Advance Prediction of Ventricular Tachyarrhythmias using Patient Metadata and Multi-Task Networks
This addresses a critical healthcare problem for patients at risk of cardiac arrhythmias, though it appears incremental with specific architectural improvements.
The paper tackled predicting ventricular tachyarrhythmias by developing a neural network that incorporates patient metadata and multi-task learning, achieving 74.02% accuracy and 77.22% specificity 60 seconds before episodes.
We describe a novel neural network architecture for the prediction of ventricular tachyarrhythmias. The model receives input features that capture the change in RR intervals and ectopic beats, along with features based on heart rate variability and frequency analysis. Patient age is also included as a trainable embedding, while the whole network is optimized with multi-task objectives. Each of these modifications provides a consistent improvement to the model performance, achieving 74.02% prediction accuracy and 77.22% specificity 60 seconds in advance of the episode.