Diagnostic Software System for Automated Classification of Lung Sounds Based on Higher-Order Spectra Parameters
DOI:
https://doi.org/10.64915/RADAP.2026.104.54-62Keywords:
lung sounds, Higher-Order Spectra, bispectral analysis, automated classification, machine learning, chronic obstructive pulmonary disease, bronchitisAbstract
This paper presents a method for the automated classification of lung sounds based on Higher-Order Spectra (HOS) parameters. The system is designed to differentiate between healthy subjects and patients with bronchitis or Chronic Obstructive Pulmonary Disease (COPD). The study was conducted using a verified database of 806 recordings from 275 adult patients, obtained via the ''KoRA-03M1'' digital system, the Littmann 3200 stethoscope, and the open international ICBHI 2017 Respiratory Sound Database (Kaggle). Particular attention is paid to the signal preprocessing stage, which includes an algorithm for removing impulse noise (''spikes'') present in the recorded signals using a bidirectional filtering method. Unlike traditional linear analysis methods, the proposed HOS-based approach accounts for the nonlinear properties of signals and identifies hidden phase coupling between harmonics, which is critical for analyzing noisy biomedical data. Seven optimal features providing maximum class separability were used: the amplitudes of dominant bispectrum peaks, the coordinates of their corresponding bifrequencies, maximum bicoherence, and third- and fourth-order statistical moments (skewness and kurtosis). Based on the compiled database, machine learning models were trained. Multilayer Perceptron (MLP) neural networks demonstrated the highest performance, achieving an accuracy of 97.8%. The results confirm the high diagnostic value of using bispectrum parameters as reliable markers of respiratory pathologies, supporting the integration of the developed software system into modern telemedicine systems for remote monitoring.
References
1. T. Wanasinghe, S. Bandara, S. Madusanka, D. Meedeniya, M. Bandara, and I. D. L. T. Diez. (2024). Lung sound classification with multi-feature integration utilizing lightweight CNN model. IEEE Access, Vol. 12, pp. 21262-21276. DOI: 10.1109/ACCESS.2024.3361943.
2. Y. Zhang, Q. Huang, W. Sun, F. Chen, D. Lin, and F. Chen. (2024). Research on lung sound classification model based on dual-channel CNN-LSTM algorithm. Biomed. Signal Process. Control, Vol. 94, Art. no. 106257. DOI: 10.1016/j.bspc.2024.106257.
3. D.-M. Huang, J. Huang, K. Qiao, N.-S. Zhong, H.-Z. Lu, and W.-J. Wang. (2023). Deep learning-based lung sound analysis for intelligent stethoscope. Mil. Med. Res., Vol. 10, No. 1, Art. no. 44. DOI: 10.1186/s40779-023-00479-3.
4. G. Altan, Y. Kutlu, and N. Allahverdi. (2020). Deep learning on computerized analysis of chronic obstructive pulmonary disease. IEEE J. Biomed. Health Inform., Vol. 24, No. 5, pp. 1344-1350. DOI: 10.1109/JBHI.2019.2931395.
5. K. Lweesy, S. Abuqran, L. Fraiwan (2025). Lightweight Hybrid Deep Learning Models for Accurate Classification of Respiratory Conditions from Raw Lung Sounds". J Med Syst., 49(1):174. doi: 10.1007/s10916-025-02315-8. PMID: 41315171.
6. G. Petmezas, G.-A. Cheimariotis, L. Stefanopoulos, B. Rocha, R. P. Paiva, et al. (2022). Automated lung sound classification using a hybrid CNN-LSTM network and focal loss function. Sensors, Vol. 22, No. 3, Art. no. 1232. DOI: 10.3390/s22031232.
7. X. Liao, Y. Wu, N. Jiang, et al. (2023). Automated detection of abnormal respiratory sound from electronic stethoscope and mobile phone using MobileNetV2. Biocybernetics and Biomedical Engineering, Vol. 43, Iss. 4, рр. 63-775, ISSN 0208-5216, doi:10.1016/j.bbe.2023.11.001.
