Automatic Diagnosis of Parkinson's Disease Using Principal Component Analysis Methods

Abstract

Parkinson's disease is a sneaky brain disorder that progresses very slowly. The diagnostic methods of this disease include the analysis of individual voices. The earliest detection of Parkinson's by voice analysis is made possible by various methods. In this study, the results obtained from the application of Tunable Q-factor Wavelet Transformation (TQWT) method to the recorded audio signals of 188 Parkinson's patients and 64 healthy individuals were used. The principal component analysis (PCA) and its types (kernel PCA (KPCA) and Probabilistic PCA (PPCA)) which are dimension reduction methods have been applied to the TQWT features. Afterwards, k-fold cross validation method was applied to the new data groups and the training-test data were obtained. In the next step, the data were separately classified by random forest (RF) algorithm to investigate the effectiveness of the dimension reduction methods and the results were also interpreted by statistical criteria. In terms of classification results, OTBA was the most successful in size reduction methods with 87.56% accuracy rate. In addition, as a result of this method, ROC and PRC area values reached a band of about 0.95, proving that patient and healthy class decomposition approached perfection. The performance results of this study, which is suitable for real-life applications, were compared with the single study in the literature in which the same data was used, and this study showed that higher statistical ratios were obtained in comparison to the other study. Moreover, the high number of people in whom the data was recorded compared to other studies in the literature increases the importance of the study in this field. 

Keywords

• Parkinson's disease,dimension reduction methods,TQWT,PCA

Temel Bileşen Analizi Yöntemleri Kullanarak Parkinson Hastalığının Otomatik Teşhisi

Öz

Parkinson rahatsızlığı çok yavaş ilerleyen sinsi bir beyin hastalığıdır. Bu hastalığın teşhis yöntemleri arasında kişilere ait seslerin analizi de bulunmaktadır. Ses analizi ile Parkinson’nun en erken tespiti kullanılan çeşitli yöntemler sayesinde mümkün olmaktadır. Bu çalışma kapsamında 188 Parkinson hastası ve 64 sağlıklı kişiye ait kaydedilmiş ses sinyallerine Ayarlanabilir Q-faktör Dalgacık Dönüşümü (AQDD) metodu uygulanması sonucunda elde edilen özellikler kullanılmıştır. AQDD özelliklerine, boyut indirgeme yöntemlerinden temel bileşen analizi (TBA) ve bunun çeşitlerinden olan kernel TBA (KTBA) ile olasılıksal TBA (OTBA) uygulanmıştır. Daha sonra boyutları indirgenen yeni veri gruplarına ayrı ayrı k-kat çapraz doğrulama yöntemi uygulanarak eğitim-test verileri elde edilmiştir. Sonraki aşamada ise, boyut indirgeme yöntemlerinin etkinliğinin araştırılması için veriler rastgele orman (RO) algoritması ile ayrı ayrı sınıflandırılmış ve elde edilen sonuçlar ayrıca istatistiksel ölçütlerle yorumlanmıştır. Sınıflandırma sonuçları açısından boyut azaltma yöntemleri içerisinde en başarılısı %87.56 doğruluk oranı ile OTBA olmuştur. Ayrıca bu yöntem sonucunda ROC ve PRC alan değerleri yaklaşık 0.95 bandına ulaşarak hasta ve sağlıklı sınıf ayrışımının mükemmele yaklaştığını kanıtlamıştır. Gerçek yaşam uygulamalarına uygun olan bu çalışmanın performans sonuçları, aynı verinin kullanıldığı literatürdeki tek çalışma ile kıyaslanmış ve bu çalışmada diğer çalışmaya nazaran daha yüksek istatistiksel oranların elde edildiği görülmüştür. Ayrıca verilerin kaydedildiği kişi sayısının literatürdeki diğer çalışmalara göre yüksek oluşu çalışmanın bu alandaki önemini arttırmaktadır. 

