Machine Learning-Based Real-Time Tremor Level Detection for Parkinson Disease

Öz

Parkinson's disease is one of the neurodegenerative diseases that affects neurons in the brain and causes motor functions to deteriorate. The most common symptom of this disease is involuntary tremor, especially in the hands and fingers, when the patient is in a resting position. In this study, a machine learning-based embedded system is proposed that can detect tremor and determine its level according to sensor data obtained from fingers. Subsequently, tremor data was obtained using Arduino UNO and MPU-6050 sensor, machine learning models were trained, and autonomous decision making have been performed. The study aims to evaluate tremor autonomously in real time, report it to the specialist, and assist in diagnosis and treatment. Unlike the studies in the literature, in this study, tremor signals were processed in real time with machine learning techniques instead of rule-based decision making. Tremor signals are digitally generated using sensors via the Internet of Things. Since mobility is crucial in the healthcare industry, the data was transferred wirelessly to the local server and evaluated for ease of use. As a result of this study, 96% accuracy was achieved using artificial neural networks in tremor level detection. By increasing the amount of data and the number of participants, the potential for the system to be developed and used in clinics is quite high.

Anahtar Kelimeler

• Machine Learning
• Internet of Things
• Parkinson Disease
• Real-Time Diagnostics
• Tremor Detection

Parkinson Hastalığı için Makine Öğrenimi Tabanlı Gerçek Zamanlı Tremor Seviyesi Saptanması

Öz

Parkinson hastalığı beyindeki nöronları etkileyerek motor fonksiyonlarının bozulmasına neden olan nörodejeneratif hastalıklardan biridir. Bu hastalığın bilinen en yaygın belirtisi hastanın dinlenir pozisyondayken özellikle el ve parmaklardaki istemsiz tremordur. Bu çalışmada el parmaklarından elde edilen sensör verilerine göre tremoru tespit ederek, seviyesini saptayabilen makine öğrenmesi tabanlı bir gömülü sistem önerilmektedir. Arduino UNO ve MPU-6050 sensörü kullanılarak tremor verileri elde edildikten sonra makine öğrenmesi modelleri eğitilerek otonom karar verme işlemi yapılmıştır. Çalışmanın amacı tremoru gerçek zamanlı, otonom olarak değerlendirebilmek, uzmana raporlama yapmak, teşhis ve tedavi işlemine yardımcı olmaktır. Literatürde bulunan çalışmalardan farklı olarak bu çalışmada kural tabanlı karar vermek yerine tremor sinyalleri gerçek zamanlı olarak makine öğrenmesi teknikleri ile işlenmiştir. Tremor sinyalleri nesnelerin interneti aracılığıyla sensör kullanılarak sayısal olarak üretilmiştir. Sağlık sektöründe mobiliteye önem verildiği için kullanım kolaylığı sağlaması amacıyla veriler kablosuz olarak yerel sunucuya aktarılarak değerlendirme yapılmıştır. Çalışma sonucunda yapılan deneyler ile tremor seviye tespitinde yapay sinir ağları kullanılarak %96 başarı elde edilmiştir. Veri miktarı ve katılımcı sayısının arttırılmasıyla birlikte sistemin geliştirilme ve kliniklerde kullanılma potansiyeli oldukça yüksektir.

Anahtar Kelimeler

• Makine Öğrenmesi
• Nesnelerin İnterneti
• Parkinson Hastalığı
• Gerçek Zamanlı Teşhis
• Tremor Tespiti