8. K.-C. Chua, V. Chandran, U. R. Acharya, and C. M. Lim. (2010). Application of higher order statistics/spectra in biomedical signals — A review. Med. Eng. Phys., Vol. 32, No. 7, pp. 679-689. DOI: 10.1016/j.medengphy.2010.04.009.
9. R. Dubey, R. M. Bodade, and D. Dubey. (2023). Efficient classification of the adventitious sounds of the lung through a combination of SVM-LSTM-Bayesian optimization algorithm with features based on wavelet bi-phase and bi-spectrum. Res. Biomed. Eng., Vol. 39, pp. 349-363. DOI: 10.1007/s42600-023-00270-2.
10. R. Palaniappan, K. Sundaraj, and S. Sundaraj. (2014). A comparative study of the SVM and k-NN machine learning algorithms for the diagnosis of respiratory pathologies using pulmonary acoustic signals. BMC Bioinformatics, Vol. 15, No. 1, Art. no. 223. DOI: 10.1186/1471-2105-15-223.
11. A. M. Kwon and K. Kang. (2022). A temporal dependency feature in lower dimension for lung sound signal classification. Sci. Rep., Vol. 12, Art. no. 7889. DOI: 10.1038/s41598-022-11726-3.
12. S. B. Sangle and C. J. Gaikwad. (2023). Accumulated bispectral image-based respiratory sound signal classification using deep learning. Signal, Image and Video Processing, Vol. 17, pp. 3629-3636. DOI: 10.1007/s11760-023-02589-w.
13. A. Rao, E. Huynh, T. J. Royston, A. Kornblith, and S. Roy. (2019). Acoustic Methods for Pulmonary Diagnosis. IEEE Rev. Biomed. Eng., Vol. 12, pp. 221-239. DOI: 10.1109/RBME.2018.2874353.
14. Garcia-Mendez, Juan P., et al. (2023). Machine Learning for Automated Classification of Abnormal Lung Sounds Obtained from Public Databases: A Systematic Review. Bioengineering, Vol. 10, No. 10: 1155. DOI: 10.3390/bioengineering10101155.
15. L. Fraiwan, N. Hassanin, M. Fraiwan, B. Khassawneh, A. E. Ibnian, and M. Alkhodari. (2021). Automatic identification of respiratory diseases from stethoscopic lung sound signals using ensemble classifiers. Biocybern. Biomed. Eng., Vol. 41, No. 1, pp. 1-14. DOI: 10.1016/j.bbe.2020.11.003.
16. H. S. Porieva, Y. S. Karplyuk, A. Makarenkova, and A. Makarenkov. (2015). Detection of COPD's diagnostic signs based on polyspectral lung sounds analysis of respiratory phases. ELNANO, pp. 351-355. DOI: 10.1109/ELNANO.2015.7146908.
17. H. Porieva, B. Kaliuga and K. Ivanko. (2022). Differentiating of Respiratory Noise Based on Higher Order Spectral Analysis. ELNANO, pp. 446-450. DOI: 10.1109/ELNANO54667.2022.9927121.
18. H. S. Porieva, V. I. Vaityshyn, and Y. S. Karplyuk. (2017). Machine learning methods for studying lungsound signals. Microsyst. Electron. Acoust., Vol. 22, No. 6, pp. 41-47. DOI: 10.20535/2523-4455.2017.22.6.108829.
19. A. A. Makarenkova. (2010). Investigation and objectifying of adventitious breath sounds in the patients with chronic obstructive pulmonary disease. Acoust. Bull., Vol. 13, No. 3, pp. 31-41.
20. Respiratory Sound Database. ICBHI 2017 Challenge, Kaggle. [Online].
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Г. С. Порєва, К. О. Іванько , Є. С. Карплюк , А. О. Попов , Філіп де Шазаль
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
