An automated system for motor function assessment in stroke patients using motion sensing technology: A pilot study

Abstract This study aims to develop and evaluate an automated system for upper-limb motor function assessment of stroke patients. The proposed system contains one motion tracking subsystem (to measure the kinematic data of participants through one Kinect V2) and one motor function assessment subsystem (to realize the automated assessment based on a feed-forward neural network (FFNN)-based assessment model). For validation, 16 stroke patients and 10 healthy subjects were recruited to perform 4 WMFT-FAS tasks, and 5 evaluation metrics were used. The experimental results showed that the proposed system could present satisfactory performance (accuracy: 0.87–0.96, F1-score: 0.83–0.93, specificity: 0.94–0.98, sensitivity: 0.87–0.95, and AUC: 0.93–1.00), and the FFNN-based assessment model could also present promising comprehensive performance (top two in all tasks in terms of accuracy and F1-score).

[1]  Ahmet H. Ertas,et al.  A clinically feasible kinematic assessment method of upper extremity motor function impairment after stroke , 2016 .

[2]  N. Paik,et al.  Upper Extremity Functional Evaluation by Fugl-Meyer Assessment Scoring Using Depth-Sensing Camera in Hemiplegic Stroke Patients , 2016, PloS one.

[3]  Ruzena Bajcsy,et al.  Evaluation of upper extremity reachable workspace using Kinect camera. , 2013, Technology and health care : official journal of the European Society for Engineering and Medicine.

[4]  Shyamal Patel,et al.  A Novel Approach to Monitor Rehabilitation Outcomes in Stroke Survivors Using Wearable Technology , 2010, Proceedings of the IEEE.

[5]  D. Giavarina.  Understanding Bland Altman analysis , 2015, Biochemia medica.

[6]  Sang Hyuk Son,et al.  A Framework to Automate Assessment of Upper-Limb Motor Function Impairment: A Feasibility Study , 2015, Sensors.

[7]  Sungmin Cho,et al.  Upper-Limb Function Assessment Using VBBTs for Stroke Patients , 2016, IEEE Computer Graphics and Applications.

[8]  Yanxin Zhang,et al.  Identification of Knee Osteoarthritis Based on Bayesian Network: Pilot Study , 2019, JMIR medical informatics.

[9]  Zhe Zhang,et al.  A Fuzzy Kernel Motion Classifier for Autonomous Stroke Rehabilitation , 2016, IEEE Journal of Biomedical and Health Informatics.

[10]  Hong-Bo Xie,et al.  Estimation of wrist angle from sonomyography using support vector machine and artificial neural network models. , 2009, Medical engineering & physics.

[11]  Carlos Balaguer,et al.  Review of Automated Systems for Upper Limbs Functional Assessment in Neurorehabilitation , 2019, IEEE Access.

[12]  Zhe Zhang,et al.  Fuzzy inference system based automatic Brunnstrom stage classification for upper-extremity rehabilitation , 2014, Expert Syst. Appl..

[13]  Bo Sheng,et al.  A comparison of different machine learning algorithms, types and placements of activity monitors for physical activity classification , 2020, Measurement.

[14]  S. Black,et al.  The Fugl-Meyer Assessment of Motor Recovery after Stroke: A Critical Review of Its Measurement Properties , 2002, Neurorehabilitation and neural repair.

[15]  Alessandro Scano,et al.  Kinect V2 implementation and testing of the reaching performance scale for motor evaluation of patients with neurological impairment. , 2018, Medical engineering & physics.

[16]  Yanxin Zhang,et al.  Application of supervised machine learning algorithms in the classification of sagittal gait patterns of cerebral palsy children with spastic diplegia , 2019, Comput. Biol. Medicine.

[17]  P. L. Weiss,et al.  Kinematics of Reaching Movements in a 2-D Virtual Environment in Adults With and Without Stroke , 2012, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[18]  Sung Min Son,et al.  Changes of kinematic parameters of lower extremities with gait speed: a 3D motion analysis study , 2015, Journal of physical therapy science.

