Simultaneous Recognition and Assessment of Post-Stroke Hemiparetic Gait by Fusing Kinematic, Kinetic, and Electrophysiological Data

Abstract

Gait analysis for the patients with lower limb motor dysfunction is a useful tool in assisting clinicians for diagnosis, assessment, and rehabilitation strategy making. Implementing accurate automatic gait analysis for the hemiparetic patients after stroke is a great challenge in clinical practice. This study is to develop a new automatic gait analysis system for qualitatively recognizing and quantitatively assessing the gait abnormality of the post-stroke hemiparetic patients. Twenty-one post-stroke patients and twenty-one healthy volunteers participated in the walking trials. Three of the most representative gait data, i.e., marker trajectory (MT), ground reaction force (GRF), and electromyogram, were simultaneously acquired from these subjects during their walking. A multimodal fusion architecture is established by using these different modal data to qualitatively distinguish the hemiparetic gait from normal gait by different pattern recognition techniques and to quantitatively estimate the patient's lower limb motor function by a novel probability-based gait score. Seven decision fusion algorithms have been tested in this architecture, and extensive data analysis experiments have been conducted. The results indicate that the recognition performance and estimation performance of the system become better when more modal gait data are fused. For the recognition performance, the random forest classifier based on the GRF data achieves an accuracy of 92.26% outperformed other single-modal schemes. When combining two modal data, the accuracy can be enhanced to 95.83% by using the support vector machine (SVM) fusion algorithm to fuse the MT and GRF data. When integrating all the three modal data, the accuracy can be further improved to 98.21% by using the SVM fusion algorithm. For the estimation performance, the absolute values of the correlation coefficients between the estimation results of the above three schemes and the Wisconsin gait scale scores for the post-stroke patients are 0.63, 0.75, and 0.84, respectively, which means the clinical relevance becomes more obvious when using more modalities. These promising results demonstrate that the proposed method has considerable potential to promote the future design of automatic gait analysis systems for clinical practice.

Appropriate Mother Wavelets for Continuous Gait Event Detection Based on Time-Frequency Analysis for Hemiplegic and Healthy Individuals

“…Gait disorders are usually associated with an ageing population as well as stroke survivors with hemiplegia, thus leading to both a reduced quality of life and an increased mortality rate. The detection of gait events or gait characteristics is essential to numerous applications including the development of control mechanisms in drop foot correction devices [1,2,3,4,5], human activity recognition for healthcare [6,7], motor recovery assessments for effective rehabilitation strategies [1,8], especially for patients with lower limb motor dysfunction following a severe stroke. Heel strike (HS) and toe off (TO) are regarded as two core gait events in a normal gait cycle, which provide information on the swing, stance, and stride gait parameters.…”

“…Thus, it is difficult for developers and clinicians to truly understand the mechanism of gait event detection that often hinders proper interpretation for practical applications [9,13,14]. By exploiting the limitations of the above described threshold-based approaches and machine learning based methods [1,8], continuous wavelet transform (CWT) based methods have been considered as an alternative solution. By simultaneously providing a signal’s information in the time and frequency domains through a series of decomposition and reconstruction operation, the wavelet transform method has been utilized as an effective tool in various fields, such as signal de-noising [15], speech/signal processing and evaluation [16,17,18], and health threatening illness diagnosis [19].…”

A Determination Method for Gait Event Based on Acceleration Sensors

“…Gait disorders are usually associated with the ageing population as well as falling, leading to both a reduced quality of life and an increased mortality rate. The detection of gait events is an important tool in clinics [1,2], including human activity recognition for healthcare [3,4] and motor recovery assessments for effective rehabilitation strategies [5,6]. Hence, it is essential to develop an effective algorithm for the accurate detection of gait events.…”

Sensors and Systems for Physical Rehabilitation and Health Monitoring—A Review

“…In [83], three different modal time-varying dynamic data, marker trajectory using a six-camera motion capture system, ground reaction force using two force plates embedded in the floor, and eight channels of sEMG signals, were synchronously recorded by a motion capture system from the subjects in both pathological and normal groups. The monitored muscles involved the rectus femoris, long head of the biceps femoris, tibialis anterior, and medial head of gastrocnemius of both lower limbs.…”