Interpretable classification for multivariate gait analysis of cerebral palsy
Ontology highlight
ABSTRACT:
SUBMITTER: Yoon C
PROVIDER: S-EPMC10664661 | biostudies-literature | 2023 Jan
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:AimTo determine the features cited by motor phenotyping experts when identifying dystonia in people with cerebral palsy (CP).MethodDystonia identification in CP, particularly when comorbid with spasticity, can be difficult. The dystonia diagnostic criterion standard remains subjective visual identification by expert consensus. For this qualitative study, we conducted an inductive thematic analysis of consensus-building discussions between three pediatric movement disorder physicians as they identified the presence or absence of dystonia in gait videos of 40 participants with spastic CP and periventricular leukomalacia.ResultsUnanimous consensus about the presence or absence of dystonia was achieved for 34 out of 40 videos. Two main themes were present during consensus-building discussions as videos were evaluated for dystonia: (1) unilateral leg or foot adduction that was variable over time, and (2) difficulty in identifying dystonia. Codes contributing to the first theme were more likely to be cited by a discussant when they felt dystonia was present (as opposed to absent) in a video (χ2 test, p=0.004).DiscussionThese results describe the gait features cited by experts during consensus-building discussion as they identify dystonia in ambulatory people with CP. Qualitative thematic analysis of these discussions could help codify the subjective process of dystonia diagnosis.
| S-EPMC9665896 | biostudies-literature
Project description:BackgroundThis study aimed to improve the automatic probabilistic classification of joint motion gait patterns in children with cerebral palsy by using the expert knowledge available via a recently developed Delphi-consensus study. To this end, this study applied both Naïve Bayes and Logistic Regression classification with varying degrees of usage of the expert knowledge (expert-defined and discretized features). A database of 356 patients and 1719 gait trials was used to validate the classification performance of eleven joint motions.HypothesesTwo main hypotheses stated that: (1) Joint motion patterns in children with CP, obtained through a Delphi-consensus study, can be automatically classified following a probabilistic approach, with an accuracy similar to clinical expert classification, and (2) The inclusion of clinical expert knowledge in the selection of relevant gait features and the discretization of continuous features increases the performance of automatic probabilistic joint motion classification.FindingsThis study provided objective evidence supporting the first hypothesis. Automatic probabilistic gait classification using the expert knowledge available from the Delphi-consensus study resulted in accuracy (91%) similar to that obtained with two expert raters (90%), and higher accuracy than that obtained with non-expert raters (78%). Regarding the second hypothesis, this study demonstrated that the use of more advanced machine learning techniques such as automatic feature selection and discretization instead of expert-defined and discretized features can result in slightly higher joint motion classification performance. However, the increase in performance is limited and does not outweigh the additional computational cost and the higher risk of loss of clinical interpretability, which threatens the clinical acceptance and applicability.
| S-EPMC5453476 | biostudies-literature
Project description:Virtual-reality-based training can influence gait recovery in children with cerebral palsy. A consensus concerning its influence on spatiotemporal gait parameters and effective training dosage is still warranted. This study analyzes the influence of virtual-reality training (relevant training dosage) on gait recovery in children with cerebral palsy. A search was performed by two reviewers according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines on nine databases: PEDro, EBSCO, PubMed, Cochrane, Web of Science, EMBASE, ICI, Scopus, and PROQUEST. Of 989 records, 16 studies involving a total of 274 children with cerebral palsy met our inclusion criteria. Eighty-eight percent of the studies reported significant enhancements in gait performance after training with virtual reality. Meta-analyses revealed positive effects of virtual-reality training on gait velocity (Hedge's g = 0.68), stride length (0.30), cadence (0.66), and gross motor function measure (0.44). Subgroup analysis reported a training duration of 20-30 min per session, ≤4 times per week across ≥8 weeks to allow maximum enhancements in gait velocity. This study provides preliminary evidence for the beneficial influence of virtual-reality training in gait rehabilitation for children with cerebral palsy.
| S-EPMC6448032 | biostudies-literature
Project description:UnlabelledBackgroundEarly classification of time series is beneficial for biomedical informatics problems such including, but not limited to, disease change detection. Early classification can be of tremendous help by identifying the onset of a disease before it has time to fully take hold. In addition, extracting patterns from the original time series helps domain experts to gain insights into the classification results. This problem has been studied recently using time series segments called shapelets. In this paper, we present a method, which we call Multivariate Shapelets Detection (MSD), that allows for early and patient-specific classification of multivariate time series. The method extracts time series patterns, called multivariate shapelets, from all dimensions of the time series that distinctly manifest the target class locally. The time series were classified by searching for the earliest closest patterns.ResultsThe proposed early classification method for multivariate time series has been evaluated on eight gene expression datasets from viral infection and drug response studies in humans. In our experiments, the MSD method outperformed the baseline methods, achieving highly accurate classification by using as little as 40%-64% of the time series. The obtained results provide evidence that using conventional classification methods on short time series is not as accurate as using the proposed methods specialized for early classification.ConclusionFor the early classification task, we proposed a method called Multivariate Shapelets Detection (MSD), which extracts patterns from all dimensions of the time series. We showed that the MSD method can classify the time series early by using as little as 40%-64% of the time series' length.
