A deep neural network to enhance prediction of 1-year mortality using echocardiographic videos of the heart
This addresses mortality prediction for patients using a novel application of deep learning to echocardiographic data, representing a first attempt in this domain.
The study tackled predicting 1-year mortality using echocardiographic videos, achieving an AUC of 0.839 with videos alone and 0.858 when combined with EHR data, and outperforming expert cardiologists.
Predicting future clinical events helps physicians guide appropriate intervention. Machine learning has tremendous promise to assist physicians with predictions based on the discovery of complex patterns from historical data, such as large, longitudinal electronic health records (EHR). This study is a first attempt to demonstrate such capabilities using raw echocardiographic videos of the heart. We show that a large dataset of 723,754 clinically-acquired echocardiographic videos (~45 million images) linked to longitudinal follow-up data in 27,028 patients can be used to train a deep neural network to predict 1-year mortality with good accuracy (area under the curve (AUC) in an independent test set = 0.839). Prediction accuracy was further improved by adding EHR data (AUC = 0.858). Finally, we demonstrate that the trained neural network was more accurate in mortality prediction than two expert cardiologists. These results highlight the potential of neural networks to add new power to clinical predictions.