Patient Domain Supervised Contrastive Learning for Lung Sound Classification Using Mobile Phone

TL;DR

This work tackles cross-device and patient variability in lung sound classification to enable smartphone-based auscultation. It introduces Patient Domain Supervised Contrastive Learning (PD-SCL), integrated with the Audio Spectrogram Transformer (AST), and augments it with Domain Adversarial Training to reduce distribution shifts between devices. PD-SCL reduces instrument- and patient-specific variability, achieving superior performance when mobile and stethoscope data are combined (notably Sc = 86.3). The results support the feasibility of mobile-phone–based lung disease detection and offer a practical path toward tele-auscultation in the post-COVID-19 era.

Abstract

Auscultation is crucial for diagnosing lung diseases. The COVID-19 pandemic has revealed the limitations of traditional, in-person lung sound assessments. To overcome these issues, advancements in digital stethoscopes and artificial intelligence (AI) have led to the development of new diagnostic methods. In this context, our study aims to use smartphone microphones to record and analyze lung sounds. We faced two major challenges: the difference in audio style between electronic stethoscopes and smartphone microphones, and the variability among patients. To address these challenges, we developed a method called Patient Domain Supervised Contrastive Learning (PD-SCL). By integrating this method with the Audio Spectrogram Transformer (AST) model, we significantly improved its performance by 2.4\% compared to the original AST model. This progress demonstrates that smartphones can effectively diagnose lung sounds, addressing inconsistencies in patient data and showing potential for broad use beyond traditional clinical settings. Our research contributes to making lung disease detection more accessible in the post-COVID-19 world.

Figures (1)

• Figure 1: ROC Curve and AUC for each model