scholarly journals Detection and Classification of Stroke Gaits by Deep Neural Networks Employing Inertial Measurement Units

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1864
Author(s):  
Fu-Cheng Wang ◽  
Szu-Fu Chen ◽  
Chin-Hsien Lin ◽  
Chih-Jen Shih ◽  
Ang-Chieh Lin ◽  
...  
Keyword(s):  
Stroke Patients ◽  
Gait Patterns ◽  
Gait Abnormality ◽  
Abnormal Gait ◽  
Average Accuracy ◽  
Targeted Treatments ◽  
Measurement Units ◽  
Gait Abnormalities ◽  
Rehabilitation Strategies

This paper develops Deep Neural Network (DNN) models that can recognize stroke gaits. Stroke patients usually suffer from partial disability and develop abnormal gaits that can vary widely and need targeted treatments. Evaluation of gait patterns is crucial for clinical experts to make decisions about the medication and rehabilitation strategies for the stroke patients. However, the evaluation is often subjective, and different clinicians might have different diagnoses of stroke gait patterns. In addition, some patients may present with mixed neurological gaits. Therefore, we apply artificial intelligence techniques to detect stroke gaits and to classify abnormal gait patterns. First, we collect clinical gait data from eight stroke patients and seven healthy subjects. We then apply these data to develop DNN models that can detect stroke gaits. Finally, we classify four common gait abnormalities seen in stroke patients. The developed models achieve an average accuracy of 99.35% in detecting the stroke gaits and an average accuracy of 97.31% in classifying the gait abnormality. Based on the results, the developed DNN models could help therapists or physicians to diagnose different abnormal gaits and to apply suitable rehabilitation strategies for stroke patients.

The validity of video clips in the diagnosis of gait disorder

2007 ◽  
Vol 13 (7) ◽  
pp. 333-336 ◽  
Author(s):  
Salih A Salih ◽  
Richard Wootton ◽  
Elaine Beller ◽  
Len Gray
Keyword(s):  
Gold Standard ◽  
Video Clip ◽  
Clinical Documentation ◽  
Gait Disorder ◽  
Average Sensitivity ◽  
Gait Patterns ◽  
Video Clips ◽  
Normal Gait ◽  
Abnormal Gait ◽  
Gait Abnormalities

We investigated the accuracy and validity of clinical gait assessment, performed by experienced geriatricians viewing video clips of 10 s duration. Nineteen patients with normal or characteristic abnormal gait patterns were studied. The treating physician's diagnosis served as the gold standard. Another live assessment was then performed by a geriatrician blinded to the medical record to establish inter-rater reliability of live assessments. Subsequently, each gait video clip was examined by two independent geriatricians without any background clinical documentation. Diagnostic accuracy was tested at two levels – whether the gait was abnormal, and the specific gait diagnosis. The agreement of the video clip examination with the gold standard to identify abnormal gait from normal gait ranged from substantial to excellent among assessors ( κ = 0.68–0.85), although low agreement with the gold standard was achieved in the detection of specific gait diagnosis (average agreement between both viewing geriatricians 50%). The technique appears to be a valid screening procedure for detecting gait abnormalities (average sensitivity 100%, specificity 70%).

EXPLOITING VISUAL CUES FOR LEARNING GAIT PATTERNS ASSOCIATED WITH NEUROLOGICAL DISORDERS

2017 ◽  
Vol 79 (3) ◽  
Author(s):  
Kuhelee Roy ◽  
Geelapaturu Subrahmanya Venkata Radha Krish Rao ◽  
Savarimuthu, Margret Anouncia
Keyword(s):  
Early Diagnosis ◽  
Real Time ◽  
Neurological Disorders ◽  
Visual Cues ◽  
Gait Pattern ◽  
Shape Features ◽  
Gait Patterns ◽  
Normal Gait ◽  
Abnormal Gait ◽  
Gait Abnormalities

