Dataset Information

An Unsupervised Data-Driven Model to Classify Gait Patterns in Children with Cerebral Palsy.

ABSTRACT: Ankle and foot orthoses are commonly prescribed to children with cerebral palsy (CP). It is unclear whether 3D gait analysis (3DGA) provides sufficient and reliable information for clinicians to be consistent when prescribing orthoses. Data-driven modeling can probe such questions by revealing non-intuitive relationships between variables such as 3DGA parameters and gait outcomes of orthoses use. The purpose of this study was to (1) develop a data-driven model to classify children with CP according to their gait biomechanics and (2) identify relationships between orthotics types and gait patterns. 3DGA data were acquired from walking trials of 25 typically developed children and 98 children with CP with additional prescribed orthoses. An unsupervised self-organizing map followed by k-means clustering was developed to group different gait patterns based on children's 3DGA. Model inputs were gait variable scores (GVSs) extracted from the gait profile score, measuring root mean square differences from TD children's gait cycle. The model identified five pathological gait patterns with statistical differences in GVSs. Only 43% of children improved their gait pattern when wearing an orthosis. Orthotics prescriptions were variable even in children with similar gait patterns. This study suggests that quantitative data-driven approaches may provide more clarity and specificity to support orthotics prescription.

SUBMITTER: Choisne J

PROVIDER: S-EPMC7290444 | biostudies-literature | 2020 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

An Unsupervised Data-Driven Model to Classify Gait Patterns in Children with Cerebral Palsy.

Choisne Julie J Fourrier Nicolas N Handsfield Geoffrey G Signal Nada N Taylor Denise D Wilson Nichola N Stott Susan S Besier Thor F TF

Journal of clinical medicine 20200512 5

Ankle and foot orthoses are commonly prescribed to children with cerebral palsy (CP). It is unclear whether 3D gait analysis (3DGA) provides sufficient and reliable information for clinicians to be consistent when prescribing orthoses. Data-driven modeling can probe such questions by revealing non-intuitive relationships between variables such as 3DGA parameters and gait outcomes of orthoses use. The purpose of this study was to (1) develop a data-driven model to classify children with CP accord ...[more]

PMID: 32408489

Similar Datasets

Project description:BackgroundChildren with cerebral palsy (CP) often show impaired selective motor control (SMC) that induces limitations in motor function. Children with CP can improve aspects of pathological gait in an immediate response to visual biofeedback. It is not known, however, how these gait adaptations are achieved at the neural level, nor do we know the extent of SMC plasticity in CP.AimInvestigate the underlying SMC and changes that may occur when gait is adapted with biofeedback.MethodsTwenty-three ambulatory children with CP and related (hereditary) forms of spastic paresis (Aged: 10.4 ± 3.1, 6-16 years, M: 16/F: 9) were challenged with real-time biofeedback to improve step length, knee extension, and ankle power while walking on an instrumented treadmill in a virtual reality environment. The electromyograms of eight superficial muscles of the leg were analyzed and synergies were further decomposed using non-negative matrix factorization (NNMF) using 1 to 5 synergies, to quantify SMC. Total variance accounted for (tVAF) was used as a measure of synergy complexity. An imposed four synergy solution was investigated further to compare similarity in weightings and timing patterns of matched paired synergies between baseline and biofeedback trials.ResultsDespite changes in walking pattern, changes in synergies were limited. The number of synergies required to explain at least 90% of muscle activation increased significantly, however, the change in measures of tVAF1 from baseline (0.75 ± 0.08) were less than ±2% between trials. In addition, within-subject similarity of synergies to baseline walking was high (>0.8) across all biofeedback trials.ConclusionThese results suggest that while gait may be adapted in an immediate response, SMC as quantified by synergy analysis is perhaps more rigidly impaired in CP. Subtle changes in synergies were identified; however, it is questionable if these are clinically meaningful at the level of an individual. Adaptations may be limited in the short term, and further investigation is essential to establish if long term training using biofeedback leads to adapted SMC.

Project description:Experts recently identified 49 joint motion patterns in children with cerebral palsy during a Delphi consensus study. Pattern definitions were therefore the result of subjective expert opinion. The present study aims to provide objective, quantitative data supporting the identification of these consensus-based patterns. To do so, statistical parametric mapping was used to compare the mean kinematic waveforms of 154 trials of typically developing children (n = 56) to the mean kinematic waveforms of 1719 trials of children with cerebral palsy (n = 356), which were classified following the classification rules of the Delphi study. Three hypotheses stated that: (a) joint motion patterns with 'no or minor gait deviations' (n = 11 patterns) do not differ significantly from the gait pattern of typically developing children; (b) all other pathological joint motion patterns (n = 38 patterns) differ from typically developing gait and the locations of difference within the gait cycle, highlighted by statistical parametric mapping, concur with the consensus-based classification rules. (c) all joint motion patterns at the level of each joint (n = 49 patterns) differ from each other during at least one phase of the gait cycle. Results showed that: (a) ten patterns with 'no or minor gait deviations' differed somewhat unexpectedly from typically developing gait, but these differences were generally small (?3°); (b) all other joint motion patterns (n = 38) differed from typically developing gait and the significant locations within the gait cycle that were indicated by the statistical analyses, coincided well with the classification rules; (c) joint motion patterns at the level of each joint significantly differed from each other, apart from two sagittal plane pelvic patterns. In addition to these results, for several joints, statistical analyses indicated other significant areas during the gait cycle that were not included in the pattern definitions of the consensus study. Based on these findings, suggestions to improve pattern definitions were made.

