EchoNet-RCT
2023
Blinded, Randomized Trial of Sonographer versus AI Cardiac Function Assessment
In 3,495 echocardiograms undergoing quantification of cardiac function, initial AI assessment of left ventricular ejection fraction was non-inferior to initial sonographer assessment for the proportion of readings the cardiologist substantially changed, and superior.
Result
- Absolute difference
- 10.4 points
- NNT
- 10
difference-10.495% CI -13.2 to -7.7 · P < 0.001
Absolute difference and NNT are derived from the event rates.
Also reported: For non-inferiority and for superiority). Mean absolute difference from a prior independent cardiologist 6.29% vs 7.23% (difference −0.96%, 95% CI −1.34% to −0.54%); blinding index 0.088.
- Subtopic
- Echocardiography
- Design
- Blinded, randomised non-inferiority trial
- Relevance
- Practice-defining: a trial the field needs to know.
- Source
- He B, et al. Nature. 2023;616(7957):520-524.doi 10.1038/s41586-023-05947-3
Discussion & critique
The first blinded randomised trial of AI in cardiac imaging: cardiologists edited AI-initiated LVEF less often than sonographer-initiated values, with time saved for both, establishing the design template for AI-versus-human reader trials. The endpoint is cardiologist editing rather than patient outcome, 274 poor-quality studies were excluded before randomisation, and a cardiologist still finalised every report, so the trial tested AI-assisted workflow rather than autonomous AI.