Automated Identification Of Respiratory Anomalies From Cough Acoustics Using Spectrogram-Driven Deep Learning

Marcus L. Bennett

Authors

Marcus L. Bennett Department of Computer Science, University of Cambridge, Cambridge, United Kingdom

Keywords:

Cough acoustics, respiratory anomaly detection, spectrogram analysis, deep learning

Abstract

Cough is a vital physiological reflex, often serving as a primary indicator of respiratory and other underlying health conditions [1]. Chronic cough, in particular, can significantly impair quality of life and signal persistent health issues such as asthma or chronic obstructive pulmonary disease (COPD) [2], [3]. Traditional diagnostic methods often rely on subjective patient reporting and time-consuming clinical assessments, which can lead to both over- and under-diagnosis [4]. This article presents a novel deep learning framework leveraging spectrograms of cough sounds for the automated identification of respiratory anomalies. By transforming raw audio signals into visual representations, we enable Convolutional Neural Networks (CNNs) to discern subtle patterns indicative of various pulmonary conditions. The proposed system demonstrates high accuracy in classifying anomalous cough sounds, offering a non-invasive, scalable, and potentially early detection tool to augment clinical diagnosis. Our findings underscore the significant potential of AI-driven acoustic analysis in revolutionizing respiratory healthcare diagnostics.

References

D. Mutolo, L. Iovino, E. Cinelli, F. Bongianni, and T. Pantaleo, "Physiology of the Cough Reflex: Sensory and Mechanical Features," Cough: Pathophysiology, Diagnosis and Treatment, pp. 3-21, 2020.

K. F. Chung et al., "Cough hypersensitivity and chronic cough," Nature Reviews Disease Primers, vol. 8, no. 1, p. 45, 2022.

U. Frey and B. Suki, "Complexity of chronic asthma and chronic obstructive pulmonary disease: implications for risk assessment, and disease progression and control," The Lancet, vol. 372, no. 9643, pp. 1088-1099, 2008.

J. Kavanagh, D. J. Jackson, and B. D. Kent, "Over-and under-diagnosis in asthma," Breathe, vol. 15, no. 1, pp. e20-e27, 2019.

A. Ijaz et al., "Towards using cough for respiratory disease diagnosis by leveraging Artificial Intelligence: A survey," Informatics in Medicine Unlocked, vol. 29, p. 100832, 2022.

S. Preethi, A. Revathi, and M. Murugan, "Exploration of cough recognition technologies grounded on sensors and artificial intelligence," Internet of Medical Things for Smart Healthcare: Covid-19 Pandemic, pp. 193-214, 2020.

M. Kilic et al., "GCLP: An automated asthma detection model based on global chaotic logistic pattern using cough sounds," Engineering Applications of Artificial Intelligence, vol. 127, p. 107184, 2024.

G. Shruthi, K. R. PM, A. S. Naidu, A. Kumari, C. Sravanti, and P. Gayathri, "Detection of Lung Disease using Deep Learning Approaches," in 2023 International Conference on Network, Multimedia and Information Technology (NMITCON), 2023: IEEE, pp. 1-8.

W. Wang, Q. Shang, and H. Lu, "Automatic COVID-19 detection from cough sounds using multi-headed convolutional neural networks," Applied Sciences, vol. 13, no. 12, p. 6976, 2023.

M. Kuluozturk et al., "DKPNet41: Directed knight pattern network-based cough sound classification model for automatic disease diagnosis," Medical Engineering & Physics, vol. 110, p. 103870, 2022.

S. K. Prajapati, T. S. Choudhary, and S. Mishra, "Early detection of lung disease using multi-class classifiers," in 2023 IEEE 4th Annual Flagship India Council International Subsections Conference (INDISCON), 2023: IEEE, pp. 01-06.

M. A. Iqbal, K. Devarajan, and S. M. Ahmed, "Real time detection and forecasting technique for asthma disease using speech signal and DENN classifier," Biomedical Signal Processing and Control, vol. 76, p. 103637, 2022.

P. D. Barua et al., "Automated asthma detection in a 1326-subject cohort using a one-dimensional attractive-and-repulsive center-symmetric local binary pattern technique with cough sounds," Neural Computing and Applications, pp. 1-15, 2024.

I. Topaloglu et al., "Explainable attention ResNet18-based model for asthma detection using stethoscope lung sounds," Engineering Applications of Artificial Intelligence, vol. 126, p. 106887, 2023.

