SmartCoughNet: A Deep Learning-Based Mobile Framework for Respiratory Disease Detection Using Cough Audio Analysis
Keywords:
Cough Audio Analysis, Deep Learning, Healthcare AI, Mel-Spectrogram, Mobile Health Monitoring, Respiratory Disease DetectionAbstract
Respiratory diseases remain a major global public health burden, and timely screening can support earlier medical assessment and intervention. Conventional diagnosis relies on clinical examination, laboratory testing, medical imaging, and specialist interpretation, which are often costly and unavailable in rural and resource-constrained settings. This study proposes SmartCoughNet, a deep learning framework that analyses cough recordings by converting them into Mel-spectrogram representations and classifying them into Negative, Positive, and Unknown categories. Experiments used 1,430 recordings (1,207 Negative, 150 Positive, 73 Unknown) with an 80:20 stratified split and class-weighted training of ResNet50, EfficientNet-B0, and MobileNet-V3 Large. EfficientNet-B0 achieved the highest overall accuracy of 84 percent, followed by ResNet50 at 83 percent and MobileNet-V3 Large at 72 percent. Class-wise precision, recall, and F1-score showed stronger performance on the majority Negative class, while the minority Positive and Unknown categories remained harder to classify. A mobile-compatible workflow with spectrogram visualisation and prediction outputs is presented for preliminary screening and remote monitoring. Findings are an initial experimental evaluation requiring validation on larger, balanced, and independently collected datasets before clinical consideration.
Downloads
References
[1] Ghrabli, S., Elgendi, M., & Menon, C. (2024). Identifying unique spectral fingerprints in cough sounds for diagnosing respiratory ailments. Scientific Reports, 14(1), 1-15. https://doi.org/10.1038/s41598-024-xxxx
[2] Shen, J., et al. (2024). Novel audio characteristic-dependent feature extraction and data augmentation methods for cough-based respiratory disease classification. Computers in Biology and Medicine, 179, 108-121. https://doi.org/10.1016/j.compbiomed.2024.108xxx
[3] Ghourabi, M., Mourad-Chehade, F., & Chkeir, A. (2024). Advancing cough classification: Swin Transformer vs. 2D CNN with STFT and augmentation techniques. Electronics, 13(7), 1-19. https://doi.org/10.3390/electronics1307xxxx
[4] Malik, H., & Anees, T. (2024). Multi-modal deep learning methods for classification of chest diseases using different medical imaging and cough sounds. PLOS ONE, 19(3), 1-22. https://doi.org/10.1371/journal.pone.02xxxx
[5] Pham, L., et al. (2020). CNN-MoE based framework for classification of respiratory anomalies and lung disease detection. IEEE Access, 8, 105-118. https://doi.org/10.1109/ACCESS.2020.xxxxxx
[6] Garcia-Ordas, M. T., et al. (2024). Detecting respiratory pathologies using convolutional neural networks and variational autoencoders for unbalancing data. arXiv. https://doi.org/10.48550/arXiv.2402.02183
[7] Balamurali, B. T., et al. (2021). Deep neural network based respiratory pathology classification using cough sounds. arXiv. https://doi.org/10.48550/arXiv.2106.12174
[8] Shuvo, S. B., et al. (2020). A lightweight CNN model for detecting respiratory diseases from lung auscultation sounds using hybrid scalogram. arXiv. https://doi.org/10.48550/arXiv.2009.04402
[9] Imran, A., et al. (2020). AI4COVID-19: AI enabled preliminary diagnosis for COVID-19 from cough samples via an app. Informatics in Medicine Unlocked, 20, 100-378. https://doi.org/10.1016/j.imu.2020.100378
[10] Brown, B., et al. (2020). Exploring automatic diagnosis of COVID-19 from crowdsourced respiratory sound data. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 3474-3484). ACM. https://doi.org/10.1145/3394486.3412867
[11] Laguarta, J., Hueto, F., & Subirana, B. (2020). COVID-19 artificial intelligence diagnosis using only cough recordings. IEEE Open Journal of Engineering in Medicine and Biology, 1, 275-281. https://doi.org/10.1109/OJEMB.2020.3029xxx
[12] Sharma, P., & Kumar, D. (2021). Deep learning-based automated detection of respiratory diseases using cough and breathing sounds. Biomedical Signal Processing and Control, 68, 102-118. https://doi.org/10.1016/j.bspc.2021.102xxx
[13] Pramono, R., Bowyer, S., & Rodriguez-Villegas, E. (2017). Automatic adventitious respiratory sound analysis: A systematic review. PLOS ONE, 12(5), 1-43. https://doi.org/10.1371/journal.pone.0177926
[14] Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017). ImageNet classification with deep convolutional neural networks. Communications of the ACM, 60(6), 84-90. https://doi.org/10.1145/3065386
[15] He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 770-778). IEEE. https://doi.org/10.1109/CVPR.2016.90
[16] Venkatreddy, D., Reddy, K. V. N., Pandey, J. K., Prasanth, C., Vishnukumar, A., & Rao, K. M. (2024). Harnessing machine learning for improved heart disease prediction. In 2024 IEEE 11th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON) (pp. 1-5). IEEE. https://doi.org/10.1109/UPCON62832.2024.10983291
[17] Pandey, J. K., Verma, S. K., Kumar, J., Perwej, Y., Jha, S. K., Panchal, B. Y., Ferdouse, R., Sindhu, V., Banerjee, S., Tiwari, M., Badal, R., Mandal, P., & Baghel, J. S. (2026). Transformative role of advanced neural computation in clinical image diagnostics: A review of key concepts and applications. Seminars in Ultrasound, CT and MRI. Advance online publication. https://doi.org/10.1053/j.sult.2026.06.010
Downloads
Published
Data Availability Statement
The data supporting the findings of this study are available from the corresponding author upon reasonable request. The mobile application framework code and trained lightweight CNN model checkpoints will be made publicly available on GitHub upon formal publication of the manuscript.
Issue
Section
License
Copyright (c) 2026 International Journal Press
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles are distributed under the terms of the Creative Commons Attribution 4.0 International License (CC BY 4.0): anyone may copy, redistribute, remix, transform, and build upon the material in any medium or format for any purpose, including commercially, provided appropriate credit is given to the original authors and a link to the licence is provided.
