![[2508.16237] A XAI-based Framework for Frequency Subband Characterization of Cough Spectrograms in Chronic Respiratory Disease](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2508.16237] A XAI-based Framework for Frequency Subband Characterization of Cough Spectrograms in Chronic Respiratory Disease
Summary
This paper presents an explainable AI framework for analyzing cough sounds linked to chronic respiratory diseases, focusing on COPD. It utilizes CNNs to extract spectral features from cough spectrograms, revealing diagnostic patterns across different frequency subbands.
Why It Matters
Understanding cough acoustics through an explainable AI framework enhances diagnostic capabilities for chronic respiratory diseases. By identifying specific spectral markers, this research could lead to improved patient outcomes and more targeted treatments, particularly for COPD.
Key Takeaways
- The study employs a CNN to analyze cough sounds for chronic respiratory disease diagnosis.
- Frequency subband analysis reveals distinct spectral patterns that differentiate COPD from other conditions.
- The framework enhances interpretability of cough acoustics, aiding in clinical diagnostics.
- Occlusion maps highlight diagnostically relevant areas within cough spectrograms.
- Findings support the use of XAI in biomedical signal interpretation for better healthcare applications.
Computer Science > Machine Learning arXiv:2508.16237 (cs) [Submitted on 22 Aug 2025 (v1), last revised 17 Feb 2026 (this version, v2)] Title:A XAI-based Framework for Frequency Subband Characterization of Cough Spectrograms in Chronic Respiratory Disease Authors:Patricia Amado-Caballero, Luis M. San-José-Revuelta, Xinheng Wang, José Ramón Garmendia-Leiza, Carlos Alberola-López, Pablo Casaseca-de-la-Higuera View a PDF of the paper titled A XAI-based Framework for Frequency Subband Characterization of Cough Spectrograms in Chronic Respiratory Disease, by Patricia Amado-Caballero and 5 other authors View PDF 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...