A. Kumar, K. Abhishek, C. Chakraborty, and N. Kryvinska, "Deep learning and internet of things based lung ailment recognition through coughing spectrograms," IEEE Access, vol. 9, pp. 95938-95948, 2021.

L. Yue and W. Xu, "Automatic classification of childhood asthma and pneumonia based on cough sound analysis," in 2021 2nd International Conference on Artificial Intelligence and Computer Engineering (ICAICE), 2021: IEEE, pp. 779-783.

S. Z. H. Naqvi, M. Arooj, S. Aziz, M. U. Khan, and M. A. Choudhary, "Spectral analysis of lungs sounds for classification of asthma and pneumonia wheezing," in 2020 International Conference on Electrical, Communication, and Computer Engineering (ICECCE), 2020: IEEE, pp. 1-6.

P. Porter et al., "A prospective multicentre study testing the diagnostic accuracy of an automated cough sound centred analytic system for the identification of common respiratory disorders in children," Respiratory research, vol. 20, pp. 1-10, 2019.

A. Ö. Türkçetin, T. Koç, and Ş. Çilekar, "The Use of ANN in the Sound Detection of Lung Diseases: Example of COPD, Asthma, Pneumonia," in 2023 31st Signal Processing and Communications Applications Conference (SIU), 2023: IEEE, pp. 1-4.

I. Sen, M. Saraclar, and Y. P. Kahya, "Differential diagnosis of asthma and COPD based on multivariate pulmonary sounds analysis," IEEE Transactions on Biomedical Engineering, vol. 68, no. 5, pp. 1601-1610, 2021.

B. BT et al., "Asthmatic versus healthy child classification based on cough and vocalised/ɑ:/sounds," The Journal of the Acoustical Society of America, vol. 148, no. 3, pp. EL253-EL259, 2020.

H. Jeon, Y. Jung, S. Lee, and Y. Jung, "Area-efficient short-time fourier transform processor for time–frequency analysis of non-stationary signals," Applied Sciences, vol. 10, no. 20, p. 7208, 2020.

J. Amoh and K. Odame, "Deep neural networks for identifying cough sounds," IEEE transactions on biomedical circuits and systems, vol. 10, no. 5, pp. 1003-1011, 2016.

M. T. García-Ordás, J. A. Benítez-Andrades, I. García-Rodríguez, C. Benavides, and H. Alaiz-Moretón, "Detecting respiratory pathologies using convolutional neural networks and variational autoencoders for unbalancing data," Sensors, vol. 20, no. 4, p. 1214, 2020.

H.-C. Kuo, B.-S. Lin, Y.-D. Wang, and B.-S. Lin, "Development of automatic wheeze detection algorithm for children with asthma," IEEE Access, vol. 9, pp. 126882-126890, 2021.

A. Yahyaoui and N. Yumuşak, "Deep and machine learning towards pneumonia and asthma detection," in 2021 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT), 2021: IEEE, pp. 494-497.

Z. Tariq, S. K. Shah, and Y. Lee, "Lung disease classification using deep convolutional neural network," in 2019 IEEE international conference on bioinformatics and biomedicine (BIBM), 2019: IEEE, pp. 732-735.

S. Jayalakshmy, B. L. Priya, and N. Kavya, "CNN based Categorization of respiratory sounds using spectral descriptors," in 2020 International Conference on Communication, Computing and Industry 4.0 (C2I4), 2020: IEEE, pp. 1-5.

M. Fraiwan, L. Fraiwan, M. Alkhodari, and O. Hassanin, "Recognition of pulmonary diseases from lung sounds using convolutional neural networks and long short-term memory," Journal of Ambient Intelligence and Humanized Computing, pp. 1-13, 2022.

D. Varshni, K. Thakral, L. Agarwal, R. Nijhawan, and A. Mittal, "Pneumonia detection using CNN based feature extraction," in 2019 IEEE international conference on electrical, computer and communication technologies (ICECCT), 2019: IEEE, pp. 1-7.

A. Roy and U. Satija, "AsthmaSCELNet: A lightweight supervised contrastive embedding learning framework for asthma classification using lung sounds," entropy, vol. 1282, p. 100, 2023.

Frontiers in Emerging Artificial Intelligence and Machine Learning

Article Details Page