-تشخیص انجماد راه رفتن در بیماران مبتلا به پارکینسون با استفاده از حسگرهای پوشیدنی و یادگیری عمیق

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجوی کارشناسی ارشد مهندسی فناوری اطلاعات، دانشکده فنی و مهندسی، دانشگاه قم، قم، ایران. رایانامه: m.talebvand@stu.qom.ac.ir

2 استادیار گروه مهندسی کامپیوتر و فناوری اطلاعات، دانشکده فنی و مهندسی، دانشگاه قم، قم، ایران. رایانامه: lakizadeh@qom.ac.ir

3 استادیار گروه مهندسی کامپیوتر و فناوری اطلاعات، دانشکده فنی و مهندسی، دانشگاه قم، قم، ایران. رایانامه: f-fotouhi@qom.ac.ir

چکیده

انجماد راه رفتن (FOG) یکی از عوارض بیماری پارکینسون (PD) است که منجر به ناتوانی بیمار در انجام فعالیت­های حرکتی می‌شود. وقوع FOG باعث کاهش استقلال بیماران در انجام فعالیت­های روزمره و به طور کلی کاهش کیفیت زندگی آن­ها می­شود. استفاده از روش­های محاسباتی می­تواند با بررسی دقیق وضعیت FOG در بیماران، پشتیبانی غیردارویی و اطلاعات تکمیل­کننده­ای را در مورد بیماری به متخصصان مغز و اعصاب ارائه ­دهد و احتمال ارائه یک درمان موثرتر را افزایش ­دهد. این مقاله، روشی را برای تشخیص FOG بر اساس تکنیک­های یادگیری عمیق و پردازش سیگنال ارائه می­دهد. داده­های به کار رفته، مجموعه داده Daphnet می­باشد که از طریق سنسورهای پوشیدنی قرار گرفته بر روی بدن بیماران، جمع­آوری شده‌اند. روش پیشنهادی، پس از پالایش و پیش­پردازش داده‌ها، به تشخیص FOG از طریق ارائه یک معماری شبکه عصبی عمیق مبتنی بر شبکه­های حافظه کوتاه مدت دوطرفه (BDL-FOG) می­پردازد. نتایج تجربی نشان می­دهد که روش پیشنهادی به دلیل سازگاری بیشتر با داده­های سری زمانی توانسته است ضمن بهبود فرآیند تشخیص FOG به دقت بالاتری نسبت به بهترین روش­های موجود دست یابد. 

کلیدواژه‌ها


عنوان مقاله [English]

Detection freezing of gait (FOG) in Parkinson's patients using wearable sensors and deep learning

نویسندگان [English]

  • maryam talebvand 1
  • Amir Lakizadeh 2
  • Faranak Fotouhi 3
1 MSc. Student, Computer Engineering Department, University of Qom, Qom, Iran. Email: m.talebvand@stu.qom.ac.ir
2 Assistant Prof., Computer Engineering Department, University of Qom, Qom, Iran. Email: lakizadeh@qom.ac.ir
3 Assistant Prof., Computer Engineering Department, University of Qom, Qom, Iran. Email: f-fotouhi@qom.ac.ir
چکیده [English]

Freezing of the gait (FOG) is a complication of Parkinson's disease (PD) that leads to the patient's inability to perform motor activities. The occurrence of FOG reduces patients' independence in daily activities and generally reduces their quality of life. The use of computational methods can provide non-pharmacological support and complementary information about the disease to neurologists by carefully examining patients’ FOG status and increasing the likelihood of a more effective treatment. This paper presents a method for FOG detection based on deep learning and signal processing techniques. The data used for this paper is the Daphnet data collection, which is collected by the wearable sensors on the patient's body. The proposed methoddetects FOG by providing a deep neural network architecture based on two-way short-term memory networks (BDL-FOG). Experimental results show that the proposed method, due to its better compatibility with time-series data, has been able to improve the FOG detection process to achieve higher accuracy than the best available methods.