Anahtar Kelimeler

• Parkinson hastalığı,boyut indirgeme yöntemleri,AQDD,TBA

Kaynakça

1. K. Rana. (2014). Parkinson Hastalığı [Online]. Available:http://www.noroloji.org.tr/TNDData/Uploads/files/ parkinson%20hastal%C4%B1%C4%9F%C4%B1.pdf.
2. S. Özekmekçi, H. Apaydın, S. Oğuz, & İ. Zileli. (2013). Parkinson Hastalığı Hasta ve Yakınları İçin El Kitabı. İstanbul, Turkey: Bayçınar Tıbbi Yayıncılık ve Reklam Hiz. Tic. Ltd. Şti, p. 98.
3. J. W. Langston. (2002). Parkinson’s disease: current and future challenges. Neurotoxicology, vol. 23, no. 4-5, pp. 443-450.
4. J. Parkinso. (1817). An essay on the shaking palsy (Printed by Whittingham and Rowland for Sherwood, Neely, and Jones). ed: London.
5. J. Jankovic. (2008). Parkinson’s disease: clinical features and diagnosis. Journal of neurology, neurosurgery & psychiatry, vol. 79, no. 4, pp. 368-376.
6. H. Gümüş, Z. Akpınar, & O. Demir. (2013). Erken evre Parkinson hastalığında motor olmayan semptomların değerlendirilmesi. Türk Nöroloji Dergisi, vol. 19, no. 3, pp. 97-103.
7. Y. Akgün & S. Peker. (2010). Tremor tedavisinde cerrahi girişimler. Acıbadem Üniversitesi Sağlık Bilimleri Dergisi, vol. 1 (3), no. 3, pp. 123-127.
8. B. Harel, M. Cannizzaro, & P. J. Snyder. (2004). Variability in fundamental frequency during speech in prodromal and incipient Parkinson's disease: A longitudinal case study. Brain and cognition, vol. 56, no. 1, pp. 24-29.

9. A. Tsanas, M. A. Little, P. E. McSharry, & L. O. Ramig. (2010). Accurate telemonitoring of Parkinson's disease progression by noninvasive speech tests. IEEE transactions on Biomedical Engineering, vol. 57, no. 4, pp. 884-893.
10. C. O. Sakar & O. Kursun. (2010). Telediagnosis of Parkinson’s disease using measurements of dysphonia. Journal of medical systems, vol. 34, no. 4, pp. 591-599.
11. H. Gürüler. (2017). A novel diagnosis system for Parkinson’s disease using complex-valued artificial neural network with k-means clustering feature weighting method. Neural Computing and Applications, vol. 28, no. 7, pp. 1657-1666.
12. M. A. Little, P. E. McSharry, E. J. Hunter, J. Spielman, & L. O. Ramig. (2009). Suitability of dysphonia measurements for telemonitoring of Parkinson's disease. IEEE transactions on biomedical engineering, vol. 56, no. 4, pp. 1015-1022.
13. M. Peker, B. Sen, & D. Delen. (2015). Computer-aided diagnosis of Parkinson’s disease using complex-valued neural networks and mRMR feature selection algorithm. Journal of healthcare engineering, vol. 6, no. 3, pp. 281-302.
14. R. Das. (2010). A comparison of multiple classification methods for diagnosis of Parkinson disease. Expert Systems with Applications, vol. 37, no. 2, pp. 1568-1572.
15. F. Åström & R. Koker. (2011). A parallel neural network approach to prediction of Parkinson’s Disease. Expert systems with applications, vol. 38, no. 10, pp. 12470-12474.
16. B. E. Sakar ve ark. (2013). Collection and analysis of a Parkinson speech dataset with multiple types of sound recordings. IEEE Journal of Biomedical and Health Informatics, vol. 17, no. 4, pp. 828-834.
17. H.-L. Chen ve ark. (2013). An efficient diagnosis system for detection of Parkinson’s disease using fuzzy k-nearest neighbor approach. Expert systems with applications, vol. 40, no. 1, pp. 263-271.
18. W.-L. Zuo, Z.-Y. Wang, T. Liu, & H.-L. Chen. (2013). Effective detection of Parkinson's disease using an adaptive fuzzy k-nearest neighbor approach. Biomedical Signal Processing and Control, vol. 8, no. 4, pp. 364-373.
19. B. E. Sakar, G. Serbes, & C. O. Sakar. (2017). Analyzing the effectiveness of vocal features in early telediagnosis of Parkinson's disease. PloS one, vol. 12, no. 8, p. e0182428.
20. S. Lahmiri, D. A. Dawson, & A. Shmuel. (2018). Performance of machine learning methods in diagnosing Parkinson’s disease based on dysphonia measures. Biomedical Engineering Letters, vol. 8, no. 1, pp. 29-39.
21. C. O. Sakar ve ark. (2019). A comparative analysis of speech signal processing algorithms for Parkinson’s disease classification and the use of the tunable Q-factor wavelet transform. Applied Soft Computing, vol. 74, pp. 255-263.
22. Ö. Eskidere. (2012). A Comparison Of Feature Selection Methods For Diagnosis Of Parkinson’s Disease From Vocal Measurements. Sigma, vol. 30, pp. 402-414.
23. I. W. Selesnick. (2011). Wavelet transform with tunable Q-factor. IEEE transactions on signal processing, vol. 59, no. 8, pp. 3560-3575.
24. F. Bulut. (2017). Different Mathematical Models for Entropy in Information Theory. Bilge International Journal of Science and Technology Research, vol. 1 (2), pp. 167-174.
25. R. M. Gray (1990). Entropy and information. Entropy and information theory: Springer, pp. 21-55.
26. S. Aydın, H. M. Saraoğlu, & S. Kara. (2009). Log energy entropy-based EEG classification with multilayer neural networks in seizure. Annals of biomedical engineering, vol. 37, no. 12, p. 2626.
27. J. F. Kaiser. (1990). On a simple algorithm to calculate the'energy'of a signal. in International conference on acoustics, speech, and signal processing: IEEE, pp. 381-384.
28. J. F. Kaiser. (1993). Some useful properties of Teager's energy operators. in 1993 IEEE international conference on acoustics, speech, and signal processing, vol. 3: IEEE, pp. 149-152.
29. P. Maragos, J. F. Kaiser, & T. F. Quatieri. (1993). On amplitude and frequency demodulation using energy operators. IEEE Transactions on signal processing, vol. 41, no. 4, pp. 1532-1550.
30. S. Solnik, P. Rider, K. Steinweg, P. DeVita, & T. Hortobágyi. (2010). Teager–Kaiser energy operator signal conditioning improves EMG onset detection. European journal of applied physiology, vol. 110, no. 3, pp. 489-498.
31. R. B. Randall & W. A. Smith. (2017). Application of the Teager Kaiser energy operator to machine diagnostics. in Tenth Dst Group International Conference on Health and Usage Monitoring Systems.
32. J. Luo & G. Oubong. (2009). A Comparison of SIFT, PCA-SIFT and SURF International Journal of Image Processing, vol. 3(4), pp. 143-152.
33. L. I. Smith. (2002). A tutorial on principal components analysis. Technical Report OUCS-2002-12, pp. 1-26.
34. H. Hoffmann. (2007). Kernel PCA for novelty detection. Pattern recognition, vol. 40, pp. 863-874.
35. V. Tsatsishvili, I. Burunat, F. Cong, P. Toiviainen, V. Alluri, & T. Ristaniemi. (2018). On application of kernel PCA for generating stimulus features for fMRI during continuous music listening. Journal of neuroscience methods, vol. 303, pp. 1-6.
36. K. R. Müller, S. Mika, G. Rätsch, K. Tsuda, & B. Schölkopf. (2001). An introduction to kernel-based learning algorithms. IEEE transactions on neural networks, vol. 12(2).
37. R. Zhang, W. Wang, & Y. Ma. (2010). Approximations of the standard principal components analysis and kernel PCA. Expert Systems with Applications, vol. 37(9), pp. 6531-6537.
38. S. M. S. Shah, S. Batool, I. Khan, M. U. Ashraf, S. H. Abbas, & S. A. Hussain. (2017). Feature extraction through parallel Probabilistic Principal Component Analysis for heart disease diagnosis. Physica A: Statistical Mechanics and its Applications, vol. 482, pp. 796-807.
39. M. E. Tipping & C. M. Bishop. (1999). Probabilistic principal component analysis. Journal of the Royal Statistical Society: Series B (Statistical Methodology), vol. 61(3), pp. 611-622.
40. L. Breiman. (2001). Random forests. Machine learning, vol. 45, no. 1, pp. 5-32.
41. I. H. Witten, E. Frank, L. E. Trigg, M. A. Hall, G. Holmes, & S. J. Cunningham. (1999). Weka: Practical machine learning tools and techniques with Java implementations.
42. Y. Ma, L. Guo, & B. Cukic. (2006). A statistical framework for the prediction of fault-proneness. Advances in Machine Learning Application in Software Engineering, Idea Group Inc, pp. 237-265.
43. D. M. Powers. (2011). Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation.
44. N. Nicolov. (2012). Machine Learning with Applications in Categorization, Popularity and Sequence Labeling: 57th and 58nd slides. [Online]. Available: http://www.slideshare.net/Nicolas_Nicolov/machine-learning-14528792.
45. Ş. Yücelbaş, C. Yücelbaş, G. Tezel, S. Özşen, & Ş. Yosunkaya. (2018). Automatic sleep staging based on SVD, VMD, HHT and morphological features of single-lead ECG signal. Expert Systems with Applications, vol. 102, pp. 193-206.
46. T. Saito & M. Rehmsmeier. (2015). The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PloS one, vol. 10, no. 3, p. e0118432.
47. T. J. Wroge, Y. Özkanca, C. Demiroglu, D. Si, D. C. Atkins, & R. H. Ghomi. (2018). Parkinson’s Disease Diagnosis Using Machine Learning and Voice. in 2018 IEEE Signal Processing in Medicine and Biology Symposium (SPMB): IEEE, pp. 1-7.