Classification of hemiplegia through gait analysis and machine learning methods

Abstract

Objective: Gait analysis is a method that is used for understanding normal walking and determining the stage of the disease as it affects walking. It is important to objectively determine the stage of the disease in order to decide interventions and treatment strategies. This study aims to determine the Brunnstrom Stage of the hemiplegic patients with an analysis of gait data. Patients and Methods: In the first part of the study, the gait signal data were taken from 28 post-stroke hemiplegic patients and 7 healthy individuals with three-axis accelerometers. In the second part, new gait data were collected from 15 healthy individuals through an accelerometer on the anteroposterior axis. First the accelerometer signals were decomposed to Daubechies 5 (Db5) level six wavelets using MATLAB software. Subsequently, these attributes were classified through several classifier and machine learning algorithms on WEKA and MATLAB software packages to predict the stages of hemiplegia. Results: The highest accuracy rate in the prediction of hemiplegia stage was achieved with the LogitBoost algorithm on WEKA with 91% for 35 samples, and 90% for 50 samples. This performance was followed by the RUSBoosted Trees algorithm on the MATLAB software with an accuracy of 86.1% correct prediction. Conclusion: The Brunnstrom Stage of hemiplegia can be predicted with machine learning algorithms with a good accuracy, helping physicians to classify hemiplegic patients into correct stages, monitor and manage their rehabilitation.

Keywords

• Hemiplegia
• Stroke
• Gait analysis
• Brunnstrom
• Machine learning

References

1. Jørgensen H S, Nakayama H, Raaschou H O, Olsen T S. Recovery of walking function in stroke patients: The copenhagen stroke study. Arch Phys Med Rehabil 2014; 76:27- 32. doi:10.1016/S0003-9993(95)80038-7.
2. Kuan TS, Tsou JY, Su FC. Hemiplegic gait of stroke patients: The effect of using a cane. Arch Phys Med Rehabil 1999; 80: 777-84. doi: 10.1016/s0003-9993(99)90227-7.
3. Van Sant A F. Movement System Diagnosis. J Neurol Physl Ther 2017; 41: 10-6. doi: 10.1097/NPT.000.000.0000000152.
4. Guo Y, Wu D, Liu G, Zhao G, Huang B, Wang L. A low-cost body inertial-sensing network for practical gait discrimination of hemiplegia patients. Telemed J E Health 2012; 18: 748-54. doi: 10.1089/tmj.2012.0014.
5. Muro-de-la-Herran A, Garcia Zapirain B, Mendez-Zorrilla A. Gait analysis methods: An overview of wearable and nonwearable systems, highlighting clinical Applications. Sensors (Basel) 2014; 14: 3362-94. doi: 10.3390/s140203362.
6. Tao W, Liu T, Zheng R, Feng H. Gait analysis using wearable sensors. Sensors (Basel) 2012; 12: 2255-83. doi: 10.3390/ s120202255.
7. Meyer Y. Wavelets: Algorithms and applications. Philadelphia: Society for Industrial and Applied Mathematics, 1993: 133.
8. Samant A. Feature extraction for traffic incident detection using wavelet transform and linear discriminant analysis. Comput‐Aided Civ Infrastruct Eng 2003; 15: 241-50. doi: 10.1111/0885-9507.00188.

9. Lee J, Park S, Shin H. Detection of hemiplegic walking using a wearable inertia sensing device. Sensors (Basel) 2018; 18: 1736. doi: 10.3390/s18061736.
10. Li M, Tian S, Sun L, Chen X. Gait analysis for post-stroke hemiparetic patient by Multi-Features Fusion Method. Sensors (Basel) 2019; 19: 1737. doi: 10.3390/s19071737.
11. Sekine M, Abe Y, Sekimoto M, et al. Assessment of gait parameter in hemiplegic patients by accelerometry. Proceedings of the 22nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (Cat. No.00CH37143). Chicago 2000; 3: 1879-82. doi: 10.1109/ IEMBS.2000.900456.
12. Yardımcı A. Fuzzy logic based gait classification for hemiplegic patients. Lect Notes Comput Sci 2007; 4723: 344-54.
13. Toprak IB. Analysis of EEG signals using the wavelet transform and artificial neural network [master’s thesis]. University of Süleyman Demirel, Isparta 2007.
14. Aydın F, Aslan Z. Yapay öğrenme yöntemleri ve dalgacık dönüşümü kullanılarak nörodejeneratif hastalıkların teşhisi. Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi 2017; 32: 749-66. doi: 10.17341/gazimmfd.337621
15. Wang N, Ambikairajah E, Lovell N H, Celler B G. Accelerometry based classification of walking patterns using time-frequency analysis. 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Lyon 2007; 36: 4899-902.