کلیدواژه‌ها [English]

  • Deep learning
  • Freezing of gait
  • Parkinson's disease
  • Recursive neural networks
  1. Aich, S., Pradhan, P. M., Park, J., Sethi, N., Vathsa, V. S. S., & Kim, H. C. (2018). A validation study of freezing of gait (FoG) detection and machine-learning-based FoG prediction using estimated gait characteristics with a wearable accelerometer. Sensors, 18(10), 3287. https://doi.org/10.1016/j.trb.2017.04.003

    1. J. Sannella, Constraint Satisfaction and Debugging for Camps, J., Sama, A., Martin, M., Rodriguez-Martin, D., Perez-Lopez, C., Arostegui, J. M. M., ... & Prats, A. (2018). Deep learning for freezing of gait detection in Parkinson’s disease patients in their homes using a waist-worn inertial measurement unit. Knowledge-Based Systems, 139, 119-131. https://doi.org/1035/j.trb.2007.33.67

    Xia, Y., Zhang, J., Ye, Q., Cheng, N., Lu, Y., & Zhang, D. (2018). Evaluation of deep convolutional neural networks for detection of freezing of gait in Parkinson’s disease patients. Biomedical Signal Processing and Control, 46, 221-230. https://doi.org/1015/j.trb.2015.7.102

    Post, B., Merkus, M. P., De Haan, R. J., Speelman, J. D., & CARPA Study Group. (2007). Prognostic factors for the progression of Parkinson's disease: a systematic review. Movement disorders, 22(13), 1839-1851. https://doi.org/1036/j.trb.2019.24.16

    Tanner, C. M., & Goldman, S. M. (1997). Epidemiology of Tourette syndrome. Neurologic clinics, 15(2), 395-402. https://doi.org/1079/j.trb.2008.7.35

    Bachlin, M., Plotnik, M., Roggen, D., Maidan, I., Hausdorff, J. M., Giladi, N., & Troster, G. (2009). Wearable assistant for Parkinson’s disease patients with the freezing of gait symptom. IEEE Transactions on Information Technology in Biomedicine, 14(2), 436-446. https://doi.org/1058/j.trb.2011.18.17

    De Lau, L. M., & Breteler, M. M. (2006). Epidemiology of Parkinson's disease. The Lancet Neurology, 5(6), 525-535. https://doi.org/1046/j.trb.2003.12.103

    Gandhi, S., & Plun-Favreau, H. (2017). Mutations and mechanism: how PINK1 may contribute to risk of sporadic Parkinson’s disease. Brain, 140(1), 2-5. https://doi.org/1029/j.trb.2009.12.35

    Giri, A., Mok, K. Y., Jansen, I., Sharma, M., Tesson, C., Mangone, G., ... & Díez-Fairen, M. (2017). Lack of evidence for a role of genetic variation in TMEM230 in the risk for Parkinson's disease in the Caucasian population. Neurobiology of aging, 50, 167-e11. https://doi.org/1073/j.trb.2002.13.69

    Jankovic, J. (2008). Parkinson’s disease: clinical features and diagnosis. Journal of neurology, neurosurgery & psychiatry, 79(4), 368-376. https://doi.org/1089/j.trb.2021.4.112

    Moore, O., Peretz, C., & Giladi, N. (2007). Freezing of gait affects quality of life of peoples with Parkinson's disease beyond its relationships with mobility and gait. Movement disorders: official journal of the Movement Disorder Society, 22(15), 2192-2195. https://doi.org/1038/j.trb.2023.9.35

    Moore, S. T., MacDougall, H. G., & Ondo, W. G. (2008). Ambulatory monitoring of freezing of gait in Parkinson's disease. Journal of neuroscience methods, 167(2), 340-348. https://doi.org/1097/j.trb.2009.11.23

