Unsupervised Heart Abnormality Detection Based On Phonocardiogram Analysis With Beta Variational Auto-Encoders

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 paperproposes a method of unsupervised PCG analysis that usesbeta variational auto-encoder (β−VAE) to model the normalPCG signals. The best performed model reaches an AUC (Area Under Curve) value of 0.91 in ROC (Receiver Oper-ating Characteristic) test for PCG signals collected from thesame source. Unlike majority of β−VAEs that are usedas generative models, the best-performed β−VAE has a β value smaller than 1. This fact demonstrates that the re-sampling process helps the improvements on anomaly PCGdetection through reconstruction loss worth a heavier weight. Further investigations suggest that anomaly score based on reconstruction loss may be better than anomaly scores based on latent vectors of samples in PCG analysis based on VAE systems.