| S-EPMC3475011 | biostudies-literature
Project description:Background and purposeInstrumented 3-D gait analyses (GA) in children with cerebral palsy (CP) have shown improved gait function 1 year postoperatively. Using GA, we assessed the outcome after 5 years and evaluated parental satisfaction with the surgery and the need for additional surgery.Patients and methods34 ambulatory children with spastic diplegia had preoperative GA. Based on this GA, the children underwent 195 orthopedic procedures on their lower limbs at a mean age of 11.6 (6-19) years. On average, 5.7 (1-11) procedures per child were performed. Outcome measures were evaluation of gait quality using the gait profile score (GPS) and selected kinematic parameters, functional level using the functional mobility scale (FMS), and the degree of parental satisfaction.ResultsThe mean GPS improved from 20.7° (95% CI: 19-23) preoperatively to 15.4° (95% CI: 14-17) 5 years postoperatively. There was no significant change in GPS between 1 and 5 years. The individual kinematic parameters at the ankle, knee, and hip improved statistically significantly, as did gait function (FMS). The mean parental satisfaction, on a scale from 0 to 10, was 7.7 (2-10) points. There was a need for additional surgical procedures in 14 children; this was more frequent in those who had the index operation at an early age.InterpretationThe main finding was that orthopedic surgery based on preoperative GA gave marked improvements in gait function and quality, which were stable over a 5-year period. Nevertheless, additional orthopedic procedures were necessary in almost half of the children and further follow-up with GA for more than 1 year postoperatively is recommended in children with risk factors for such surgery.
| S-EPMC4513609 | biostudies-literature
Project description:PurposeA flexed knee gait is a common gait in children with unilateral cerebral palsy. In children without knee contracture, hamstring spasticity is commonly considered a major contributor to a flexed knee gait. We hypothesized that the popliteal angle would not correlate to a flexed knee gait.MethodsThis retrospective study included 109 children with unilateral cerebral palsy who had undergone complete 3D gait analysis. Children who had previous surgery or knee flexion contracture were excluded. Children were divided into three groups based on knee position during stance as determined by 3D gait analysis: flexion (FK, 47), hyperextension (HK, 42), and normal (NK, 20).ResultsThere were no significant correlations between popliteal angle and dynamic peak knee extension in stance or at initial contact. Similarly, peak dorsiflexion during the stance phase did not correlate with dynamic peak knee extension in stance (all p > 0.05). Significant differences were observed in foot position during stance between FK and HK groups, as well as in quick stretch dorsiflexion with the knee extended between HK and NK groups.ConclusionA flexed knee gait in children with unilateral cerebral palsy does not always correlate with the popliteal angle or dynamic ankle position in gait. These factors may contribute but are insufficient to explain all observed differences. A flexed knee gait likely involves a complex interplay of motor control, strength, spasticity, and lever arm dynamics, indicating that interventions at a single level may not fully improve dynamic knee extension.
| S-EPMC11907585 | biostudies-literature
Project description:Background and Objectives: Equinus is the most common deformity in children with cerebral palsy, and surgical lengthening of the gastrocsoleus muscle-tendon unit is the most commonly performed operation for children with cerebral palsy. Treatment outcomes of orthopaedic surgery can be measured objectively with three-dimensional gait analysis. This study examined the quality of evidence for gastrocsoleus lengthening surgery based on objective measures. Materials and Methods: A search was performed with Medline, Embase and PubMed from 1990 to 25 August 2020 using the keywords "cerebral palsy", "equinus", "surgery" and "gait analysis". Only studies of gastrocsoleus lengthening surgery using three-dimensional gait analysis were included, yielding 34 studies. Results: Fourteen studies reported swing phase kinematics and all studies reported a significant improvement. Rates of recurrent equinus and calcaneus were reported in 21 studies and varied widely based on follow-up period and surgical technique. Conclusions: Poor study quality and marked variability in study samples and interventions made comparison difficult. Future studies should consider prospective design, controls or comparison groups and more detailed breakdowns of outcomes by cerebral palsy subtype, sagittal gait pattern, and equinus type in order to allow more rigorous treatment recommendations to be made.
