Detection of Parkinson Disease Using Frequency Sub-bands of Vocal Cords Vibration Signals and Machine Learning Techniques

Öz

In this study, we proposed a new approach for diagnosing Parkinson’s disease (PD) based on the slope values between neighboring amplitudes of vocal cord vibration signals. The inter-amplitude slope signals were obtained by computing the slopes between adjacent amplitudes in the vocal cord vibration signals. Feature vectors were extracted using common statistical parameters and applied to widely used machine learning classifiers such as Naive Bayes (NB), Generalized Logistic Regression (GLR), Logistic Regression (LR), Decision Tree (DT), and Random Forest (RFs). Different experiments were conducted to evaluate the contribution of the inter-amplitude slope approach and the performance of the classifiers in distinguishing healthy and PD segments. The experiments were carried out on original signals, inter-amplitude slope signals, and sub-band decompositions of both original and slope signals. The results showed satisfactory classification accuracy for all feature extraction methods, with the highest accuracy achieved using inter-amplitude slope signals. The GLR and Random Forest (RFs)-based classifiers outperformed others, achieving 100% accuracy, while the LR classifier reached 91%, and the DT and NB classifiers achieved 95%. Finally, the inter-amplitude slope approach, used for the first time in this study, enhanced classifier performance in PD diagnosis.

Anahtar Kelimeler

• Vocal cords
• Parkinson
• inter-features slope

Ses Telleri Titreşim Sinyallerinin Frekans Alt Bantları ve Makine Öğrenimi Teknikleri Kullanılarak Parkinson Hastalığının TespitiDetection of Parkinson Disease Using Frequency Sub-Bands of Vocal Cords Vibration Signals and Machine Learning Techniques

Öz

Bu çalışmada, ses teli titreşim sinyallerinin komşu genlikleri arasındaki eğim değerlerine dayanarak Parkinson hastalığının (PH) teşhisi için yeni bir yaklaşım önerdik. Genlikler arası eğim sinyalleri, ses teli titreşim sinyallerindeki komşu genlikler arasındaki eğimlerin hesaplanmasıyla elde edilmiştir. Özellik vektörleri ortak istatistiksel parametreler kullanılarak çıkarılmış ve Naive Bayes (NB), Genelleştirilmiş Lojistik Regresyon (GLR), Lojistik Regresyon (LR), Karar Ağacı (DT) ve Rastgele Orman (RFs) gibi yaygın olarak kullanılan makine öğrenimi sınıflandırıcılarına uygulanmıştır. Genlikler arası eğim yaklaşımının katkısını ve sınıflandırıcıların sağlıklı ve PD segmentlerini ayırt etmedeki performansını değerlendirmek için farklı deneyler yapılmıştır. Deneyler orijinal sinyaller, genlikler arası eğim sinyalleri ve hem orijinal hem de eğim sinyallerinin alt bant ayrıştırmaları üzerinde gerçekleştirilmiştir. Sonuçlar, tüm özellik çıkarma yöntemleri için tatmin edici sınıflandırma doğruluğu göstermiş ve en yüksek doğruluk genlikler arası eğim sinyalleri kullanılarak elde edilmiştir. GLR ve Rastgele Orman (RFs) tabanlı sınıflandırıcılar diğerlerinden daha iyi performans göstererek %100 doğruluk elde ederken, LR sınıflandırıcı %91'e, DT ve NB sınıflandırıcılar ise %95'e ulaşmıştır. Son olarak, bu çalışmada ilk kez kullanılan genlikler arası eğim yaklaşımı, PH teşhisinde sınıflandırıcı performansını artırmıştır.

