Deep Attention-based Representation Learning for Heart Sound Classification

TL;DR

This paper introduces a deep learning approach with attention mechanisms for automatic classification of heart sounds, aiming to improve diagnosis support for cardiovascular diseases using recorded data.

Contribution

It proposes a novel deep representation learning method with attention for heart sound classification, reducing reliance on handcrafted features and enhancing performance.

Findings

Achieved 51.2% unweighted average recall on the HSS dataset.

Effectively classified normal, mild, and severe heart sounds.

Validated the approach with real clinical data.

Abstract

Cardiovascular diseases are the leading cause of deaths and severely threaten human health in daily life. On the one hand, there have been dramatically increasing demands from both the clinical practice and the smart home application for monitoring the heart status of subjects suffering from chronic cardiovascular diseases. On the other hand, experienced physicians who can perform an efficient auscultation are still lacking in terms of number. Automatic heart sound classification leveraging the power of advanced signal processing and machine learning technologies has shown encouraging results. Nevertheless, human hand-crafted features are expensive and time-consuming. To this end, we propose a novel deep representation learning method with an attention mechanism for heart sound classification. In this paradigm, high-level representations are learnt automatically from the recorded heart sound data. Particularly, a global attention pooling layer improves the performance of the learnt representations by estimating the contribution of each unit in feature maps. The Heart Sounds Shenzhen (HSS) corpus (170 subjects involved) is used to validate the proposed method. Experimental results validate that, our approach can achieve an unweighted average recall of 51.2% for classifying three categories of heart sounds, i. e., normal, mild, and moderate/severe annotated by cardiologists with the help of Echocardiography.