| S-EPMC7911110 | biostudies-literature
Project description:BackgroundInstrumented gait analysis (IGA) has been around for a long time but has never been shown to be useful for improving patient outcomes. In this study we demonstrate the potential utility of IGA by showing that machine learning models are better able to estimate treatment outcomes when they include both IGA and clinical (CLI) features compared to when they include CLI features alone.DesignWe carried out a retrospective analysis of data from ambulatory children diagnosed with cerebral palsy who were seen at least twice at our gait analysis center. Individuals underwent a variety of treatments (including no treatment) between sequential gait analyses. We fit Bayesian Additive Regression Tree (BART) models that estimated outcomes for mean stance foot progression to demonstrate the approach. We built two models: one using CLI features only, and one using CLI and IGA features. We then compared the models' performance in detail. We performed similar, but less detailed, analyses for a number of other outcomes. All results were based on independent test data from a 70%/30% training/testing split.ResultsThe IGA model was more accurate than the CLI model for mean stance-phase foot progression outcomes (RMSEIGA = 11∘, RMSECLI = 13∘) and explained more than 1.5 × as much of the variance (R2IGA = .45, R2CLI = .28). The IGA model outperformed the CLI model for every level of treatment complexity, as measured by number of simultaneous surgeries. The IGA model also exhibited superior performance for estimating outcomes of mean stance-phase knee flexion, mean stance-phase ankle dorsiflexion, maximum swing-phase knee flexion, gait deviation index (GDI), and dimensionless speed.InterpretationThe results show that IGA has the potential to be useful in the treatment planning process for ambulatory children diagnosed with cerebral palsy. We propose that the results of machine learning outcome estimators-including estimates of uncertainty-become the primary IGA tool utilized in the clinical process, complementing the standard medical practice of conducting a through patient history and physical exam, eliciting patient goals, reviewing relevant imaging data, and so on.
| S-EPMC11003627 | biostudies-literature
Project description:AimThe aim of this cross-sectional study was to measure the effect of dual tasks on gait stability in ambulant children with cerebral palsy (CP) compared to typically developing (TD) children.MethodsThe children of the CP (n = 20) and TD groups (n = 20) walked first without a dual task, then while counting forward and finally while alternatively naming fruits and animals (DTf/a). They then completed the same cognitive exercises while sitting comfortably. We calculated the distance between the foot placement estimator (FPE) and the real foot placement in the anterior direction (DFPEAP) and in the mediolateral direction (DFPEML) as a measure of gait stability, in a gait laboratory using an optoelectronic system. Cognitive scores were computed. Comparisons within and between groups were analysed with linear mixed models.ResultsThe dual task had a significant effect on the CP group in DFPEAP and DFPEML. The CP group was more affected than the TD group during dual task in the DFPEML. Children in both groups showed significant changes in gait stability during dual tasks.InterpretationThe impact of dual task on gait stability is possibly due to the sharing of attention between gait and the cognitive task. All children favoured a 'posture second' strategy during the dual task of alternatively naming animals and fruits. Children with CP increased their mediolateral stability during dual task.
| S-EPMC9216605 | biostudies-literature
Project description:Auditory entrainment can influence gait performance in movement disorders. The entrainment can incite neurophysiological and musculoskeletal changes to enhance motor execution. However, a consensus as to its effects based on gait in people with cerebral palsy is still warranted. A systematic review and meta-analysis were carried out to analyze the effects of rhythmic auditory cueing on spatiotemporal and kinematic parameters of gait in people with cerebral palsy. Systematic identification of published literature was performed adhering to Preferred Reporting Items for Systematic Reviews and Meta-Analyses and American Academy for Cerebral Palsy and Developmental Medicine guidelines, from inception until July 2017, on online databases: Web of Science, PEDro, EBSCO, Medline, Cochrane, Embase and ProQuest. Kinematic and spatiotemporal gait parameters were evaluated in a meta-analysis across studies. Of 547 records, nine studies involving 227 participants (108 children/119 adults) met our inclusion criteria. The qualitative review suggested beneficial effects of rhythmic auditory cueing on gait performance among all included studies. The meta-analysis revealed beneficial effects of rhythmic auditory cueing on gait dynamic index (Hedge's g=0.9), gait velocity (1.1), cadence (0.3), and stride length (0.5). This review for the first time suggests a converging evidence toward application of rhythmic auditory cueing to enhance gait performance and stability in people with cerebral palsy. This article details underlying neurophysiological mechanisms and use of cueing as an efficient home-based intervention. It bridges gaps in the literature, and suggests translational approaches on how rhythmic auditory cueing can be incorporated in rehabilitation approaches to enhance gait performance in people with cerebral palsy.
| S-EPMC5746070 | biostudies-literature