Generalization Studies of Neural Network Models for Cardiac Disease Detection Using Limited Channel ECG

TL;DR

This paper investigates how neural networks can better generalize in detecting various cardiac conditions from limited ECG data, emphasizing the role of unsupervised learning to improve accuracy and robustness.

Contribution

It introduces an unsupervised learning approach to enhance neural network generalization for cardiac disease detection from limited ECG channels, outperforming existing methods.

Findings

Significant improvements in F1-scores over state-of-the-art models.

Unsupervised learning constructs effective latent spaces for better generalization.

Enhanced detection accuracy across unseen cardiac conditions.

Abstract

Acceleration of machine learning research in healthcare is challenged by lack of large annotated and balanced datasets. Furthermore, dealing with measurement inaccuracies and exploiting unsupervised data are considered to be central to improving existing solutions. In particular, a primary objective in predictive modeling is to generalize well to both unseen variations within the observed classes, and unseen classes. In this work, we consider such a challenging problem in machine learning driven diagnosis: detecting a gamut of cardiovascular conditions (e.g. infarction, dysrhythmia etc.) from limited channel ECG measurements. Though deep neural networks have achieved unprecedented success in predictive modeling, they rely solely on discriminative models that can generalize poorly to unseen classes. We argue that unsupervised learning can be utilized to construct effective latent spaces that facilitate better generalization. This work extensively compares the generalization of our proposed approach against a state-of-the-art deep learning solution. Our results show significant improvements in F1-scores.