Anahtar Kelimeler

• Ses telleri
• Parkinson Hastalığı
• özellikler arası eğim

Kaynakça

1. Ai, L., Wang, J. ve Wang, X., 2008. Multi-features fusion diagnosis of tremor based on artificial neural network and d–s evidence theory. Signal Processing, 88(12), 2927-2935.
2. Ali, A. M., Salim, F., Saeed, F., 2023. A Comprehensive Review on Parkinson's Disease Detection Using Machine Learning Techniques. IEEE Access, 11, 78945-78968. https://doi.org/10.1109/ACCESS.2023.3255672.
3. Ayhan, S. (2006). Determining the Factors Affecting Nurses' Intention to Quit in Turkey Using Ordered Logistic Regression Analysis. Master's Thesis, Institute of Science, Eskişehir Osmangazi University.
4. Baby, M.S., Saji, A.J., Kumar, C.S., 2017. Parkinson's disease classification using wavelet transform-based feature extraction of gait data. International Conference on Circuit Power and Computing Technologies (ICCPCT), Kollam India.
5. Balaji, R., Alam, M. N., et al., 2023. An ensemble classifier for assessing Parkinson’s disease severity using decision trees and gait analysis. Journal of Biomedical Informatics. https://doi.org/10.1016/j.jbi.2023.103647.
6. Bhattacharyya, S., Gupta, D., & Pradhan, R. (2011). Performance analysis of left/right hand movement classification from EEG signal by intelligent algorithms. In 2011 IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain (CCMB) (pp. 1-6). IEEE. https://doi.org/10.1109/CCMB.2011.5952133
7. Bishop, C. M. (2006). Pattern recognition and machine learning. Springer.
8. Bosch, A., Zisserman, A., & Munoz, X. (2007). Image classification using random forests and ferns. In 2007 IEEE 11th International Conference on Computer Vision (pp. 1-8). IEEE. https://doi.org/10.1109/ICCV.2007.4409066.

