Patient-Aware Feature Alignment for Robust Lung Sound Classification:Cohesion-Separation and Global Alignment Losses

TL;DR

This paper introduces PAFA, a novel framework with two loss functions that improve lung sound classification by capturing patient-specific features and reducing variability, leading to better diagnostic accuracy.

Contribution

The paper presents a new Patient-Aware Feature Alignment framework with two innovative loss functions for robust, patient-specific lung sound classification.

Findings

Achieved 64.84% four-class classification accuracy on ICBHI dataset.

Achieved 72.08% two-class classification accuracy on ICBHI dataset.

Demonstrated improved performance in patient-specific clustering and classification.

Abstract

Lung sound classification is vital for early diagnosis of respiratory diseases. However, biomedical signals often exhibit inter-patient variability even among patients with the same symptoms, requiring a learning approach that considers individual differences. We propose a Patient-Aware Feature Alignment (PAFA) framework with two novel losses, Patient Cohesion-Separation Loss (PCSL) and Global Patient Alignment Loss (GPAL). PCSL clusters features of the same patient while separating those from other patients to capture patient variability, whereas GPAL draws each patient's centroid toward a global center, preventing feature space fragmentation. Our method achieves outstanding results on the ICBHI dataset with a score of 64.84\% for four-class and 72.08\% for two-class classification. These findings highlight PAFA's ability to capture individualized patterns and demonstrate performance gains in distinct patient clusters, offering broader applications for patient-centered healthcare.