# Comparison of Autoencoder Encodings for ECG Representation in Downstream Prediction Tasks

arXiv: https://arxiv.org/abs/2410.02937 · HTML: https://mlsanity.com/paper/2410.02937/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 20 references that are in the map.
- First posted on arXiv 3 Oct 2024.

## Builds on (most cited first, 3 of 3)

- [Variational Dropout and the Local Reparameterization Trick](https://mlsanity.com/paper/1506.02557/) (2015)
- [Symbolic Discovery of Optimization Algorithms](https://mlsanity.com/paper/2302.06675/) (2023)
- [Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing](https://mlsanity.com/paper/1903.10145/) (2019)

## Built on by (most cited first, 2 of 2)

- [Unsupervised Time-Series Signal Analysis with Autoencoders and Vision Transformers: A Review of Architectures and Applications](https://mlsanity.com/paper/2504.16972/) (2025)
- [Predicting Fetal Outcomes from Cardiotocography Signals Using a Supervised Variational Autoencoder](https://mlsanity.com/paper/2509.06540/) (2025)

## Abstract (arXiv)

The electrocardiogram (ECG) is an inexpensive and widely available tool for cardiovascular assessment. Despite its standardized format and small file size, the high complexity and inter-individual variability of ECG signals (typically a 60,000-size vector) make it challenging to use in deep learning models, especially when only small datasets are available. This study addresses these challenges by exploring feature generation methods from representative beat ECGs, focusing on Principal Component Analysis (PCA) and Autoencoders to reduce data complexity. We introduce three novel Variational Autoencoder (VAE) variants: Stochastic Autoencoder (SAE), Annealed beta-VAE (Abeta-VAE), and cyclical beta-VAE (Cbeta-VAE), and compare their effectiveness in maintaining signal fidelity and enhancing downstream prediction tasks. The Abeta-VAE achieved superior signal reconstruction, reducing the mean absolute error (MAE) to 15.7 plus-minus 3.2 microvolts, which is at the level of signal noise. Moreover, the SAE encodings, when combined with ECG summary features, improved the prediction of reduced Left Ventricular Ejection Fraction (LVEF), achieving an area under the receiver operating characteristic curve (AUROC) of 0.901. This performance nearly matches the 0.910 AUROC of state-of-the-art CNN models but requires significantly less data and computational resources. Our findings demonstrate that these VAE encodings are not only effective in simplifying ECG data but also provide a practical solution for applying deep learning in contexts with limited-scale labeled training data.