Voice as an Indicator for Laryngeal Disorders Using Data Mining Approach

Mohammadjavad Sayadi, Mostafa Langarizadeh, Farhad Torabinezhad, Gholamreza Bayazian
9

Views


Abstract

Introduction: Laryngeal disorders are a common health problem that affects people of all ages, genders, and races. One of the main symptoms of laryngeal disorders is changes in the voice, which can be used as an indicator for the presence of such disorders. In this paper, we present a data mining approach for using voice as an indicator for laryngeal disorders.

Material and Methods: We collected a dataset of voice recordings from individuals with and without laryngeal disorders including 434 people from two clinical centers in Tehran. The dataset was created using a powerful signal processing program and then based on the difference between male and female voice, the dataset was separated into two datasets. Finally, a Deep Neural Network was implemented for modelling using Python programming language and F1-score, Accuracy, Sensitivity, Specificity, and AUC as the model’s evaluation metrics were reported.

Results: Among all the acoustic features, 23 features were selected for the male dataset and 25 features for the female data set. For the male dataset the final model achieved F1-Score of 0.915 and Accuracy of 0.910. For the female dataset the result was 0.884 of F1-Score and 0.896 of Accuracy.

Conclusion: Our results show that machine learning algorithms can accurately classify voice recordings into two groups: individuals with laryngeal disorders and those without. The high accuracy achieved by the algorithms suggests that voice can be used as an objective and automated diagnostic tool for laryngeal disorders.

Keywords

Voice; Laryngeal Disorders; Indicator; Data Mining;

References

Yavari A, Fatehi F, Dalvand H, Valizadeh A, Moradzadeh R, Mirhoseini FS. Prevalence of speech disorders in Arak primary school students, 2014-2015. Journal of Arak University of Medical Sciences. 2016; 19(111): 87-94.

Rufo MJ, Martin J, Perez CJ, Paniagua S. A bayesian decision analysis approach to assess voice disorder risks by using acoustic features. Biom J. 2019; 61(3): 503-13. PMID: 30408226 DOI: 10.1002/bimj.201700233

Sutton RT, Pincock D, Baumgart DC, Sadowski DC, Fedorak RN, Kroeker KI. An overview of clinical decision support systems: Benefits, risks, and strategies for success. NPJ Digit Med. 2020; 3: 17. PMID: 32047862 DOI: 10.1038/s41746-020-0221-y

Musen MA, Middleton B, Greenes RA. Clinical decision-support systems. In: Shortliffe EH, Cimino JJ (Eds). Biomedical informatics: Computer applications in health care and biomedicine. 5th ed. Springer; 2021.

Asadi H, AliNejad B. Speech rhythm measures: Acoustic cues for speaker identification. Journal of Language Research. 2022; 12(2): 29-49.

Abaspur Kazerouni I, Moslemi H, Hourali F. The intelligent diagnosis of speech disorder: Using of audio signal processing system. Medical Journal of Tabriz University of Medical Sciences. 2018; 40(5): 55-62.

Arjmandi MK, Pooyan M, Mikaili M, Vali M, Moqarehzadeh A. Identification of voice disorders using long-time features and support vector machine with different feature reduction methods. J Voice. 2011; 25(6): e275-89. PMID: 21186096 DOI: 10.1016/j.jvoice.2010.08.003

Kuo Y-M, Ruan S-J, Chen Y-C, Tu Y-W. Deep-learning-based automated classification of chinese speech sound disorders. Children (Basel). 2022; 9(7): 996. PMID: 35883979 DOI: 10.3390/children9070996

Sayadi M, Varadarajan V, Langarizadeh M, Bayazian G, Torabinezhad F. A systematic review on machine learning techniques for early detection of mental, neurological and laryngeal disorders using patient’s speech. Electronics. 2022; 11: 4235.

Ghasemzadeh H, Khass MT, Arjmandi MK, Pooyan M. Detection of vocal disorders based on phase space parameters and lyapunov spectrum. Biomedical Signal Processing and Control. 2015; 22(1): 135-45.

Mahmoud SS, Kumar A, Li Y, Tang Y, Fang Q. Performance evaluation of machine learning frameworks for aphasia assessment. Sensors (Basel). 2021; 21(8): 2582. PMID: 33916993 DOI: 10.3390/s21082582

Fonseca ES, Guido RC, Scalassara PR, Maciel CD, Pereira JC. Wavelet time-frequency analysis and least squares support vector machines for the identification of voice disorders. Comput Biol Med. 2007; 37(4): 571-8. PMID: 17078942 DOI: 10.1016/j.compbiomed.2006.08.008

Verikas A, Gelzinis A, Bacauskiene M, Hållander M, Uloza V, Kaseta M. Combining image, voice, and the patient’s questionnaire data to categorize laryngeal disorders. Artif Intell Med. 2010; 49(1): 43-50. PMID: 20338736 DOI: 10.1016/j.artmed.2010.02.002




DOI: https://doi.org/10.30699/fhi.v13i0.605

Refbacks

  • There are currently no refbacks.