تشخیص بیماری پارکینسون با استفاده از تحلیل سیگنال‌های الکتروانسفالوگرام مبتنی بر تبدیل والش هادامارد
محورهای موضوعی : پردازش چند رسانه ای، سیستمهای ارتباطی، سیستمهای هوشمند
یاسمین اعزازی
1
(
دانشجو کارشناسی ارشد، دانشکده مهندسی پزشکی، دانشگاه صنعتی سهند
)
پیوند قادریان
2
(
دانشکده مهندسی پزشکی، دانشگاه صنعتی سهند، تبریز، ایران
)
کلید واژه: بیماری پارکینسون, تکلیف یادگیری-تقویتی, تبدیل والش هادامارد, ماشین بردار پشتیبان, k نزدیک‌ترین همسایگی,
چکیده مقاله :
بیماری پارکینسون یکی از مهم‌ترین بیماری‌های سیستم عصبی است که به دلیل انحطاط نورون‌های دوپامینرژیک در جسم سیاه مغز رخ می‌دهد. از آنجایی‌که این بیماری درمان قطعی ندارد، بنابراین تشخیص کلینیکی و به‌موقع آن می‌تواند در کند نمودن سیر پیشرفت بیماری و ارائه راهکارهای کنترلی برای بهبود کیفیت زندگی بیماران نقش اساسی ایفا کند. در این مطالعه از تحلیل سیگنال الکتروانسفالوگرام به عنوان یک مشخصه کم‌هزینه، غیرتهاجمی و قابل اعتماد برای تشخیص استفاده شده است. روش پیشنهادی بر مبنای استخراج اطلاعات فرکانسی سیگنال به کمک تبدیل والش و محاسبه مجموعه‌ای از ویژگی‌‌ها مانند آنتروپی، معیارهای تکانش، ویژگی‌های آماری پایه و مرتبه بالا از ضرایبِ استخراج‌شده است. سپس، برای ارزیابی قدرت تفکیکی روش ارائه‌شده، از ماشین بردار پشتیبان و k نزدیک‌ترین همسایگی به منظور تفکیک بیماران از گروه سالم استفاده شده است. قابلیت تشخیص روش با استفاده از داده‌های الکتروانسفالوگرام 28 فرد سالم و 28 بیمار مبتلا به پارکینسون در حین انجام تکلیف یادگیری-تقویتی مورد ارزیابی قرار گرفته است. نتایج به‌دست‌آمده نشان داده است که روش پیشنهادی قادر است با استفاده از ویژگی آنتروپی، ماشین بردار پشتیبان و k نزدیک‌ترین همسایگی بیماری پارکینسون را به ترتیب با صحت بالای 99.95% و 99.98% تشخیص دهد.
Background: Parkinson's disease (PD) is one of the most important diseases of the nervous system that occurs due to the degeneration of dopaminergic neurons in the substantia nigra. Because of increasing prevalence rate, lack of specific treatment, and aggravation symptoms over time, PD detection is very important for the optimal control of patients' life. Therefore, the development of non-invasive, low-cost and reliable clinical diagnostic methods play an essential role to help doctors in diagnosis, slowing progressions of the disease and providing better control strategies to improve the quality of patients' life. Among diagnostic methods, recording and analyzing the electroencephalogram (EEG) signal as a low-cost and non-invasive approach has attracted a lot of attention.Method: EEG signal analysis in the time domain contains important information, but does not include the frequency information. Hence, this study is based on extracting new frequency features from the EEG signal using Walsh-Hadamard transform (WHT). WHT converts the signal from the time domain into the frequency domain and decompose it into orthogonal and rectangular waves. In this method, after calculating the Walsh coefficients, a set of features such as entropy, impulsive metrics, basic and high-order statistical features have been extracted from these coefficients. Subsequently, the discriminating capability of the presented method has been assessed using two classifiers namely support vector machine and k-nearest neighbor to classify PD patients from the healthy group.Results: The proposed method has been evaluated using the EEG signals of 28 healthy individuals and 28 patients with PD in two medication states (ON and OFF) during the reinforcement learning task. The obtained results have shown that this method is able to detect PD by using the entropy feature, support vector machine, and k nearest neighbor with acceptable accuracy of 99.95% and 99.98%, respectively. The good performance of entropy feature in comparison of other ones can be attributed to non-linear and non-stationary nature of EEG signal.Conclusion: In this study, a non-invasive, low-cost, and reliable method for PD detection using EEG signal analysis has been proposed. This algorithm is a multi-stage technique with a feature extraction approach based on WHT, entropy feature, and support vector machine and k-nearest neighbor classifiers. The reported results indicate that this method is effective in PD detection while being simple and easy, as well as being robust to the clinical factor of medication status.
[1] A. P. S. de Oliveira, M. A. de Santana, M. K. S. Andrade, J. C. Gomes, M. C. Rodrigues, and W. P. dos Santos, "Early diagnosis of Parkinson’s disease using EEG, machine learning and partial directed coherence," Research on Biomedical Engineering, vol. 36, pp. 311-331, 2020.
[2] X. Wang, Y. Zhang, C. Zhu, G. Li, J. Kang, F. Chen, and L. Yang, "The diagnostic value of SNpc using NM-MRI in Parkinson’s disease: meta-analysis," Neurological Sciences, vol. 40, pp. 2479-2489, 2019.
[3] A. M. Maitín, A. J. García-Tejedor, and J. P. R. Muñoz, "Machine Learning Approaches for Detecting Parkinson’s Disease from EEG Analysis: A Systematic Review," Applied Sciences, vol. 10, p. 8662, 2020.
[4] L. Luu, P. Pham, and T. Q. Le, "Feature Extraction and Electrophysiological Modeling in Personalized Deep Brain Structure Using Electroencephalography Signal," in International Conference on the Development of Biomedical Engineering in Vietnam, 2018, pp. 551-556.
