A Robust Interpretable Deep Learning Classifier for Heart Anomaly Detection Without Segmentation

TL;DR

This paper proposes a robust, explainable deep learning classifier for abnormal heart sound detection that emphasizes the importance of segmentation, achieving near-perfect accuracy on a standard dataset.

Contribution

It introduces a novel classifier that integrates segmentation importance and model interpretability, advancing heart sound analysis without relying solely on segmentation.

Findings

Segmentation significantly improves classification accuracy.

The classifier achieves nearly 100% accuracy on PhysioNet dataset.

Model interpretation techniques reveal meaningful learned representations.

Abstract

Traditionally, abnormal heart sound classification is framed as a three-stage process. The first stage involves segmenting the phonocardiogram to detect fundamental heart sounds; after which features are extracted and classification is performed. Some researchers in the field argue the segmentation step is an unwanted computational burden, whereas others embrace it as a prior step to feature extraction. When comparing accuracies achieved by studies that have segmented heart sounds before analysis with those who have overlooked that step, the question of whether to segment heart sounds before feature extraction is still open. In this study, we explicitly examine the importance of heart sound segmentation as a prior step for heart sound classification, and then seek to apply the obtained insights to propose a robust classifier for abnormal heart sound detection. Furthermore, recognizing the pressing need for explainable Artificial Intelligence (AI) models in the medical domain, we also unveil hidden representations learned by the classifier using model interpretation techniques. Experimental results demonstrate that the segmentation plays an essential role in abnormal heart sound classification. Our new classifier is also shown to be robust, stable and most importantly, explainable, with an accuracy of almost 100% on the widely used PhysioNet dataset.