Logo PTI Logo FedCSIS

Proceedings of the 21st Conference on Computer Science and Intelligence Systems (FedCSIS)

Annals of Computer Science and Information Systems, Volume 47

Audio-Based Detection of COPD Exacerbations via Two-Stage Cough Detection and Classification

, ,

DOI: http://dx.doi.org/10.15439/2026F8312

Citation: Marcin Kolakowski, ,

Full text

Abstract. Chronic obstructive pulmonary disease (COPD) is a chronic respiratory condition characterized by frequent exacerbation episodes. The paper presents an approach to detecting COPD exacerbations based on audio recordings performed by patients. In the proposed algorithm, the audio signal is processed in two stages. First, it is converted to a mel spectrogram and analyzed by a neural network to extract cough segments. Next, the detected coughs are passed to a cough classification model, determining whether the cough is induced by a COPD exacerbation. The proposed approach was cross-validated using two datasets for cough detection and classification, and further evaluated on a synthetic dataset of recorded user narratives. The results show that effective cough detection is feasible, achieving an AUC of 0.989 and 0.967 on the synthetic dataset. COPD cough classification remains more challenging, with an AUC of 0.794, particularly due to the limited size of publicly available COPD-focused datasets.

References

  1. A. Lindberg et al., “Large underreporting of COPD as cause of death-results from a population-based cohort study,” Respiratory Medicine, vol. 186, p. 106518, Sep. 2021, http://dx.doi.org/10.1016/j.rmed.2021.106518.
  2. A. Anzueto, H. Hoy, and C. Gainer, “Challenges and Opportunities for the Management of COPD: A Narrative Review of Patient and Health Care Professional Perspectives,” J COPD F, vol. 12, no. 4, pp. 339–356, 2025, http://dx.doi.org/10.15326/jcopdf.2024.0597.
  3. L. Beckman, C. D. Muylder, and O. Reinhold, “Effects and challenges of Governance, Lean Healthcare and Digital Transformation in Outpatient Management: An integrative review,” Annals of Computer Science and Information Systems, vol. 45. Polish Information Processing Society, pp. 33–40, Oct. 15, 2025. http://dx.doi.org/10.15439/2025f2505.
  4. D. Zhu et al., “Identification of frequent acute exacerbations phenotype in COPD patients based on imaging and clinical characteristics,” Respiratory Medicine, vol. 209, p. 107150, Apr. 2023, http://dx.doi.org/10.1016/j.rmed.2023.107150.
  5. G. S. Araújo, O. A. C. Cortes, O. Reinhold, and F. M. F. Lobato, “Hybrid Approaches for Pneumonia Detection in X-rays: Combining CNNs and ML Classifiers,” Annals of Computer Science and Information Systems, vol. 43. Polish Information Processing Society, pp. 461–470, Oct. 15, 2025. http://dx.doi.org/10.15439/2025f4310.
  6. University Hospitals of Leicester NHS Trust, “i-IMPACT | An online programme for patients with a long-term cardiac, respiratory or Covid condition.” https://www.i-impact.co.uk/ (accessed Jun. 25, 2026)
  7. H. Davies et al., “myCOPD App for Managing Chronic Obstructive Pulmonary Disease: A NICE Medical Technology Guidance for a Digital Health Technology,” Appl Health Econ Health Policy, vol. 21, no. 5, pp. 689–700, May 2023, http://dx.doi.org/10.1007/s40258-023-00811-x.
