A XAI-based Framework for Frequency Subband Characterization of Cough Spectrograms in Chronic Respiratory Disease

2025-08-22

AI Summary

This study addresses the limited interpretability of cough acoustic biomarkers in diagnosing chronic respiratory diseases—particularly chronic obstructive pulmonary disease (COPD). We propose an explainable artificial intelligence (XAI)-driven, band-aware analytical framework. Methodologically, we design a time-frequency spectrogram–based convolutional neural network (CNN), integrate occlusion sensitivity analysis to localize diagnostically critical regions, and adaptively partition the spectrum into five sub-bands to model complementary and compensatory spectral features. Our key contribution is the first application of XAI-guided spectral band decomposition to cough acoustics, uncovering cross-band pathophysiological associations. Experiments demonstrate significant improvement in differentiating COPD from asthma, bronchitis, and non-chronic cough (AUC = 0.92) and identify clinically meaningful, interpretable acoustic biomarkers. This work establishes a novel paradigm for non-invasive, interpretable intelligent diagnosis of respiratory diseases.

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Computer Vision: Interpretability, Explainability, and Transparency
• Machine Learning: Transparent, Interpretable, Explainable ML

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Responsible Web: Algorithmic accountability and transparency on the web
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

This paper presents an explainable artificial intelligence (XAI)-based framework for the spectral analysis of cough sounds associated with chronic respiratory diseases, with a particular focus on Chronic Obstructive Pulmonary Disease (COPD). A Convolutional Neural Network (CNN) is trained on time-frequency representations of cough signals, and occlusion maps are used to identify diagnostically relevant regions within the spectrograms. These highlighted areas are subsequently decomposed into five frequency subbands, enabling targeted spectral feature extraction and analysis. The results reveal that spectral patterns differ across subbands and disease groups, uncovering complementary and compensatory trends across the frequency spectrum. Noteworthy, the approach distinguishes COPD from other respiratory conditions, and chronic from non-chronic patient groups, based on interpretable spectral markers. These findings provide insight into the underlying pathophysiological characteristics of cough acoustics and demonstrate the value of frequency-resolved, XAI-enhanced analysis for biomedical signal interpretation and translational respiratory disease diagnostics.

Problem

• Characterizing cough spectrograms in chronic respiratory diseases
• Identifying diagnostically relevant frequency subbands using XAI
• Distinguishing COPD from other respiratory conditions via spectral markers

Innovation

• XAI-based CNN analyzes cough spectrograms using occlusion maps
• Decomposes spectrograms into five diagnostic frequency subbands
• Identifies interpretable spectral markers distinguishing respiratory diseases