Riemannian Prediction of Anatomical Diagnoses in Congenital Heart Disease based on 12-lead ECGs
This work addresses the problem of rare disease diagnosis for patients with congenital heart disease, representing an incremental advancement in ECG-based classification.
The paper tackled the challenge of accurately classifying congenital heart disease from 12-lead ECG signals despite limited datasets, achieving significant improvement over traditional machine learning and deep learning methods.
Congenital heart disease (CHD) is a relatively rare disease that affects patients at birth and results in extremely heterogeneous anatomical and functional defects. 12-lead ECG signal is routinely collected in CHD patients because it provides significant biomarkers for disease prognosis. However, developing accurate machine learning models is challenging due to the lack of large available datasets. Here, we suggest exploiting the Riemannian geometry of the spatial covariance structure of the ECG signal to improve classification. Firstly, we use covariance augmentation to mix samples across the Riemannian geodesic between corresponding classes. Secondly, we suggest to project the covariance matrices to their respective class Riemannian mean to enhance the quality of feature extraction via tangent space projection. We perform several ablation experiments and demonstrate significant improvement compared to traditional machine learning models and deep learning on ECG time series data.