Detecting abnormal heart sound using mobile phones and on-device IConNet
This work addresses the need for accessible early diagnosis of cardiovascular diseases, particularly for remote health monitoring, but it is incremental as it builds on existing neural network methods with a focus on on-device optimization and interpretability.
The paper tackles the problem of early screening for cardiovascular diseases by developing a mobile phone-based system for detecting abnormal heart sounds, using a lightweight neural network called IConNet that analyzes audio recordings directly, achieving on-device inference without specialized stethoscopes.
Given the global prevalence of cardiovascular diseases, there is a pressing need for easily accessible early screening methods. Typically, this requires medical practitioners to investigate heart auscultations for irregular sounds, followed by echocardiography and electrocardiography tests. To democratize early diagnosis, we present a user-friendly solution for abnormal heart sound detection, utilizing mobile phones and a lightweight neural network optimized for on-device inference. Unlike previous approaches reliant on specialized stethoscopes, our method directly analyzes audio recordings, facilitated by a novel architecture known as IConNet. IConNet, an Interpretable Convolutional Neural Network, harnesses insights from audio signal processing, enhancing efficiency and providing transparency in neural pattern extraction from raw waveform signals. This is a significant step towards trustworthy AI in healthcare, aiding in remote health monitoring efforts.