Joint optimization of a $β$-VAE for ECG task-specific feature extraction
This work addresses the need for better explainable AI in ECG analysis for diagnosing and monitoring cardiac conditions, representing an incremental improvement over existing methods.
The researchers tackled the problem of extracting explainable features from electrocardiograms (ECGs) for cardiac function prediction by jointly optimizing a β-VAE for reconstruction and prediction, resulting in significantly improved prediction and explainability compared to a vanilla β-VAE while maintaining similar reconstruction performance on data from 7255 patients.
Electrocardiography is the most common method to investigate the condition of the heart through the observation of cardiac rhythm and electrical activity, for both diagnosis and monitoring purposes. Analysis of electrocardiograms (ECGs) is commonly performed through the investigation of specific patterns, which are visually recognizable by trained physicians and are known to reflect cardiac (dis)function. In this work we study the use of $β$-variational autoencoders (VAEs) as an explainable feature extractor, and improve on its predictive capacities by jointly optimizing signal reconstruction and cardiac function prediction. The extracted features are then used for cardiac function prediction using logistic regression. The method is trained and tested on data from 7255 patients, who were treated for acute coronary syndrome at the Leiden University Medical Center between 2010 and 2021. The results show that our method significantly improved prediction and explainability compared to a vanilla $β$-VAE, while still yielding similar reconstruction performance.