Heart failure & cardiomyopathies
Echocardiogram Vector Embeddings Via R3D Transformer for the Advancement of Automated Echocardiography
Authors' conclusion
We present 10,030 vector embeddings learned by this model as a resource to the cardiology research community, as well as the trained model itself.
Study context
- Population
- Echocardiograms of the EchoNet dataset
- Participants
- 10,030 echocardiograms
- Outcome
- Classification of EF below or above 50% (test set)
Main finding
As reported in the abstract
| Group | AUC | Accuracy |
|---|---|---|
| R3D model | 0.916 | 87.5% |
R3D model
AUC0.916
Accuracy87.5%
- 400-dimensional vector embeddings extracted for each echocardiogram
- 10,030
Original publication
Echocardiogram Vector Embeddings Via R3D Transformer for the Advancement of Automated Echocardiography. JACC Adv. Published 25 September 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →