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

2025-05-29

AI Summary

This study addresses the clinical need for smartphone-based lung sound diagnosis using built-in microphones, tackling distribution shifts arising from discrepancies between electronic stethoscope and smartphone audio characteristics, as well as inter-patient physiological variability. We propose Patient-Domain Supervised Contrastive Learning (PD-SCL), the first approach to explicitly model patient identity as a domain variable within a contrastive learning framework, enabling cross-device and cross-patient feature alignment. Integrated with the Audio Spectrogram Transformer (AST), our method employs mel-spectrograms as input and introduces a patient-label-guided supervised contrastive loss alongside domain-aware feature regularization. Evaluated on a real-world smartphone-recording dataset, the proposed method achieves a 2.4% absolute improvement in classification accuracy over the baseline AST model, demonstrating the feasibility and robustness of non-contact, portable pulmonary disease screening.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Search and Optimization: Learning to Search
• Natural Language Processing: Safety and Robustness

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Security and Privacy: Large-scale security measurements

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.

Problem

• Classify lung sounds using mobile phone recordings
• Address audio style differences between devices
• Reduce patient data variability for accurate diagnosis

Innovation

• Patient Domain Supervised Contrastive Learning method
• Integration with Audio Spectrogram Transformer model
• Smartphone microphone lung sound analysis