# Learning from VAE Errors to support ECG-based Differential Diagnosis of Myocardial Scar

arXiv: https://arxiv.org/abs/2609.05294 · HTML: https://mlsanity.com/paper/2609.05294/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 1 of its 20 references that are in the map.
- First posted on arXiv 4 Sep 2026.

## Builds on (most cited first, 1 of 1)

- [Mitigating the reconstruction-detection trade-off in VAE-based unsupervised anomaly detection](https://mlsanity.com/paper/2605.02918/) (2026)

## Abstract (arXiv)

Late Gadolinium Enhancement (LGE) on cardiac magnetic resonance is a key marker of myocardial scar, but its limited accessibility motivates routine ECG-based screening. We evaluated whether β-variational autoencoder (VAE)-derived ECG representations can discriminate LGE+ from LGE- cardiomyopathic patients in a local cohort of 300 subjects. We compared 32-dimensional features from the foundation ECGx.AI model with those from a shallower β-VAE trained on normal PTB-XL ECGs, evaluating downstream classification and Dynamic Time Warping (DTW)-based reconstruction errors. ECGx.AI reached an area under ROC of 0.686 with Random Forest, while the proposed β-VAE reached 0.577 with sensitivity of 0.775 with Gradient Boosting. Notably, DTW-reconstruction errors significantly differed between classes in 10 out of 12 leads according to Mann-Whitney U test and help in classification, leading to an area under ROC of 0.643 with Logistic Regression, supporting their potential as markers of scar-related ECG alterations.