory ECG, supporting AI-first reporting with physician review. It is an accuracy study, not an outcome trial: the reference standard was a cardiologist-adjudicated random sample of 5,235 events rather than every recording, the comparison was not randomised, and the price of the very high sensitivity was a higher false-positive burden that physicians must absorb.