Unsupervised heart abnormality detection based on phonocardiogram analysis with Beta Variational Auto-Encoders

TL;DR

This paper introduces an unsupervised method for detecting heart abnormalities using phonocardiogram analysis with Beta Variational Auto-Encoders, achieving high accuracy without needing abnormal training samples.

Contribution

It proposes a novel unsupervised approach employing Beta Variational Auto-Encoders with a smaller beta value for effective heart abnormality detection from PCG signals.

Findings

Achieved an AUC of 0.91 in ROC tests for abnormal PCG detection.

Introducing a weighted KL divergence improves anomaly detection performance.

Reconstruction loss-based anomaly scores outperform latent vector-based scores.

Abstract

Heart Sound (also known as phonocardiogram (PCG)) analysis is a popular way that detects cardiovascular diseases (CVDs). Most PCG analysis uses supervised way, which demands both normal and abnormal samples. This paper proposes a method of unsupervised PCG analysis that uses beta variational auto-encoder ($\beta-\text{VAE}$) to model the normal PCG signals. The best performed model reaches an AUC (Area Under Curve) value of 0.91 in ROC (Receiver Operating Characteristic) test for PCG signals collected from the same source. Unlike majority of $\beta-\text{VAE}$s that are used as generative models, the best-performed $\beta-\text{VAE}$ has a $\beta$ value smaller than 1. Further experiments then find that the introduction of a light weighted KL divergence between distribution of latent space and normal distribution improves the performance of anomaly PCG detection based on anomaly scores resulted by reconstruction loss. The fact suggests that anomaly score based on reconstruction loss may be better than anomaly scores based on latent vectors of samples