Sound-Dr: Reliable Sound Dataset and Baseline Artificial Intelligence System for Respiratory Illnesses

TL;DR

Sound-Dr introduces a reliable, high-quality dataset of human respiratory sounds and a baseline AI system, enhancing diagnosis of respiratory illnesses like pneumonia and COVID-19 with improved robustness and real-time mobile application potential.

Contribution

The paper presents a new comprehensive respiratory sound dataset and a baseline AI system, outperforming existing datasets in robustness and feature richness for diagnosing respiratory diseases.

Findings

Sound-Dr dataset has richer features than existing datasets.

The system demonstrates better performance and robustness across datasets.

It is suitable for real-time mobile health applications.

Abstract

As the burden of respiratory diseases continues to fall on society worldwide, this paper proposes a high-quality and reliable dataset of human sounds for studying respiratory illnesses, including pneumonia and COVID-19. It consists of coughing, mouth breathing, and nose breathing sounds together with metadata on related clinical characteristics. We also develop a proof-of-concept system for establishing baselines and benchmarking against multiple datasets, such as Coswara and COUGHVID. Our comprehensive experiments show that the Sound-Dr dataset has richer features, better performance, and is more robust to dataset shifts in various machine learning tasks. It is promising for a wide range of real-time applications on mobile devices. The proposed dataset and system will serve as practical tools to support healthcare professionals in diagnosing respiratory disorders. The dataset and code are publicly available here: https://github.com/ReML-AI/Sound-Dr/.