Variational Autoencoders for Anomaly Detection in Respiratory Sounds
This work addresses the need for an accessible tool to alert patients about respiratory diseases, though it appears incremental as it matches rather than surpasses existing approaches.
The paper tackled the problem of detecting respiratory diseases from sounds using a weakly-supervised approach based on Variational Autoencoders, achieving an accuracy of 57%, which matches existing strongly-supervised methods.
This paper proposes a weakly-supervised machine learning-based approach aiming at a tool to alert patients about possible respiratory diseases. Various types of pathologies may affect the respiratory system, potentially leading to severe diseases and, in certain cases, death. In general, effective prevention practices are considered as major actors towards the improvement of the patient's health condition. The proposed method strives to realize an easily accessible tool for the automatic diagnosis of respiratory diseases. Specifically, the method leverages Variational Autoencoder architectures permitting the usage of training pipelines of limited complexity and relatively small-sized datasets. Importantly, it offers an accuracy of 57 %, which is in line with the existing strongly-supervised approaches.