Records of cases involving neurological disorders often exhibit abnormalities in the gait pattern of an individual. As mentioned in various articles, the causes of various gait disorders can be attributed to neurological disorders. Hence analysis of gait abnormalities can be a key to predict the type of neurological disorders as a part of early diagnosis. A number of sensor-based measurements have aided towards quantifying the degree of abnormalities in a gait pattern. A shape oriented motion based approach has been proposed in this paper to envisage the task of classifying an abnormal gait pattern into one of the five types of gait viz. Parkinsonian, Scissor, Spastic, Steppage and Normal gait. The motion and shape features for two cases viz. right-leg-front and left-leg-front will be taken into account. Experimental results of application on real-time videos suggest the reliability of the proposed method.

scholarly journals High prevalence of gait abnormalities in pugs

2018 ◽  
Vol 182 (6) ◽  
pp. 167-167 ◽  
Author(s):  
Cecilia Rohdin ◽  
Karin Hultin Jäderlund ◽  
Ingrid Ljungvall ◽  
Kerstin Lindblad-Toh ◽  
Jens Häggström
Keyword(s):  
Prospective Study ◽  
Kennel Club ◽  
Future Studies ◽  
Video Footage ◽  
Gait Abnormality ◽  
Abnormal Gait ◽  
High Prevalence ◽  
Associated Conditions ◽  
Health Disorders ◽  
Gait Abnormalities

The objective of this prospective study was to determine the prevalence of gait abnormalities in a cohort of Swedish pugs by using an owner-based questionnaire targeting signs of gait abnormality and video footage showing the dog’s gait. This study also evaluated associated conditions of abnormal gait, including other health disorders prevalent in the breed. Five hundred and fifty (550) pugs registered in the Swedish Kennel Club, of one, five and eight years of age, in 2015 and 2016, were included in the study. Gait abnormalities were reported in 30.7 per cent of the responses. In the majority of cases, the character of the described gait indicated a neurological cause for the gait abnormality. An association was observed between abnormal gait and age, with gait abnormalities being significantly more common in older pugs (P=0.004). An association was also found between abnormal gait and dyspnoea, with dyspnoea being significantly more common in pugs with gait abnormalities (P<0.0001). This study demonstrated that the prevalence of gait abnormalities was high in the Swedish pug breed and increased with age. Future studies on the mechanisms behind these gait abnormalities are warranted.

P052 Classification of gait patterns in chronic post stroke patients

2008 ◽  
Vol 28 ◽  
pp. S80-S81
Author(s):  
C. Huenaerts ◽  
G. Molenaers ◽  
H. Beyens ◽  
K. Daniels ◽  
K. Desloovere
Keyword(s):  
Stroke Patients ◽  
Gait Patterns ◽  
Post Stroke

scholarly journals String Grammar Unsupervised Possibilistic Fuzzy C-Medians for Gait Pattern Classification in Patients with Neurodegenerative Diseases

2018 ◽  
Vol 2018 ◽  
pp. 1-10 ◽  
Author(s):  
Atcharin Klomsae ◽  
Sansanee Auephanwiriyakul ◽  
Nipon Theera-Umpon
Keyword(s):  
Neurodegenerative Diseases ◽  
Nearest Neighbor ◽  
Gait Pattern ◽  
Time Interval ◽  
K Nearest Neighbor ◽  
Symbolic Aggregate Approximation ◽  
Average Accuracy ◽  
Stride Interval ◽  
Gait Abnormalities

Neurodegenerative diseases that affect serious gait abnormalities include Parkinson's disease (PD), amyotrophic lateral sclerosis (ALS), and Huntington disease (HD). These diseases lead to gait rhythm distortion that can be determined by stride time interval of footfall contact times. In this paper, we present a new method for gait classification of neurodegenerative diseases. In particular, we utilize a symbolic aggregate approximation algorithm to convert left-foot stride-stride interval into a sequence of symbols using a symbolic aggregate approximation. We then find string prototypes of each class using the newly proposed string grammar unsupervised possibilistic fuzzy C-medians. Then in the testing process the fuzzy k-nearest neighbor is used. We implement the system on three 2-class problems, i.e., the classification of ALS against healthy patients, that of HD against healthy patients , and that of PD against healthy patients. The system is also implemented on one 4-class problem (the classification of ALS, HD, PD, and healthy patients altogether) called NDDs versus healthy. We found that our system yields a very good detection result. The average correct classification for ALS versus healthy is 96.88%, and that for HD versus healthy is 97.22%, whereas that for PD versus healthy is 96.43%. When the system is implemented on 4-class problem, the average accuracy is approximately 98.44%. It can provide prototypes of gait signals that are more understandable to human.