  8. M. Atzeni, G. Cappon, J. K. Quint, F. Kelly, B. Barratt, and M. Vettoretti, “A machine learning framework for short-term prediction of chronic obstructive pulmonary disease exacerbations using personal air quality monitors and lifestyle data,” Sci Rep, vol. 15, no. 1, Jan. 2025, http://dx.doi.org/10.1038/s41598-024-85089-2.
  9. Y. Gong et al., “AI-driven smartphone screening for acute COPD exacerbations: enhancing health equity in developing regions,” npj Digit. Med., vol. 8, no. 1, Nov. 2025, http://dx.doi.org/10.1038/s41746-02502086-z.
  10. R. T. Bhowmik and S. P. Most, “A Personalized Respiratory Disease Exacerbation Prediction Technique Based on a Novel SpatioTemporal Machine Learning Architecture and Local Environmental Sensor Networks,” Electronics, vol. 11, no. 16, p. 2562, Aug. 2022, http://dx.doi.org/10.3390/electronics11162562.
  11. C. R. Khandhan and G. M. Kaviya, “Deep Learning Model for Chronic Obstructive Pulmonary Disease through Breathing Sound,” 2023 4th International Conference on Electronics and Sustainable Communication Systems (ICESC). IEEE, pp. 1514–1521, Jul. 06, 2023. http://dx.doi.org/10.1109/icesc57686.2023.10193372.
  12. Y. Yan, L. van Bemmel, F. M. E. Franssen, S. O. Simons, and V. Urovi, “Developing a multi-feature fusion model for exacerbation classification in asthma and COPD,” Computer Methods and Programs in Biomedicine, vol. 268, p. 108796, Aug. 2025, http://dx.doi.org/10.1016/j.cmpb.2025.108796.
  13. W. Sun, G. Wu, M. Ming, J. Zhang, C. Shi, and L. Qin, “Self-supervised learning for intelligent disease diagnosis using audio signals: beyond copd to a spectrum of diseases,” Appl Intell, vol. 55, no. 7, Feb. 2025, http://dx.doi.org/10.1007/s10489-024-06028-2.
  14. L. Orlandic, J. Thevenot, T. Teijeiro, and D. Atienza, “A Multimodal Dataset for Automatic Edge-AI Cough Detection,” 2023 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). IEEE, pp. 1–7, Jul. 24, 2023. http://dx.doi.org/10.1109/embc40787.2023.10340413.
  15. M. A. Fernandez-Granero, D. Sanchez-Morillo, and A. LeonJimenez, “An artificial intelligence approach to early predict symptom-based exacerbations of COPD,” Biotechnology & Biotechnological Equipment, vol. 32, no. 3, pp. 778–784, Feb. 2018, http://dx.doi.org/10.1080/13102818.2018.1437568.
  16. A. B. Chang, “The physiology of cough,” Paediatric Respiratory Reviews, vol. 7, no. 1, pp. 2–8, Mar. 2006, http://dx.doi.org/10.1016/j.prrv.2005.11.009.
  17. OpenAI, ChatGPT (GPT-5.3), large language model. [Online]. Available: https://chat.openai.com. (accessed Apr. 7, 2026)
  18. ElevenLabs, Eleven v3 — Most Expressive AI Voice Model.” https://elevenlabs.io/v3 (accessed Jun. 25, 2026)
  19. University of Science and Technology of China and Hangzhou slanhealth Co, Ltd, “Cough-COPD(CC) Dataset”. Zenodo, Feb. 17, 2025. http://dx.doi.org/10.5281/zenodo.14881818.
  20. B. McFee et al., “librosa: Audio and Music Signal Analysis in Python,” Proceedings of the Python in Science Conference. SciPy, pp. 18–24, 2015. http://dx.doi.org/10.25080/majora-7b98e3ed-003.
  21. F. Eyben, M. Wöllmer, and B. Schuller, “Opensmile,” Proceedings of the 18th ACM international conference on Multimedia. ACM, pp. 1459–1462, Oct. 25, 2010. http://dx.doi.org/10.1145/1873951.1874246.
  22. K. Matsumoto, M. Yoshida, and C. Karino, “Mining Patient Narratives to Analyze Lifestyle–Blood Glucose Relationships: An LLMBased Text Mining Framework,” J, vol. 9, no. 2, p. 14, May 2026. http://dx.doi.org/10.3390/j9020014.