Comparative Analysis of Classifiers for the Assessment of Respiratory Disorders Using Speech Parameters

• Autorzy: Shrivastava Poonam , Tripathi Neeta , Singh Bikesh Kumar , Dewangan Bhupesh Kumar

Identyfikatory

DOI

10.24425/aoa.2022.142905

• Języki publikacji: EN

Abstrakty

EN

Non-invasive techniques for the assessment of respiratory disorders have gained increased importance in recent years due to the complexity of conventional methods. In the assessment of respiratory disorders, machine learning may play a very essential role. Respiratory disorders lead to variation in the production of speech as both go hand in hand. Thus, speech analysis can be a useful means for the pre-diagnosis of respiratory disorders. This article aims to develop a machine learning approach to differentiate healthy speech from speech corresponding to different respiratory disorders (affected). Thus, in the present work, a set of 15 relevant and efficient features were extracted from acquired data, and classification was done using different classifiers for healthy and affected speech. To assess the performance of different classifiers, accuracy, specificity (Sp), sensitivity (Se), and area under the receiver operating characteristic curve (AUC) was used by applying both multi-fold cross-validation methods (5-fold and 10-fold) and the holdout method. Out of the studied classifiers, decision tree, support vector machine (SVM), and k-nearest neighbor (KNN) were found more appropriate in providing correct assessment clinically while considering 15 features as well as three significant features (Se > 89%, Sp > 89%, AUC> 82%, and accuracy > 99%). The conclusion was that the proposed classifiers may provide an aid in the simple assessment of respiratory disorders utilising speech parameters with high efficiency. In the future, the proposed approach can be evaluated for the detection of specific respiratory disorders such as asthma, COPD, etc.

Słowa kluczowe

EN

healthy speech; affected speech; machine learning; classification techniques; respiratory disorders; speech analysis

• Wydawca: Instytut Podstawowych Problemów Techniki PAN ; Komitet Akustyki PAN ; Polskie Towarzystwo Akustyczne
• Czasopismo: Archives of Acoustics
• Rocznik: 2023
• Tom: Vol. 48, No. 1
• Strony: 13--24
• Opis fizyczny: Bibliogr., 25 poz., rys., tab., wykr.

Twórcy

autor

Shrivastava Poonam

• Department of Electronics and Telecommunication, SSTC Bhilai, India

autor

Tripathi Neeta

• Department of Electronics and Telecommunication, SSTC Bhilai, India

autor

Singh Bikesh Kumar

• Department of Biomedical Engineering, National Institute of Technology Raipur, India

• https://orcid.org/0000-0002-5052-9768

autor

Dewangan Bhupesh Kumar

• Department of Computer Science and Engineering, School of Engineering, OP Jindal University Raigarh, India