scholarly journals Diagnostic usefulness of 10-step tandem gait test for the patient with degenerative cervical myelopathy

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Dallah Yoo ◽  
Kyung-Chung Kang ◽  
Jung-Hee Lee ◽  
Ki Young Lee ◽  
In-Uk Hwang
Keyword(s):  
Cervical Myelopathy ◽  
Screening Tools ◽  
Control Group ◽  
Japanese Orthopedic Association ◽  
Gait Abnormality ◽  
Abnormal Gait ◽  
Diagnostic Usefulness ◽  
Gait Abnormalities ◽  
Degenerative Cervical Myelopathy ◽  
Tandem Gait

AbstractTandem gait is considered one of the most useful screening tools for gait impairment. The aim of this study is to evaluate diagnostic usefulness of 10-step tandem gait test for the patients with degenerative cervical myelopathy (DCM). Sixty-two DCM patients were compared to 55 persons without gait abnormalities as control. We counted the number of consecutive steps and graded into five according the number of steps and stability. Five grades of tandem gait were investigated for association with clinical parameters including qualitative Japanese orthopedic association (JOA) sub-score for lower extremities and Nurick scale and quantitative balance and gait assessments. The number of tandem steps were reduced and the grades of tandem gait were differently distributed in the DCM patients compared to controls (steps, 7.1 ± 3.6 versus 9.9 ± 0.4, p < 0.001; grades of 0/1/2/3/4/5, 1/13/14/15/19 versus 0/0/2/15/38, p < 0.001 in patients with DCM and control respectively). Patients with DCM showed more unstable balance and abnormal gait features including slower velocity, shorter strides, wider bases with increased stance phase of a gait cycle compared to the control group. The grades of tandem gait were correlated with JOA sub-score (r = 0.553, p < 0.001) and the Nurick scale (r = − 0.652, p < 0.001) as well as both balance and gait parameters. In DCM patients, tandem gait was impaired and correlated with severity of gait abnormality. The authors believe that 10-step tandem gait test is an objective and useful screening test for evaluating gait disturbance in patients with DCM.

scholarly journals The Actuation System of the Ankle Exoskeleton T-FLEX: First Use Experimental Validation in People with Stroke

2021 ◽  
Vol 11 (4) ◽  
pp. 412
Author(s):  
Daniel Gomez-Vargas ◽  
Felipe Ballen-Moreno ◽  
Patricio Barria ◽  
Rolando Aguilar ◽  
José M. Azorín ◽  
...  
Keyword(s):  
Inertial Sensor ◽  
Movement Analysis ◽  
Biomechanical Analysis ◽  
Gait Patterns ◽  
Positive Effects ◽  
General Terms ◽  
Actuation System ◽  
Abnormal Gait ◽  
Ankle Kinematics ◽  
Robotic Devices