[5] J. Jankovic, "Parkinson’s disease: clinical features and diagnosis," Journal of neurology, neurosurgery & psychiatry, vol. 79, pp. 368-376, 2008.
[6] O.-B. Tysnes and A. Storstein, "Epidemiology of Parkinson’s disease," Journal of Neural Transmission, vol. 124, pp. 901-905, 2017.
[7] W. Poewe, K. Seppi, C. M. Tanner, G. M. Halliday, P. Brundin, J. Volkmann, A.-E. Schrag, and A. E. Lang, "Parkinson disease," Nature reviews Disease primers, vol. 3, pp. 1-21, 2017.
[8] S. Bhat, U. R. Acharya, Y. Hagiwara, N. Dadmehr, and H. Adeli, "Parkinson's disease: Cause factors, measurable indicators, and early diagnosis," Computers in biology and medicine, vol. 102, pp. 234-241, 2018.
[9] H. Railo, I. Suuronen, V. Kaasinen, M. Murtojarvi, T. Pahikkala, and A. Airola, "Resting state EEG as a biomarker of Parkinson's disease: Influence of measurement conditions," BioRxiv, 2020.
[10] R. Yuvaraj, M. Murugappan, N. M. Ibrahim, K. Sundaraj, M. I. Omar, K. Mohamad, and R. Palaniappan, "Optimal set of EEG features for emotional state classification and trajectory visualization in Parkinson's disease," International Journal of Psychophysiology, vol. 94, pp. 482-495, 2014.
[11] R. Yuvaraj and M. Murugappan, "Hemispheric asymmetry non-linear analysis of EEG during emotional responses from idiopathic Parkinson’s disease patients," Cognitive neurodynamics, vol. 10, pp. 225-234, 2016.
[12] A. Saikia, V. Majhi, M. Hussain, A. R. Barua, and S. Paul, "Performance Analysis of various Neural Network functions for Parkinson’s disease Classification using EEG and EMG," EXECUTIVE EDITOR, vol. 11, p. 541, 2020.
[13] M. Subathra, M. A. Mohammed, M. S. Maashi, B. Garcia-Zapirain, N. Sairamya, and S. T. George, "Detection of focal and non-focal electroencephalogram signals using fast Walsh-Hadamard transform and artificial neural network," Sensors, vol. 20, p. 4952, 2020.
[14] V. K. Dave, V. Vakharia, and S. Singh, "Ball Bearing Fault Diagnosis Using Mutual Information and Walsh–Hadamard Transform," in Reliability, Safety and Hazard Assessment for Risk-Based Technologies, ed: Springer, 2020, pp. 607-616.
[15] D. Sawant, V. Padwal, J. Joshi, T. Keluskar, R. Lalwani, T. Sharma, and R. Daruwala, "Classification of Motor Imagery EEG Signals using MEMD, CSP, Entropy and Walsh Hadamard Transform," in 2019 IEEE Bombay Section Signature Conference (IBSSC), 2019, pp. 1-6.
[16] D. R. Brown, S. P. Richardson, and J. F. Cavanagh, "An EEG marker of reward processing is diminished in Parkinson’s disease," Brain research, vol. 1727, p. 146541, 2020.
[17] V. Dave and V. Vakharia, "Fault Diagnosis of Ball Bearing Using Walsh–Hadamard Transform and Random Tree Classifier," Reliability and Risk Assessment in Engineering, p. 373, 2020.
[18] N. Ahmed and K. R. Rao, Orthogonal transforms for digital signal processing: Springer Science & Business Media, 2012.
[19] X. Xiang, J. Zhou, X. An, B. Peng, and J. Yang, "Fault diagnosis based on Walsh transform and support vector machine," Mechanical Systems and Signal Processing, vol. 22, pp. 1685-1693, 2008.
[20] S. Sareen, S. K. Sood, and S. K. Gupta, "An automatic prediction of epileptic seizures using cloud computing and wireless sensor networks," Journal of medical systems, vol. 40, pp. 1-18, 2016.
[21] A. Shoeibi, N. Ghassemi, R. Alizadehsani, M. Rouhani, H. Hosseini-Nejad, A. Khosravi, M. Panahiazar, and S. Nahavandi, "A comprehensive comparison of handcrafted features and convolutional autoencoders for epileptic seizures detection in EEG signals," Expert Systems with Applications, vol. 163, p. 113788, 2021.
[22] D. A. Pisner and D. M. Schnyer, "Support vector machine," in Machine Learning, ed: Elsevier, 2020, pp. 101-121.
[23] S. Abe, Support vector machines for pattern classification vol. 2: Springer, 2005.
[24] P. Cunningham and S. J. Delany, "k-Nearest neighbour classifiers: (with Python examples)," arXiv preprint arXiv, 2020, 2004/04523.
[25] A. Tharwat, "Classification assessment methods," Applied Computing and Informatics, 2020.
[26] S. L. Oh, Y. Hagiwara, U. Raghavendra, R. Yuvaraj, N. Arunkumar, M. Murugappan, and U. R. Acharya, "A deep learning approach for Parkinson’s disease diagnosis from EEG signals," Neural Computing and Applications, pp. 1-7, 2018.
[27] S. K. Khare, V. Bajaj, and U. R. Acharya, "PDCNNet: An automatic framework for the detection of Parkinson’s Disease using EEG signals," IEEE Sensors Journal, 2021.
[28] R. Yuvaraj, U. R. Acharya, and Y. Hagiwara, "A novel Parkinson’s Disease Diagnosis Index using higher-order spectra features in EEG signals," Neural Computing and Applications, vol. 30, pp. 1225-1235, 2018.
_||_