    Polymeropoulos, M. H., Lavedan, C., Leroy, E., Ide, S. E., Dehejia, A., Dutra, A., ... & Stenroos, E. S. (1997). Mutation in the α-synuclein gene identified in families with Parkinson's disease. science, 276(5321), 2035-2047. https://doi.org/1054/j.trb.2006.31.122

    Han, J. H., Lee, W. J., Ahn, T. B., Jeon, B. S., & Park, K. S. (2003, September). Gait analysis for freezing detection in patients with movement disorder using three dimensional acceleration system. In Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat. No. 03CH37439) (Vol. 2, pp. 1863-1865). IEEE. https://doi.org/1027/j.trb.2021.23.20

    Schaafsma, J. D., Balash, Y., Gurevich, T., Bartels, A. L., Hausdorff, J. M., & Giladi, N. (2003). Characterization of freezing of gait subtypes and the response of each to levodopa in Parkinson's disease. European journal of neurology, 10(4), 391-398. https://doi.org/1066/j.trb.2009.4.97

    Tripoliti, E. E., Tzallas, A. T., Tsipouras, M. G., Rigas, G., Bougia, P., Leontiou, M., ... & Fotiadis, D. I. (2013). Automatic detection of freezing of gait events in patients with Parkinson's disease. Computer methods and programs in biomedicine, 110(1), 12-26. https://doi.org/1038/j.trb.2014.26.89

    Bächlin, M., Hausdorff, J. M., Roggen, D., Giladi, N., Plotnik, M., & Tröster, G. (2009, April). Online detection of freezing of gait in Parkinson's disease patients: a performance characterization. In Proceedings of the Fourth International Conference on Body Area Networks (pp. 1-8). https://doi.org/1066/j.trb.2007.25.62

    Niazmand, K., Tonn, K., Zhao, Y., Fietzek, U. M., Schroeteler, F., Ziegler, K., ... & Lueth, T. C. (2011, November). Freezing of Gait detection in Parkinson's disease using accelerometer based smart clothes. In 2011 IEEE Biomedical Circuits and Systems Conference (BioCAS) (pp. 201-204). IEEE. https://doi.org/1094/j.trb.2003.37.90

    Polat, K. (2019, April). Freezing of Gait (FoG) Detection Using Logistic Regression in Parkinson's Disease from Acceleration Signals. In 2019 Scientific Meeting on Electrical-Electronics & Biomedical Engineering and Computer Science (EBBT) (pp. 1-4). IEEE. https://doi.org/1068/j.trb.2009.27.134

    Handojoseno, A. A., Shine, J. M., Nguyen, T. N., Tran, Y., Lewis, S. J., & Nguyen, H. T. (2012, August). The detection of Freezing of Gait in Parkinson's disease patients using EEG signals based on Wavelet decomposition. In 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (pp. 69-72). IEEE. https://doi.org/1068/j.trb.2019.16.70

    Handojoseno, A. A., Shine, J. M., Nguyen, T. N., Tran, Y., Lewis, S. J., & Nguyen, H. T. (2012, August). The detection of Freezing of Gait in Parkinson's disease patients using EEG signals based on Wavelet decomposition. In 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (pp. 69-72). IEEE. https://doi.org/1073/j.trb.2002.33.122

    Carlos P´erez-Lo´pez Andreu Catal`a Berta Mestre Sheila Alcaine `Angels Bay`es Daniel Rodr´ıguez-Mart´ın, Albert Sam`a. Comparison of Features, Window Sizes and Classifiers in Detecting Freezing of Gait in Patients with Parkinson’s Disease Through a Waist-Worn Accelerometer, volume 288 of Frontiers in Artificial Intelligence and Applications. 2016. https://doi.org/1034/j.trb.2011.20.23

    Chollet, F. (2018). Deep Learning mit Python und Keras: Das Praxis-Handbuch vom Entwickler der Keras-Bibliothek. MITP-Verlags GmbH & Co. KG. https://doi.org/1054/j.trb.2017.9.18

CAPTCHA Image