مهندسی مکانیک مدرس

مهندسی مکانیک مدرس

تشخیص پارکیسنون براساس الگوی حرکتی با استفاده از هوش مصنوعی

نویسندگان
دانشکده مهندسی مکانیک دانشگاه صنعتی خواجه نصیرالدین طوسی
چکیده
بیماری پارکینسون به‌عنوان یک اختلال عصبی پیش‌رونده شناخته می‌شود که منجر به اختلالات حرکتی می‌گردد. با توجه به اهمیت تشخیص زودهنگام و دقیق برای مدیریت مؤثر این بیماری، رویکردی نوین برای شناسایی و پیش‌بینی مرحله پیشرفت پارکینسون پیشنهاد شده است. در این مطالعه، سیگنال‌های راه‌رفتن با استفاده از الگوریتم تجزیه حالت ذاتی (EMD) پردازش گردیده و از شبکه عصبی عمیق ترکیبی CNN-LSTM به‌منظور استخراج ویژگی‌های زمانی بهره گرفته شده است. داده‌های حرکتی از طریق شانزده حسگر نیرو که در زیر پای چپ و راست ۹۳ فرد مبتلا به پارکینسون و ۷۳ فرد سالم نصب شده بود، گردآوری و پیش‌پردازش شده‌اند. سپس مؤلفه‌های فرکانسی ذاتی استخراج گردیده‌اند. برای ارزیابی عملکرد مدل، از دو رویکرد آموزشی استفاده شده است: نخست، تقسیم ساده داده‌ها به مجموعه‌های آموزش و آزمون؛ و دوم، روش اعتبارسنجی متقابل K-Fold. ویژگی‌های زمانی مرتبط با پیشرفت بیماری توسط ساختار CNN-LSTM استخراج گردیده‌اند. بر اساس نتایج به‌دست‌آمده، مدل مبتنی بر اعتبارسنجی متقابل با دقت 96.44٪ عملکرد بهتری نسبت به مدل ساده با دقت 84.27٪ ارائه داده است. این نتایج بر قابلیت بالای مدل پیشنهادی به‌عنوان ابزاری هوشمند، غیرتهاجمی و پشتیبان تصمیم‌گیری بالینی برای تشخیص و مرحله‌بندی بیماری پارکینسون دلالت دارند
کلیدواژه‌ها

موضوعات


عنوان مقاله English

Parkinson's Diagnosis Based on Gait Patterns Using Artificial Intelligence

نویسندگان English

Farzin Zeinaddini Meymand
Mahkame Sharbatdar
Mechanical Engineering Department, K. N. Toosi University of Technology
چکیده English

Parkinson’s disease is recognized as a progressive neurological disorder that leads to motor impairments. Due to the necessity of early and accurate diagnosis for effective disease management, a novel approach has been proposed for detecting and predicting the progression stages of Parkinson’s disease. In this study, gait signals were processed using Empirical Mode Decomposition (EMD), and temporal features were extracted by employing a hybrid CNN-LSTM deep neural network architecture. The gait data were collected using sixteen force sensors placed beneath the left and right feet of 93 individuals with Parkinson’s disease and 73 healthy controls. The signals were then preprocessed, and their intrinsic frequency components were extracted.

To evaluate model performance, two training strategies were applied: a conventional train-test split, and K-Fold cross-validation. Temporal dynamics associated with disease progression were effectively extracted through the CNN-LSTM model.

According to the results, the cross-validation-based model demonstrated superior accuracy of 96.44%, compared to 84.27% achieved by the simple split approach. These findings indicate that the proposed method can be reliably utilized as an intelligent, non-invasive clinical decision-support tool for the diagnosis and staging of Parkinson’s disease

