![[2508.14949] XAI-Driven Spectral Analysis of Cough Sounds for Respiratory Disease Characterization](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2508.14949] XAI-Driven Spectral Analysis of Cough Sounds for Respiratory Disease Characterization
Summary
The paper presents an XAI-driven methodology for analyzing cough sounds to improve respiratory disease diagnosis, highlighting significant spectral differences in cough patterns among disease groups.
Why It Matters
This research is significant as it leverages explainable AI to enhance the interpretability of cough sound analysis, potentially leading to better diagnostic tools for respiratory diseases like COPD. Understanding cough patterns can aid in early detection and management of these conditions.
Key Takeaways
- XAI techniques improve the analysis of cough sounds for respiratory diseases.
- Significant spectral differences in cough patterns were found in COPD patients.
- Raw spectrogram analysis lacked the specificity revealed by the proposed methodology.
- Occlusion maps are effective in identifying relevant spectral regions in cough sounds.
- The study demonstrates the potential for AI to enhance diagnostic capabilities in healthcare.
Computer Science > Sound arXiv:2508.14949 (cs) [Submitted on 20 Aug 2025 (v1), last revised 17 Feb 2026 (this version, v2)] Title:XAI-Driven Spectral Analysis of Cough Sounds for Respiratory Disease Characterization Authors:Patricia Amado-Caballero, Luis Miguel San-José-Revuelta, María Dolores Aguilar-García, José Ramón Garmendia-Leiza, Carlos Alberola-López, Pablo Casaseca-de-la-Higuera View a PDF of the paper titled XAI-Driven Spectral Analysis of Cough Sounds for Respiratory Disease Characterization, by Patricia Amado-Caballero and 5 other authors View PDF Abstract:This paper proposes an eXplainable Artificial Intelligence (XAI)-driven methodology to enhance the understanding of cough sound analysis for respiratory disease management. We employ occlusion maps to highlight relevant spectral regions in cough spectrograms processed by a Convolutional Neural Network (CNN). Subsequently, spectral analysis of spectrograms weighted by these occlusion maps reveals significant differences between disease groups, particularly in patients with COPD, where cough patterns appear more variable in the identified spectral regions of interest. This contrasts with the lack of significant differences observed when analyzing raw spectrograms. The proposed approach extracts and analyzes several spectral features, demonstrating the potential of XAI techniques to uncover disease-specific acoustic signatures and improve the diagnostic capabilities of cough sound analysis by providing more inte...