9. Chandrashekar, P., 2014. Mathematically modeling the GPE/STN neuronal cluster to account for Parkinsonian tremor and developing a novel method to accurately diagnose Parkinson's disease using speech measurements and an artificial neural network. Quantitative Biology, Neurons and Cognition, https://arxiv.org/abs/1405.1314
10. Chen, H.L., Huang, C. C., Yu, X.G., Xu, X., Sun, X., Wang, G., Wang, S.J., 2013. An efficient diagnosis system for detection of Parkinson's disease using fuzzy k-nearest neighbor approach. Expert Systems with Applications, 40(1), 263-271.
11. Coşkun, M., & Ayhan Istanbullu. (2012). Analysis of EEG Signals with FFT and Wavelet Transform. XIV. Academic Computing Conference, Usak, Turkey.
12. Ghanbari, A., Hossain, M. S., Saba, T., Yaqoob, I., 2023. Information Set-Based Decision Tree for Parkinson’s Disease Severity Assessment Using Multidimensional Gait Dataset. IEEE Access, 11, 4010-4022. https://doi.org/10.1109/ACCESS.2023.3238656.
13. Gonzalez, R. C., & Woods, R. E. (2002). Digital image processing (2nd ed.). Prentice Hall.
14. Guruler, H., 2017. A novel diagnosis system for Parkinson's disease using a complex-valued artificial neural network with k-means clustering feature weighting method. Neural Computing & Applications, 28(7), 1657.
15. Hamilton, D., List, A., Butler, T., Hogg, S., Cawley, M., 2016. Discrimination between parkinsonian syndrome and essential tremor using artificial neural network classification of quantified DaTSCAN data. Nuclear Medicine Communications, 27(12), 939-944.
16. Hariharan, M., Balasubramanian, A., Kumar, P. G. P., 2022. Early Detection of Parkinson’s Disease Using Fusion of Discrete Wavelet Transformation and Histograms of Oriented Gradients. Mathematics, 10(4218).
17. Hlavica J., Prauzek M., Peterek, T., Musilek, P., 2016. Assessment of Parkinson's disease progression using neural network and ANFIS models. Neural Network World, 26(2), 111-128.
18. Hoehn, M. M., Yahr, M. D., 1967. Parkinsonism: onset, progression, and mortality. Neurology, 17(5), 427-442. Jankovic, J., 2007. Parkinson’s disease: clinical features and diagnosis. J Neurol Neurosurg Psychiatry, 79(4), 368–376.
19. Kavanagh, E. R., Diamond, D., 2015. Fourier transform infrared spectroscopy for the diagnosis of Parkinson's disease. Analytical Chemistry, 87(14), 7081-7088. https://doi.org/10.1021/acs.analchem.5b01434.
20. Khan, M.M., Mendes, A., Zhang, P., Chalup, S., 2017. Evolving multi-dimensional wavelet neural networks for classification using Cartesian Genetic Programming. Neurocomputing, 247, 39-58.
21. Kwon, H., Kim, S., 2020. Machine learning techniques for diagnosis of Parkinson's disease: A review. Artificial Intelligence in Medicine, 105, 101853. https://doi.org/10.1016/j.artmed.2020.101853.
22. Langston, J.W., 2002. Parkinson’s disease: current and future challenges. Neurotoxicology, 23(4–5), 443–450. Mirelman, A., Maidan, I., Herman, T., 2011. Gait analysis in Parkinson's disease: A review. Journal of Neurology, 258(1), 90-99. https://doi.org/10.1007/s00415-010-5658-2.
23. Mitchel, T. “Machine Learning”. McGraw-Hill Science, 1997.
24. Muniz, A., Liu, W., Liu, H., Lyons, K.E., Pahwa, R., Nobre, F.F., Nadal, J., 2009. Assessment of the effects of subthalamic stimulation in Parkinson disease patients by artificial neural network. Annual International Conference of the IEEE Engineering in Medicine and Biology Society Engineering in Medicine and Biology Society, 5673-5676.
25. Muro, A., Orlik, P., 2018. Vocal characteristics in Parkinson's disease: A review of the literature. Journal of Voice, 32(6), 748-755. https://doi.org/10.1016/j.jvoice.2017.09.001.
26. Nilashi, M., Ibrahim, O., Ahani, A., 2016. Accuracy Improvement for Predicting Parkinson's Disease Progression.Scientific Reports, 6(34181). Doi:10.1038/Srep34181.
27. Overall, J. E., Gorham, D. R., 1962. The brief psychiatric rating scale. Psychological Reports, 10(3), 799-812. Ozcift, A., 2012. SVM Feature Selection Based Rotation Forest Ensemble Classifiers to Improve Computer-Aided Diagnosis of Parkinson Disease. Journal of Medical Systems, 36(4), 2141-2147.
28. Özdamar, K. (2009). Statistical Data Analysis with Software. Kaan Publishing, Eskisehir.
29. Peto, V., Jenkinson, C., Fitzpatrick, R., Greenhall, R., 1995. The development and validation of a short measure of functioning and well being for individuals with Parkinson's disease. Quality of Life Research, 4(3), 241-248. Polat, K. (2011). Classification of Parkinson’s disease using feature weighting method on the basis of fuzzy C-means clustering. International Journal of Systems Science, 43(4), 597–609. https://doi.org/10.1080/00207721.2011.581395.
30. S. Haykin and E. Frank, Neural Networks, 2nd ed. New Jersey: Prentice Hall, 1999.
31. Yılancıoğlu K. 2017. Vocal Cord Measure Based Ann Approach for Prediction of Parkınson's Diseases Status. SDU Journal of Health Science Institute / SDÜ Sağlık Bilimleri Enstitüsü Dergisi, 1, 139-142.
32. Yiğit, E.N.; Sönmez, E.; Söğüt, M.S.; Çakır, T.; Kurnaz, I.A. Validation of an In-Vitro Parkinson’s Disease Model for the Study of Neuroprotection. Proceedings 2018, 2, 1559. https://doi.org/10.3390/proceedings2251559.
33. Zayrit, S., Drissi, T. B., Ammoumou, A., Nsiri, B., 2020. Daubechies Wavelet Cepstral Coefficients for Parkinson's Disease Detection. Complex Systems, 29(3), 729-734. DOI: 10.25088/COMPLEXSYSTEMS.29.3.729.
34. https://archive.ics.uci.edu/ml/datasets/parkinsons+telemonitoring (21.01.2018).
35. Anonim, Parkinsons Data Set, https://archive.ics.uci.edu/ml/datasets/parkinsons (21.01.2018).