Given the global prevalence of cardiovascular diseases, there is a The cardiovascular disease screening process detects abnormalities pressing need for easily accessible early screening methods. Typically, such as heart murmur, which is an irregular sound audible during this requires medical practitioners to investigate heart auscultations the heartbeat cycle through a stethoscope. Detection of a heart for irregular sounds, followed by echocardiography and electrocardiography murmur suggests underlying cardiac issues, prompting further evaluation tests. To democratize early diagnosis, we present a through echocardiography and electrocardiography tests user-friendly solution for abnormal heart sound detection, utilizing to pinpoint the specific heart disease. To enhance the accessibility mobile phones and a lightweight neural network optimized for of early diagnosis, we introduce a novel system for detecting abnormal on-device inference. Unlike previous approaches reliant on specialized heart sounds using mobile phones and an on-device neural stethoscopes, our method directly analyzes audio recordings, network. Our system does not require extra equipment, a server, facilitated by a novel architecture known as IConNet. IConNet, an or a specific data preprocessing pipeline, which is an advantage Interpretable Convolutional Neural Network, harnesses insights compared to existing works.

This paper introduces a novel convolutional neural networks (CNN) framework tailored for end-to-end audio deep learning models, presenting advancements in efficiency and explainability. By benchmarking experiments on three standard speech emotion recognition datasets with five-fold cross-validation, our framework outperforms Mel spectrogram features by up to seven percent. It can potentially replace the Mel-Frequency Cepstral Coefficients (MFCC) while remaining lightweight. Furthermore, we demonstrate the efficiency and interpretability of the front-end layer using the PhysioNet Heart Sound Database, illustrating its ability to handle and capture intricate long waveform patterns. Our contributions offer a portable solution for building efficient and interpretable models for raw waveform data.

The fairness of machine learning-based decisions has become an increasingly important focus in the design of supervised machine learning methods. Most fairness approaches optimize a specified trade-off between performance measure(s) (e.g., accuracy, log loss, or AUC) and fairness metric(s) (e.g., demographic parity, equalized odds). This begs the question: are the right performance-fairness trade-offs being specified? We instead re-cast fair machine learning as an imitation learning task by introducing superhuman fairness, which seeks to simultaneously outperform human decisions on multiple predictive performance and fairness measures. We demonstrate the benefits of this approach given suboptimal decisions.