Class Augmented Semi-Supervised Learning for Practical Clinical Analytics on Physiological Signals
This addresses practical class imbalance issues in clinical analytics using physiological signals, though it appears incremental as it builds on existing semi-supervised learning with augmentation techniques.
The paper tackles the class imbalance problem in physiological signal analysis for clinical anomaly detection by augmenting minority class examples to create a smooth decision boundary for semi-supervised learning. It demonstrates high performance on MIT-Physionet PCG and ECG datasets, outperforming state-of-the-art algorithms.
Computational analysis on physiological signals would provide immense impact for enabling automated clinical analytics. However, the class imbalance issue where negative or minority class instances are rare in number impairs the robustness of the practical solution. The key idea of our approach is intelligent augmentation of minority class examples to construct smooth, unbiased decision boundary for robust semi-supervised learning. This solves the practical class imbalance problem in anomaly detection task for computational clinical analytics using physiological signals. We choose two critical cardiac marker physiological signals: Heart sound or Phonocardiogram (PCG) and Electrocardiogram (ECG) to validate our claim of robust anomaly detection of clinical events under augmented class learning, where intelligent synthesis of minority class instances attempt to balance the class distribution. We perform extensive experiments on publicly available expert-labelled MIT-Physionet PCG and ECG datasets that establish high performance merit of the proposed scheme, and our scheme fittingly performs better than the state-of-the-art algorithms.