Kaynakça

1. Simon DK, Tanner CM, Brundin P. Parkinson disease epidemiology, pathology, genetics, and pathophysiology. Clin Geriatr Med 2020;36(1):1-12. doi:10.1016/j.cger.2019.08.002.
2. Poewe W, Seppi K, Tanner C, Halliday G, Brundin P, Volkmann J, et al. Parkinson disease. Nat Rev Dis Primers 2017;3:17013. doi:10.1038/nrdp.2017.13.
3. Abdo WF, Van De Warrenburg B, Burn D, Quinn NP, Bloem BR. The clinical approach to movement disorders. Nat Rev Neurol 2010;6(1):29–37. doi:10.1038/nrneurol.2009.196.
4. Helmich RC, Hallett M, Deuschl G, Toni I, Bloem BR. Cerebral causes and consequences of parkinsonian resting tremor: a tale of two circuits?. Brain 2012;135(11):3206–26. doi:10.1093/brain/aws023.
5. Gupta DK, Marano M, Zweber C, Boyd JT, Kuo SH. Prevalence and Relationship of Rest Tremor and Action Tremor in Parkinson's Disease. Tremor Other Hyperkinet Mov (N Y) 2020;10:58. doi:10.5334/tohm.552.
6. Zhao J, Fu Y, Xiao Y, Dong Y, Wang X, Lin L. A naturally integrated smart textile for wearable electronics applications. Adv Mater Technol 2020;5(1):1900781. doi:10.1002/admt.201900781.
7. Marc ME, Ignacio G, Raúl FG. A smart textile system to detect urine leakage. IEEE Sens J 2021;21(23):26234–42. doi:10.1109/JSEN.2021.3080824.
8. Nia MB, Kazemi MA, Valmohammadi C, Abbaspour G. Wearable IoT intelligent recommender framework for a smarter healthcare approach. Libr Hi Tech 2023;41(4):1238-61. doi:10.1108/LHT-04-2021-0151.