Bibliografia

• 1. Alghowinem S. et al. (2013), A comparative study of different classifiers for detecting depression from spontaneous speech, [in:] 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 8022-8026, doi: 10.1109/ICASSP.2013.6639227.
• 2. Amaral J.L., Lopes A.J., Jansen J.M., Faria A.C., Melo P.L. (2012), Machine learning algorithms and forced oscillation measurements applied to the automatic identification of chronic obstructive pulmonary disease, Computer Methods and Programs in Biomedicine, 105(3): 183-193, doi: 10.1016/j.cmpb.2011.09.009.
• 3. Amaral J.L., Lopes A.J., Jansen J.M., Faria A.C., Melo P.L. (2013), An improved method of early diagnosis of smoking-induced respiratory changes using machine learning algorithms, Computer Methods and Programs in Biomedicine, 112(3): 441-454, doi: 10.1016/j.cmpb.2013.08.004.
• 4. Byun H., Lee S.W. (2002), Applications of support vector machines for pattern recognition: A survey, [in:] International Workshop on Support Vector Machines, pp. 213-236, Springer, Berlin, Heidelberg, doi: 10.1007/3-540-45665-1_17.
• 5. Calverley P.M.A. (2020), Defining airflow obstruction: More data, further clarity, American Journal of Respiratory and Critical Care Medicine, 202(5): 649-650, doi: 10.1164/rccm.202005-1551ED.
• 6. Caruana R., Niculescu-Mizil A. (2006), An empirical comparison of supervised learning algorithms, [in:] Proceedings of the 23rd International Conference on Machine Learning, pp. 161-168, doi: 10.1145/1143844.1143865.
• 7. Chun K.S. et al. (2020), Towards passive assessment of pulmonary function from natural speech recorded using a mobile phone, [in:] 2020 IEEE International Conference on Pervasive Computing and Communications (PerCom), pp. 1-10, doi: 10.1109/PerCom45495.2020.9127380.
• 8. Dixit, Mittal V., Sharma Y. (2014), Voice parameter analysis for the disease detection, IOSR Journal of Electronics and Communication Engineering, 9(3): 48-55.
• 9. Dogan M., Eryuksel E., Kocak I., Celikel T., Sehitoglu M.A. (2007), Subjective and objective evaluation of voice quality in patients with asthma, Journal of Voice, 21(2): 224-230, doi: 10.1016/j.jvoice.2005.11.003.
• 10. Fawcett T. (2006), An introduction to ROC analysis, Pattern Recognition Letters, 27(8): 861-874, doi: 10.1016/j.patrec.2005.10.010.
• 11. Gore S.M., Salunke M.M., Patil S.A., Kemalkar A.K. (2020), Disease detection using voice analysis, International Research Journal of Engineering and Technology, 7(5): 7655-7659.
• 12. Gürbüz E., Kılıç E. (2014), A new adaptive support vector machine for diagnosis of diseases, Expert Systems, 31(5), 389-397, doi: 10.1111/exsy.12051.
• 13. Halpin D.M. et al. (2021), Global initiative for the diagnosis, management, and prevention of chronic obstructive lung disease. The 2020 GOLD science committee report on COVID-19 and chronic obstructive pulmonary disease, American Journal of Respiratory and Critical Care Medicine, 203(1): 24-36, doi: 10.1164/rccm.202009-3533SO.
• 14. Jain D., Singh V. (2018), Feature selection and classification systems for chronic disease prediction: A re view, Egyptian Informatics Journal, 19(3): 179-189, doi: 10.1016/j.eij.2018.03.002.
• 15. Kocsis O. et al. (2017), Assessing machine learning algorithms for self-management of asthma, [in:] 2017 E-Health and Bioengineering Conference (EHB), pp. 571-574, doi: 10.1109/EHB.2017.7995488.
• 16. Kuncheva L.I. (2014), Combining Pattern Classifiers: Methods and Algorithms, John Wiley & Sons.
• 17. Mohamed E.E., El Maghraby R.A. (2014), Voice changes in patients with chronic obstructive pulmonary disease, Egyptian Journal of Chest Diseases and Tuberculosis, 63(3), 561-567, doi: 10.1016/j.ejcdt.2014.03.006.
• 18. Refaeilzadeh P., Tang L., Liu H. (2009), Cross-validation, [in:] Encyclopedia of Database Systems, Liu L., Özsu M. [Eds.], Springer, doi: 10.1007/978-0-387-39940-9_565.
• 19. Saloni, Sharma R.K., Gupta A.K. (2014), Disease detection using voice analysis: A review, International Journal of Medical Engineering and Informatics, 6(3): 189-209, doi: 10.1504/IJMEI.2014.063173.
• 20. Sapankevych N.I., Sankar R. (2009), Time series prediction using support vector machines: A survey, IEEE Computational Intelligence Magazine, 4(2): 24-38, doi: 10.1109/MCI.2009.932254.
• 21. Sonu, Sharma R.K. (2011), Disease detection using analysis of voice parameters, [in:] 5th IEEE International Conference on Advanced Computing and Communication Technologies (ICACCT-2011), Choudhary R.K., Verma M., Saini S. [Eds.], pp. 416-420.
• 22. Teixeira J.P., Fernandes P.O. (2014), Jitter, shimmer and HNR classification within gender, tones and vowels in healthy voices, Procedia Technology, 16: 1228-1237, doi: 10.1016/j.protcy.2014.10.138.
• 23. Tsang K.C., Pinnock H., Wilson A.M., Shah S.A. (2020), Application of machine learning to support self-management of asthma with mHealth, [in:] 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), pp. 5673-5677, doi: 10.1109/EMBC44109.2020.9175679.
• 24. Walia G.S., Sharma R.K. (2016), Level of asthma: mathematical formulation based on acoustic parameters, [in:] 2016 Conference on Advances in Signal Processing (CASP), pp. 24-27, doi: 10.1109/CASP.2016.7746131.
• 25. Wiechern B., Liberty K.A., Pattemore P., Lin E. (2018), Effects of asthma on breathing during reading aloud, Speech, Language and Hearing, 21(1): 30-40, doi: 10.1080/2050571X.2017.1322740.

Uwagi

Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023). (PL)