Project description:Clinical gait analysis is widely used in clinical routine to assess the function of patients with motor disorders. The proper assessment of the patient's function relies greatly on the repeatability between the measurements. Marker misplacement has been reported as the largest source of variability between measurements and its impact on kinematics is not fully understood. Thus, the purpose of this study was: 1) to evaluate the impact of the misplacement of the lateral femoral epicondyle marker on lower limb kinematics, and 2) evaluate if such impact can be predicted. The kinematic data of 10 children with cerebral palsy and 10 aged-match typical developing children were included. The lateral femoral epicondyle marker was virtually misplaced around its measured position at different magnitudes and directions. The outcome to represent the impact of each marker misplacement on the lower limb was the root mean square deviations between the resultant kinematics from each simulated misplacement and the originally calculated kinematics. Correlation and regression equations were estimated between the root mean square deviation and the magnitude of the misplacement expressed in percentage of leg length. Results indicated that the lower-limb kinematics is highly sensitive to the lateral femoral epicondyle marker misplacement in the anterior-posterior direction. The joint angles most impacted by the anterior-posterior misplacement were the hip internal-external rotation (5.3° per 10 mm), the ankle internal-external rotation (4.4° per 10 mm) and the knee flexion-extension (4.2° per 10 mm). Finally, it was observed that the lower the leg length, the higher the impact of misplacement on kinematics. This impact was predicted by regression equations using the magnitude of misplacement expressed in percentage of leg length. An error below 5° on all joints requires a marker placement repeatability under 1.2% of the leg length. In conclusion, the placement of the lateral femoral epicondyle marker in the antero-posterior direction plays a crucial role on the reliability of gait measurements with the Conventional Gait Model.

Project description:Upper body movements during walking provide information about balance control and gait stability. Typically developing (TD) children normally present a progressive decrease of accelerations from the pelvis to the head, whereas children with cerebral palsy (CP) exhibit a general increase of upper body accelerations. However, the literature describing how they are transmitted from the pelvis to the head is lacking. This study proposes a multilevel motion sensor approach to characterize upper body accelerations and how they propagate from pelvis to head in children with CP, comparing with their TD peers. Two age- and gender-matched groups of 20 children performed a 10m walking test at self-selected speed while wearing three magneto-inertial sensors located at pelvis, sternum, and head levels. The root mean square value of the accelerations at each level was computed in a local anatomical frame and its variation from lower to upper levels was described using attenuation coefficients. Between-group differences were assessed performing an ANCOVA, while the mutual dependence between acceleration components and the relationship between biomechanical parameters and typical clinical scores were investigated using Regression Analysis and Spearman's Correlation, respectively (? = 0.05). New insights were obtained on how the CP group managed the transmission of accelerations through the upper body. Despite a significant reduction of the acceleration from pelvis to sternum, children with CP do not compensate for large accelerations, which are greater than in TD children. Furthermore, those with CP showed negative sternum-to-head attenuations, in agreement with the documented rigidity of the head-trunk system observed in this population. In addition, the estimated parameters proved to correlate with the scores used in daily clinical practice. The proposed multilevel approach was fruitful in highlighting CP-TD gait differences, supported the in-field quantitative gait assessment in children with CP and might prove beneficial to designing innovative intervention protocols based on pelvis stabilization.

Project description:The interaction between brain damage and motor function is not yet fully understood in children with spastic cerebral palsy (CP). Therefore, a semi-quantitative MRI (sqMRI) scale was used to explore whether identified brain lesions related to functional abilities and gait pathology in this population. A retrospective cohort of ambulatory children with spastic CP was selected [N = 104; 52 bilateral (bCP) and 52 unilateral (uCP)]. Extent and location-specific scores were defined according to the sqMRI scale guidelines. The gross motor function classification system (GMFCS), the gait profile score (GPS), GPSs per motion plane, gait variable scores (GVS) and multiple-joint (MJ) gait patterns were related to brain lesion scores. In all groups, the global total brain scores correlated to the GPS (total: r s = 0.404, p ≤ 0.001; bCP: r s = 0.335, p ≤ 0.05; uCP: r s = 0.493, p ≤ 0.001). The global total hemispheric scores correlated to the GMFCS (total: r s = 0.392, p ≤ 0.001; bCP: r s = 0.316, p ≤ 0.05; uCP: r s = 0.331, p ≤ 0.05). The laterality scores of the hemispheres in the total group correlated negatively to the GMFCS level (r s = -0.523, p ≤ 0.001) and the GVS-knee sagittal (r s = -0.311, p ≤ 0.01). Lesion location, for the total group demonstrated positive correlations between parietal lobe involvement and the GPS (r s = 0.321, p ≤ 0.001) and between periventricular layer damage and the GMFCS (r s = 0.348, p ≤ 0.001). Involvement of the anterior part of the corpus callosum (CC) was associated with the GVS-hip sagittal in all groups (total: r pb = 0.495, p ≤ 0.001; bCP: r pb = 0.357, p ≤ 0.05; uCP: r pb = 0.641, p ≤ 0.001). The global total hemispheric and laterality of the hemispheres scores differentiated between the minor and both the extension (p ≤ 0.001 and p ≤ 0.001) and flexion (p = 0.016 and p = 0.013, respectively) MJ patterns in the total group. Maximal periventricular involvement and CC intactness were associated with extension patterns (p ≤ 0.05 and p ≤ 0.001, respectively). Current findings demonstrated relationships between brain structure and motor function as well as pathological gait, in this cohort of children with CP. These results might facilitate the timely identification of gait pathology and, ultimately, guide individualized treatment planning of gait impairments in children with CP.

Dataset Information

An Unsupervised Data-Driven Model to Classify Gait Patterns in Children with Cerebral Palsy.

Publications

An Unsupervised Data-Driven Model to Classify Gait Patterns in Children with Cerebral Palsy.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets