vix.ing · top · new · best · stats · spec

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

2025/05/28 by Seung Gyu Jeong, Jeong, Seung Gyu, Seong Eun Kim +1 · 1 citation
Computer Science · Medicine · Nursing · #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Music and Audio Processing #Nursing Diagnosis and Documentation #Phonocardiography and Auscultation Techniques #Sound (cs.SD) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2505.23834

openalex publication_date 2025/05/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

Cited by

Related