Robotic devices can provide physical assistance to people who have suffered neurological impairments such as stroke. Neurological disorders related to this condition induce abnormal gait patterns, which impede the independence to execute different Activities of Daily Living (ADLs). From the fundamental role of the ankle in walking, Powered Ankle-Foot Orthoses (PAFOs) have been developed to enhance the users’ gait patterns, and hence their quality of life. Ten patients who suffered a stroke used the actuation system of the T-FLEX exoskeleton triggered by an inertial sensor on the foot tip. The VICONmotion capture system recorded the users’ kinematics for unassisted and assisted gait modalities. Biomechanical analysis and usability assessment measured the performance of the system actuation for the participants in overground walking. The biomechanical assessment exhibited changes in the lower joints’ range of motion for 70% of the subjects. Moreover, the ankle kinematics showed a correlation with the variation of other movements analyzed. This variation had positive effects on 70% of the participants in at least one joint. The Gait Deviation Index (GDI) presented significant changes for 30% of the paretic limbs and 40% of the non-paretic, where the tendency was to decrease. The spatiotemporal parameters did not show significant variations between modalities, although users’ cadence had a decrease of 70% of the volunteers. Lastly, the satisfaction with the device was positive, the comfort being the most user-selected aspect. This article presents the assessment of the T-FLEX actuation system in people who suffered a stroke. Biomechanical results show improvement in the ankle kinematics and variations in the other joints. In general terms, GDI does not exhibit significant increases, and the Movement Analysis Profile (MAP) registers alterations for the assisted gait with the device. Future works should focus on assessing the full T-FLEX orthosis in a larger sample of patients, including a stage of training.

scholarly journals Using Machine Learning and Wearable Inertial Sensor Data for the Classification of Fractal Gait Patterns in Women and Men During Load Carriage

2021 ◽  
Vol 185 ◽  
pp. 282-291
Author(s):  
Nizam U. Ahamed ◽  
Kellen T. Krajewski ◽  
Camille C. Johnson ◽  
Adam J. Sterczala ◽  
Julie P. Greeves ◽  
...  
Keyword(s):  
Machine Learning ◽  
Inertial Sensor ◽  
Load Carriage ◽  
Sensor Data ◽  
Gait Patterns

scholarly journals Effect of Functional Electrical Stimulation of the Gluteus Medius during Gait in Patients following a Stroke

2020 ◽  
Vol 2020 ◽  
pp. 1-6
Author(s):  
Sota Araki ◽  
Masayuki Kawada ◽  
Takasuke Miyazaki ◽  
Yuki Nakai ◽  
Yasufumi Takeshita ◽  
...  
Keyword(s):  
Electrical Stimulation ◽  
Lower Limb ◽  
Stride Length ◽  
Gluteus Medius ◽  
Gait Velocity ◽  
Inertial Measurement Units ◽  
Stroke Patients ◽  
Inertial Measurement ◽  
Motion Range ◽  
Measurement Units

Many stroke patients rely on cane or ankle-foot orthosis during gait rehabilitation. The purpose of this study was to investigate the immediate effect of functional electrical stimulation (FES) to the gluteus medius (GMed) and tibialis anterior (TA) on gait performance in stroke patients, including those who needed assistive devices. Fourteen stroke patients were enrolled in this study (mean poststroke duration: 194.9 ± 189.6   d ; mean age: 72.8 ± 10.7   y ). Participants walked 14 m at a comfortable velocity with and without FES to the GMed and TA. After an adaptation period, lower-limb motion was measured using magnetic inertial measurement units attached to the pelvis and the lower limb of the affected side. Motion range of angle of the affected thigh and shank segments in the sagittal plane, motion range of the affected hip and knee extension-flexion angle, step time, and stride time were calculated from inertial measurement units during the middle ten walking strides. Gait velocity, cadence, and stride length were also calculated. These gait indicators, both with and without FES, were compared. Gait velocity was significantly faster with FES ( p = 0.035 ). Similarly, stride length and motion range of the shank of the affected side were significantly greater with FES (stride length: p = 0.018 ; motion range of the shank: p = 0.02 6). Meanwhile, cadence showed no significant difference ( p = 0.238 ) in gait with or without FES. Similarly, range of motion of the affected hip joint, knee joint, and thigh did not differ significantly depending on FES condition ( p = 0.115 ‐ 0.529 ). FES to the GMed and TA during gait produced an improvement in gait velocity, stride length, and motion range of the shank. Our results will allow therapists to use FES on stroke patients with varying conditions.

Sign in / Sign up

Export Citation Format

Share Document