9. Devi DH, Duraisamy K, Armghan A, Alsharari M, Aliqab K, Sorathiya V, et al. 5G Technology in Healthcare and Wearable Devices: A Review. Sensors 2023;23:2519. doi:10.3390/s23052519.
10. Fernández-Caramés TM, Fraga-Lamas P. Towards the internet of smart clothing: A review on iot wearables and garments for creating intelligent connected e-textiles. Electronics 2018;7(12):405. doi:10.3390/electronics7120405.
11. Simegnaw AA, Malengier B, Rotich G, Tadesse MG, Van Langenhove L. Review on the integration of microelectronics for e-textile. Materials 2021;14(17):5113. doi:10.3390/ma14175113.
12. Iskanderov J, Güvensan MA. Akıllı telefon ve giyilebilir cihazlarla aktivite tanıma: Klasik yaklaşımlar, yeni çözümler. Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi 2019;25(2):223-39. doi:10.5505/pajes.2018.84758.
13. Serçek S, Korkmaz M. Sporda giyilebilir teknoloji üzerine sistematik bir literatür taraması. Uluslararası Güncel Eğitim Araştırmaları Dergisi 2023;9(1):77-92.
14. Himi ST, Monalisa NT, Whaiduzzaman MD, Barros A, Uddin MS. MedAi: A Smartwatch-Based Application Framework for the Prediction of Common Diseases Using Machine Learning. IEEE Access 2023;11:12342-59. doi:10.1109/ACCESS.2023.3236002.
15. Alassafi MO, Jarrah M, Alotaibi R. Time series predicting of COVID-19 based on deep learning. Neurocomputing 2022;468:335-44. doi:10.1016/j.neucom.2021.10.035.
16. Islam MN, Raiyan KR, Mitra S, Mannan MR, Tasnim T, Putul AO, et al. Predictis: an IoT and machine learning-based system to predict risk level of cardio-vascular diseases. BMC Health Serv Res 2023;23(1):171. doi:10.1186/s12913-023-09104-4.
17. Çiftçi B, Zeynep Ş, Akkaş M. Nesnelerin interneti tabanlı kablosuz taşınabilir ekg cihazı. Avrupa Bilim ve Teknoloji Dergisi 2021;26:91–5. doi:10.31590/ejosat.949795.
18. Oğuz FE, Bolat ED. Nesnelerin interneti tabanlı akıllı uzaktan hasta sağlık takip ve uyarı sistemi. Kocaeli Üniversitesi Fen Bilimleri Dergisi 2021;4(1):14–21.
19. Chang CS, Wu TH, Wu YC, Han CC. Bluetooth-Based Healthcare Information and Medical Resource Management System. Sensors 2023;23(12):5389. doi:10.3390/s23125389.
20. Tiwari S, Jain A, Sapra V, Koundal D, Alenezi F, Polat K, et al. A smart decision support system to diagnose arrhythymia using ensembled ConvNet and ConvNet-LSTM model. Expert Syst Appl 2023;213. doi:10.1016/j.eswa.2022.118933.
21. Nagarajan SM, Deverajan GG, Chatterjee P, Alnumay W, Ghosh U. Effective task scheduling algorithm with deep learning for internet of health things (ioht) in sustainable smart cities. Sustain Cities Soc 2021;71:102945. doi:10.1016/j.scs.2021.102945.
22. Bolhasani H, Mohseni M, Rahmani AM. Deep learning applications for iot in health care: A systematic review. Inform Med Unlocked 2021;23:100550. doi:10.1016/j.imu.2021.100550.
23. Dusarlapudi K, Raju KN, Narayanam VSK. COVID-19 patient breath monitoring and assessment with MEMS accelerometerbased DAQ-a Machine Learning Approach. NVEO 2021;8(5):1567–75.
24. Can Ö, Sezer E, Bursa O, Ünalır MO. Nesnelerin interneti ve güvenli bir sağlık bilgi modeli önerisi. In: 4th International Symposium on Innovative Technologies in Engineering and Science (ISITES2016). 2016.
25. Chatterjee P, Cymberknop LJ, Armentano RL. Iot-based decision support system for intelligent healthcare—applied to cardiovascular diseases. In: 2017 7th International Conference on Communication Systems and Network Technologies (CSNT). 2017, p. 362–6. doi:10.1109/CSNT.2017.8418567.
26. Aktaş F, Çeken C, Erdemli YE. Biyomedikal uygulamaları için nesnelerin interneti tabanlı veri toplama ve analiz sistemi. Tıp teknolojileri ulusal kongresi 2014;25(27):299–302.
27. Raza M, Awais M, Singh N, Imran M, Hussain S. Intelligent IoT framework for indoor healthcare monitoring of Parkinson’s disease patient. IEEE J Sel Areas Commun 2020;39(2):593-602. doi:10.1109/JSAC.2020.3021571.
28. AlZubi AA, Alarifi A, Al-Maitah M. Deep brain simulation wearable IoT sensor device based Parkinson brain disorder detection using heuristic tubu optimized sequence modular neural network. Measurement 2020;161:107887. doi:10.1016/j.measurement.2020.107887.
29. Zhao Y, Liu Y, Lu W, Li J, Shan P, Lian C, et al. Intelligent IoT Anklets for Monitoring the Assessment of Parkinson’s Diseases. IEEE Sens J 2023. doi:10.1109/JSEN.2023.3331277.
30. Saleh S, Cherradi B, Laghmati S, El Gannour O, Hamida S, Bouattane O. Healthcare embedded system for predicting Parkinson's Disease based on AI of things. In: 2023 3rd international conference on innovative research in applied science, engineering and technology (IRASET). IEEE; 2023, p. 1-7. doi:10.1109/IRASET57153.2023.10153040.
31. Belyaev M, Murugappan M, Velichko A, Korzun D. Entropy-based machine learning model for diagnosis and monitoring of Parkinson's Disease in smart IoT environment. arXiv preprint arXiv:2309.07134 2023. doi:10.48550/arXiv.2309.07134.
32. Poungponsri S, Yu XH. An adaptive filtering approach for electrocardiogram (ecg) signal noise reduction using neural networks. Neurocomputing 2013;117:206–13. doi:10.1016/j.neucom.2013.02.010.
33. Shpektorov A, Van Tuan P. Comparison between methods for construction of the kalman filter for inertial measurement module. In: 2017 XX IEEE International Conference on Soft Computing and Measurements (SCM). 2017, p. 67–9. doi:10.1109/SCM.2017.7970497.
34. Alfian RI, Ma’arif A, Sunardi S. Noise reduction in the accelerometer and gyroscope sensor with the kalman filter algorithm. Journal of Robotics and Control (JRC) 2021;2(3):180–9. doi:10.18196/jrc.2375.
35. Heijmans M, Habets J, Kuijf M, Kubben P, Herff C. Evaluation of parkinson’s disease at home: Predicting tremor from wearable sensors. In: 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). 2019, p. 584–7. doi:10.1109/EMBC.2019.8857717.
36. Fraiwan L, Khnouf R, Mashagbeh AR. Parkinson’s disease hand tremor detection system for mobile application. J Med Eng Technol 2016;40(3):127–34. doi:10.3109/03091902.2016.1148792.
37. San-Segundo R, Zhang A, Cebulla A, Panev S, Tabor G, Stebbins K, et al. Parkinson's Disease Tremor Detection in the Wild Using Wearable Accelerometers. Sensors (Basel) 2020;20(20):5817. doi:10.3390/s20205817.
38. Milano F, Cerro G, Santoni F, De Angelis A, Miele G, Rodio A, et al. Parkinson’s Disease Patient Monitoring: A Real-Time Tracking and Tremor Detection System Based on Magnetic Measurements. Sensors 2021;21(12):4196. doi:10.3390/s21124196.