EchoNet-Dynamic: Video-Based Deep Learning Outperforms Experts in Cardiac Function Assessment
EchoNet-Dynamic, a deep learning algorithm trained on over 10,000 echocardiogram videos, achieved a mean absolute error of 4.1% for ejection fraction prediction and an AUC of 0.97 for classifying heart failure with reduced ejection fraction. In prospective evaluation, the model demonstrated reproducibility comparable to or better than human experts. By leveraging information across multiple cardiac cycles rather than sampling individual frames, the system enables more precise and consistent cardiac function assessment.
The original study
Video-based AI for beat-to-beat assessment of cardiac function.
- Authors
- Ouyang D, He B, Ghorbani A, Yuan N, Ebinger J, Langlotz CP, et al.
- Journal
- Nature
- Type
- Journal Article, Research Support, N.I.H., Extramural, Research Support, Non-U.S. Gov't, Research Support, U.S. Gov't, Non-P.H.S., Validation Study
- PMID
- 32269341
Original abstract
Accurate assessment of cardiac function is crucial for the diagnosis of cardiovascular disease1, screening for cardiotoxicity2 and decisions regarding the clinical management of patients with a critical illness3. However, human assessment of cardiac function focuses on a limited sampling of cardiac cycles and has considerable inter-observer variability despite years of training4,5. Here, to overcome this challenge, we present a video-based deep learning algorithm-EchoNet-Dynamic-that surpasses the performance of human experts in the critical tasks of segmenting the left ventricle, estimating ejection fraction and assessing cardiomyopathy. Trained on echocardiogram videos, our model accurately segments the left ventricle with a Dice similarity coefficient of 0.92, predicts ejection fraction with a mean absolute error of 4.1% and reliably classifies heart failure with reduced ejection fraction (area under the curve of 0.97). In an external dataset from another healthcare system, EchoNet-Dynamic predicts the ejection fraction with a mean absolute error of 6.0% and classifies heart failure with reduced ejection fraction with an area under the curve of 0.96. Prospective evaluation with repeated human measurements confirms that the model has variance that is comparable to or less than that of human experts. By leveraging information across multiple cardiac cycles, our model can rapidly identify subtle changes in ejection fraction, is more reproducible than human evaluation and lays the foundation for precise diagnosis of cardiovascular disease in real time. As a resource to promote further innovation, we also make publicly available a large dataset of 10,030 annotated echocardiogram videos.