[19]  Erienne V. Olesh,et al.  Automated Assessment of Upper Extremity Movement Impairment due to Stroke , 2014, PloS one.

[20]  S. Wolf,et al.  Can the Wolf Motor Function Test be Streamlined? , 2009, Neurorehabilitation and neural repair.

[21]  Shuping Xiong,et al.  Validity and Reliability of Upper Limb Functional Assessment Using the Microsoft Kinect V2 Sensor , 2019, Applied bionics and biomechanics.

[22]  Daniel Simonsen,et al.  Design and test of an automated version of the modified Jebsen test of hand function using Microsoft Kinect , 2017, Journal of NeuroEngineering and Rehabilitation.

[23]  Qiang Fang,et al.  A Novel Multistandard Compliant Hand Function Assessment Method Using an Infrared Imaging Device , 2019, IEEE Journal of Biomedical and Health Informatics.

[24]  Gabriele Maria Lozito,et al.  On Training Efficiency and Computational Costs of a Feed Forward Neural Network: A Review , 2015, Comput. Intell. Neurosci..

[25]  J. Elsner.  Analysis of Time Series Structure: SSA and Related Techniques , 2002 .

[26]  Wenbing Zhao,et al.  A Survey of Applications and Human Motion Recognition with Microsoft Kinect , 2015, Int. J. Pattern Recognit. Artif. Intell..

[27]  SchmidhuberJürgen.  Deep learning in neural networks , 2015 .

[28]  Alejandro Santos-Lozano,et al.  Technical variability of the GT3X accelerometer. , 2012, Medical engineering & physics.

[29]  Carlos Balaguer,et al.  Automatic Outcome in Manual Dexterity Assessment Using Colour Segmentation and Nearest Neighbour Classifier , 2018, Sensors.

[30]  Guy Lapalme,et al.  A systematic analysis of performance measures for classification tasks , 2009, Inf. Process. Manag..

[31]  Ruth E Mayagoitia,et al.  A portable system for collecting anatomical joint angles during stair ascent: a comparison with an optical tracking device , 2009, Dynamic medicine : DM.

[32]  Etienne Burdet,et al.  A Robust and Sensitive Metric for Quantifying Movement Smoothness , 2012, IEEE Transactions on Biomedical Engineering.

[33]  Caroline S. Langensiepen,et al.  Clinical assessment of depth sensor based pose estimation algorithms for technology supervised rehabilitation applications , 2019, Int. J. Medical Informatics.

[34]  S. Wolf,et al.  Assessing Wolf Motor Function Test as Outcome Measure for Research in Patients After Stroke , 2001, Stroke.

[35]  Adam Miller,et al.  Gait event detection using a multilayer neural network. , 2009, Gait & posture.

[36]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[37]  Yu-Wei Hsieh,et al.  Development and Validation of a Short Form of the Fugl-Meyer Motor Scale in Patients With Stroke , 2007, Stroke.

[38]  David A. Winter,et al.  Biomechanics and Motor Control of Human Movement , 1990 .

[39]  Jonghyun Kim,et al.  Automated Evaluation of Upper-Limb Motor Function Impairment Using Fugl-Meyer Assessment , 2018, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[40]  A. Zhigljavsky.  Singular Spectrum Analysis for time series: Introduction to this special issue , 2010 .

[41]  C. Winstein,et al.  Interrater Reliability of the Wolf Motor Function Test–Functional Ability Scale , 2015, Neurorehabilitation and Neural Repair.

[42]  Zhe Zhang,et al.  Objective Assessment of Upper-Limb Mobility for Poststroke Rehabilitation , 2016, IEEE Transactions on Biomedical Engineering.

[43]  S. Chong,et al.  Prevalence of stroke, risk factors, disability and care needs in older adults in Singapore: results from the WiSE study , 2018, BMJ Open.

[44]  Kumar Mithraratne,et al.  The Validity and Reliability of a Kinect v2-Based Gait Analysis System for Children with Cerebral Palsy , 2019, Sensors.