کلیدواژه‌ها English

Parkinson
Gait Signal
Neural Network
Disease Diagnosis
1 - W. Poewe, K. Seppi, C. M. Tanner, G. M. Halliday, P. Brundin, J. Volkmann, A. Eleonore Schrag and A. E. Lang, "Parkinson disease," Nature Reviews Disease Primers, vol. 3, no. 1, pp. 1-21, 2017.
doi: 10.1038/nrdp.2017.13
2 - Y. Wu and S. Krishnan, "Statistical Analysis of Gait Rhythm in Patients With Parkinson's Disease," IEEE Xplore, vol. 18, no. 2, pp. 150-158, 2010. doi: 10.1109/TNSRE.2009.2033062
3 - W. Ferdous, K. B. Rezaul, J. H. Chris, S. Halgamuge and C. A. David, "Classification of Parkinson's Disease Gait Using Spatial-Temporal Gait Features," IEEE Xplore, vol. 23, no. 6, pp. 973-982, 2015. doi: 10.1109/TNSRE.2015.2404812
4 - I. E. Maachi, G.-A. B. and W. B. , "Deep 1D-Convnet for accurate Parkinson disease detection and severity prediction from gait," ELSEVIER, vol. 143, p. 113075, 2020.
doi: 10.1016/j.eswa.2019.113075
5 - P. P. A. K. H. A. and N. P. , "Classification of gait signals into different neurodegenerative diseases using statistical analysis and recurrence quantification analysis," ELSEVIER, vol. 117, pp. 1-7, 2018.
doi: 10.1016/j.patrec.2018.04.005
6 - N. Khoury, F. Attal, Y. Amirat, L. Oukhellou and S. Mohammed, "Data-Driven Based Approach to Aid Parkinson’s," Sensors, vol. 19, no. 2, p. 242, 2019. doi: 10.3390/s19020242
7 - B. E. B. D and B. R. , "Supervised machine learning based gait classification system for early detection and stage classification of Parkinson’s disease," ELSEVIER, vol. 49, p. 106494, 2020.
doi: 10.1016/j.asoc.2020.106494
8 - A. B. Oktay and A. Kocer, "Differential diagnosis of Parkinson and essential tremor with convolutional LSTM networks," ELSEVIER, vol. 56, p. 6, 2020. doi: 10.1016/j.bspc.2019.101683
9 - B. Vidya and S. P. , "Parkinson’s disease diagnosis and stage prediction based on gait signal analysis using EMD and CNN–LSTM network," ELSEVIER, vol. 114, p. 16, 2022.
doi: 10.1016/j.engappai.2022.105099
10 - G. Yogev, N. Giladi, C. Peretz, S. Springer, E. S. Simon and J. M. Hausdorff, "Dual tasking, gait rhythmicity, and Parkinson’s disease:," European Journal of Neuroscience, vol. 22, no. 5, pp. 1248-1256, 2005. doi: 10.1111/j.1460-9568.2005.04298.x
11- J. M. Hausdorff, J. Lowenthal, T. Herman, L. Gruendlinger, C. Peretz and N. Giladi, "Rhythmic auditory stimulation modulates gait variability," European Journal of Neuroscience, vol. 26, no. 8, pp. 2369-2375, 2007.
doi: 10.1111/j.1460-9568.2007.05810.x
12 - S. F. Toledo, N. Giladi, C. Peretz, T. Herman, L. Gruendlinger and J. M. Hausdorff, "Treadmill Walking as an External Pacemaker to Improve Gait," Movement Disorders, vol. 20, no. 9, pp. 1109-1114, 2005. doi: 10.1002/mds.20507
13 - N. Giladi, C. Peretz, T. Herman, L. Gruendlinger, J. M. Hausdorff and S. F. Toledo, "Effect of gait speed on gait rhythmicity in Parkinson's disease: variability of stride time and swing time respond differently," NeuroEngineering and Rehabilitation, vol. 2, no. 23, p. 7, 2005.
doi: 10.1186/1743-0003-2-23
14 - C. G. Goetz, W. Poewe, O. Rascol and G. T. Stebbins, "Movement Disorder Society Task Force report on the Hoehn and Yahr staging scale: Status and recommendations The Movement Disorder Society Task Force on rating scales for Parkinson's disease," Movement Disorders, vol. 19, no. 9, pp. 1020-1028, 2014.
doi: 10.1002/mds.20115
15 - L. J. Evers, J. H. Krijthe, M. J. Meinders, B. R. Bloem and T. M. Heskes, "Measuring Parkinson's disease over time: The real-world within-subject reliability of the MDS-UPDRS," Movement Disorders, vol. 36, no. 10, pp. 2444-2451, 2019.
doi: 10.1002/mds.27790
16 - D. Joshi, A. Khajuria and P. Joshi, "An automatic non-invasive method for Parkinson's disease classification," ELSEVIER, vol. 145, pp. 135-145, 2017. doi: 10.1016/j.cmpb.2017.04.007
17 - Vahid Mehdipour, "Mahsa Memarianfard," Modares Civil Engineering, vol. 18, no. 5, pp. 217-226, 2019.
doi: 20.1001.1.24766763.1397.18.5.3.3
18 - M. S. T. R. J. G. M. S. Mahsa Vaghefi, "Polymer Gear Fault Detection Based on Audio Signal and Wavelet Packet," Modares Mechanical Engineering, vol. 24, no. 6, pp. 351-362, 2024.
doi: 10.48311/MME.24.6.351