Modeling the assessment of the upper limb motor function impairment in children with cerebral palsy using sEMG and IMU sensors

AbstractSeveral rehabilitation approaches have shown that robot-assisted therapy (robot-AT) can improve the quality of upper limb movements in children with cerebral palsy (CP). However, there is still no method for assessing upper limb motor function impairment using a combination of surface electromyography (sEMG) and inertial measurement unit (IMU) sensors. The aim of this study was to develop a functional ability model to assess the effectiveness of robot-AT on improving upper limb function in children with CP. Fifteen healthy children and fifteen children with CP were included in this study. Children with CP performed eighteen robot-AT sessions and were evaluated twice, using EMG and three-axis IMU readings from accelerometer (IMU-ACC). Principal component analysis and the RELIEFF algorithm were used for dimensionality reduction of the feature space. The classification was performed by using support vector machines, linear discriminant analysis, and random forest. The proposed assessment method was evaluated by using leave-one-out cross validation. With this approach, it was possible to differentiate between healthy children and children with CP pre-robot-AT and post-robot-AT with an overall accuracy of 97.56%. This study suggests that there is potential for modeling the assessment of the upper limb motor function impairment in children with CP using sEMG and IMU-ACC sensors.

Download Full-text

Robot-Assisted Therapy Influence on Kinematic and EMG Activity in the Upper Limb for Children with Cerebral Palsy

10.20944/preprints202001.0021.v1 ◽

2020 ◽

Author(s):

Sana Raouafi ◽

Maxime Raison ◽

Sofiane Achiche

Keyword(s):

Cerebral Palsy ◽

Motor Function ◽

Upper Limb ◽

Typically Developing ◽

Typically Developing Children ◽

Robot Assisted ◽

Function Index ◽

Children With Cerebral Palsy ◽

Before And After ◽

Inertial Measurements

Aim: To develop an index for quantitative assessment of the upper limb motor function in children with cerebral palsy before and after robot-assisted therapy. Method: An upper limb motor function index was developed using kinematic, surface electromyography and three-axis inertial measurements unit data collected from 15 children with cerebral palsy (CP) and 15 typically developed children. Children with CP underwent 18 robot-assisted therapy sessions with the REAplan device. All children were evaluated, using kinematic data from the REAplan, electromyography and three-axis inertial measurements unit readings from its accelerometer. A principal component analysis was conducted to produce an evaluation index, which is able to detect the deviation from the upper limb motor function of typically developing children group. Children with CP were evaluated twice before and after the intervention with Box and Blocks test and Finger-To-Nose test. The discriminative and concurrent validity of the upper limb motor function index were investigated. Results: The upper limb motor function index was higher in children with CP post therapy (p<0.001). Finger-To-Nose test values improved after robot-assisted therapy (p<0.03). A weak but positive correlation was observed between upper limb motor function index and clinical tests (r=0.012, p=0.95 and r=0.13, p= 0.54 for Box and Blocks test and Finger-To-Nose test respectively). Interpretation: The upper limb motor function index successfully differentiated between the typically developing children and children with CP and was effective in assessing the improvement of the upper limb motor function after robot-assisted therapy. The upper limb motor function index could be extended to assess and monitor rehabilitation therapies of other populations, such as those with stroke and Parkinson’s disease.

Download Full-text

Prevalence of Speech Problems and the Use of Augmentative and Alternative Communication in Children With Cerebral Palsy: A Registry-Based Study in Norway

Perspectives on Augmentative and Alternative Communication ◽

10.1044/aac19.1.12 ◽

2010 ◽

Vol 19 (1) ◽

pp. 12-20 ◽

Cited By ~ 29

Author(s):

Guro Andersen ◽

Tone R. Mjøen ◽

Torstein Vik

Keyword(s):

Cerebral Palsy ◽

Motor Function ◽

Gestational Age ◽

Augmentative And Alternative Communication ◽

Alternative Communication ◽

Gross Motor ◽

Gross Motor Function ◽

Children With Cerebral Palsy ◽

Communicative Abilities ◽

Normal Speech

Abstract This study describes the prevalence of speech problems and the use of augmentative and alternative communication (AAC) in children with cerebral palsy (CP) in Norway. Information on the communicative abilities of 564 children with CP born 1996–2003, recorded in the Norwegian CP Registry, was collected. A total of 270 children (48%) had normal speech, 90 (16%) had slightly indistinct speech, 52 (9%) had indistinct speech, 35 (6%) had very indistinct speech, 110 children (19%) had no speech, and 7 (1%) were unknown. Speech problems were most common in children with dyskinetic CP (92 %), in children with the most severe gross motor function impairments and among children being totally dependent on assistance in feeding or tube-fed children. A higher proportion of children born at term had speech problems when compared with children born before 32 weeks of gestational age 32 (p > 0.001). Among the 197 children with speech problems only, 106 (54%) used AAC in some form. Approximately 20% of children had no verbal speech, whereas ~15% had significant speech problems. Among children with either significant speech problems or no speech, only 54% used AAC in any form.

Download Full-text