Dataset Information

The Validity and Reliability of a Kinect v2-Based Gait Analysis System for Children with Cerebral Palsy.

ABSTRACT: The aim of this study is to evaluate if Kinect is a valid and reliable clinical gait analysis tool for children with cerebral palsy (CP), and whether linear regression and long short-term memory (LSTM) recurrent neural network methods can improve its performance. A gait analysis was conducted on ten children with CP, on two occasions. Lower limb joint kinematics computed from the Kinect and a traditional marker-based Motion Analysis system were investigated by calculating the root mean square errors (RMSE), the coefficients of multiple correlation (CMC), and the intra-class correlation coefficients (ICC_2,k). Results showed that the Kinect-based kinematics had an overall modest to poor correlation (CMC-less than 0.001 to 0.70) and an angle pattern similarity with Motion Analysis. After the calibration, RMSE on every degree of freedom decreased. The two calibration methods indicated similar levels of improvement in hip sagittal (CMC-0.81 ± 0.10 vs. 0.75 ± 0.22)/frontal (CMC-0.41 ± 0.35 vs. 0.42 ± 0.37) and knee sagittal kinematics (CMC-0.85±0.07 vs. 0.87 ± 0.12). The hip sagittal (CMC-0.97±0.05) and knee sagittal (CMC-0.88 ± 0.12) angle patterns showed a very good agreement over two days. Modest to excellent reliability (ICC_2,k-0.45 to 0.93) for most parameters renders it feasible for observing ongoing changes in gait kinematics.

SUBMITTER: Ma Y

PROVIDER: S-EPMC6479781 | biostudies-literature | 2019 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

The Validity and Reliability of a Kinect v2-Based Gait Analysis System for Children with Cerebral Palsy.

Ma Yunru Y Mithraratne Kumar K Wilson Nichola C NC Wang Xiangbin X Ma Ye Y Zhang Yanxin Y

Sensors (Basel, Switzerland) 20190407 7

The aim of this study is to evaluate if Kinect is a valid and reliable clinical gait analysis tool for children with cerebral palsy (CP), and whether linear regression and long short-term memory (LSTM) recurrent neural network methods can improve its performance. A gait analysis was conducted on ten children with CP, on two occasions. Lower limb joint kinematics computed from the Kinect and a traditional marker-based Motion Analysis system were investigated by calculating the root mean square er ...[more]

PMID: 30959970

Similar Datasets

Project description:ObjectiveTo investigate construct validity and test-retest reliability of the parent-rated Hand-Use-at-Home questionnaire (HUH) in children with neonatal brachial plexus palsy or unilateral cerebral palsy.Design and subjectsFor this cross-sectional study, children with neonatal brachial plexus palsy or unilateral cerebral palsy, aged 3-10 years, were eligible.Main measuresThe HUH, Pediatric Outcome Data Collection Instrument Upper Extremity Scale (neonatal brachial plexus palsy only), and Children's Hand-Use Experience Questionnaire (unilateral cerebral palsy only) were completed. The HUH was completed twice in subgroups of both diagnoses. Lesion-extent (indication of involved nerve rootlets in neonatal brachial plexus palsy as confirmed during clinical observation and/or nerve surgery) and Manual Ability Classification System levels (unilateral cerebral palsy) were obtained from the medical records. Spearman correlation coefficients between the HUH and all clinical variables, agreement, standard error of measurement, smallest detectable change and intra-class correlation were calculated.ResultsA total of 260 patients participated (neonatal brachial plexus palsy: 181), of which 56 completed the second HUH (neonatal brachial plexus palsy: 16). Median age was 6.9 years for children with neonatal brachial plexus palsy, 116 had C5-C6 lesions. Median age for children with unilateral cerebral palsy was 6.4 years, 33 had Manual Ability Classification System Level II. The HUH correlated moderately with lesion-extent ( rs =-0.5), Pediatric Outcome Data Collection Instrument Upper Extremity Scale ( rs = 0.6) and Children's Hand-Use Experience Questionnaire ( rs = 0.5) but weakly with Manual Ability Classification System levels ( rs = -0.4). Test-retest reliability was excellent (intra-class correlation2,1 = 0.89, standard error of measurement = 0.599 and smallest detectable change = 1.66 logits) and agreement was good (mean difference HUH1 - HUH2 = 0.06 logits).ConclusionThe HUH showed good construct validity and test-retest reliability in children with neonatal brachial plexus palsy or unilateral cerebral palsy.

Dataset Information

The Validity and Reliability of a Kinect v2-Based Gait Analysis System for Children with Cerebral Palsy.

Publications

The Validity and Reliability of a Kinect v2-Based Gait Analysis System for Children with Cerebral Palsy.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets