Dataset Information

A Novel Deep Learning Approach for Recognizing Stereotypical Motor Movements within and across Subjects on the Autism Spectrum Disorder.

ABSTRACT: Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder characterized by persistent difficulties including repetitive patterns of behavior known as stereotypical motor movements (SMM). So far, several techniques have been implemented to track and identify SMMs. In this context, we propose a deep learning approach for SMM recognition, namely, convolutional neural networks (CNN) in time and frequency-domains. To solve the intrasubject SMM variability, we propose a robust CNN model for SMM detection within subjects, whose parameters are set according to a proper analysis of SMM signals, thereby outperforming state-of-the-art SMM classification works. And, to solve the intersubject variability, we propose a global, fast, and light-weight framework for SMM detection across subjects which combines a knowledge transfer technique with an SVM classifier, therefore resolving the "real-life" medical issue associated with the lack of supervised SMMs per testing subject in particular. We further show that applying transfer learning across domains instead of transfer learning within the same domain also generalizes to the SMM target domain, thus alleviating the problem of the lack of supervised SMMs in general.

SUBMITTER: Sadouk L

PROVIDER: S-EPMC6077579 | biostudies-other | 2018

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

A Novel Deep Learning Approach for Recognizing Stereotypical Motor Movements within and across Subjects on the Autism Spectrum Disorder.

Sadouk Lamyaa L Gadi Taoufiq T Essoufi El Hassan EH

Computational intelligence and neuroscience 20180710

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder characterized by persistent difficulties including repetitive patterns of behavior known as stereotypical motor movements (SMM). So far, several techniques have been implemented to track and identify SMMs. In this context, we propose a deep learning approach for SMM recognition, namely, convolutional neural networks (CNN) in time and frequency-domains. To solve the intrasubject SMM variability, we propose a robust CNN model for SMM ...[more]

PMID: 30111994

Similar Datasets

Project description:Reaching and grasping (prehension) is one of the earliest developing motor skills in humans, but continued prehension development in childhood and adolescence enables the performance of increasingly complex manual tasks. In individuals with autism spectrum disorder (ASD) atypical unimanual reaching and grasping has been reported, but to date, no studies have investigated discrete bimanual movements. We examined unimanual and bimanual reach to grasp tasks in youth with ASD to better understand how motor performance might change with increasing complexity. Twenty youth with ASD (10.1 ± 2.4 years) and 17 youth with typical development (TD) (9.6 ± 2.6 years) were instructed to reach and grasp cubes that became illuminated. Participants were asked to reach out with the right and/or left hands to grasp and lift targets located at near (18 cm) and/or far (28 cm) distances. For the unimanual (simplest) condition, participants grasped one illuminated cube (with either the left or right hand). For the bimanual conditions, participants grasped two illuminated cubes located at the same distance from the start position (bimanual symmetric condition) or two illuminated cubes located at different distances (bimanual asymmetric condition). Significant interactions among diagnostic group, task complexity, and age were found for initiation time (IT) and movement time (MT). Specifically, the older children in both groups initiated and performed their movements faster in the unimanual condition than in the bimanual conditions, although the older children with ASD produced slower ITs and MTs compared to typically developing peers across all three conditions. Surprisingly, the younger children with ASD had similar ITs and MTs as their peers for the unimanual condition but did not considerably slow these times to adjust for the complexity of the bimanual tasks. We hypothesize that they chose to re-use the motor plans that were generated for the unimanual trials rather than generate more appropriate motor plans for the bimanual tasks. An atypical spatiotemporal relationship between MT and peak aperture (PA) was also found in the ASD group. Together, our results suggest deficits in motor planning that result in subtle effects on performance in younger children with ASD that become more pronounced with age.

Project description:BackgroundIn the United States, about 3 million people have autism spectrum disorder (ASD), and around 1 out of 59 children are diagnosed with ASD. People with ASD have characteristic social communication deficits and repetitive behaviors. The causes of this disorder remain unknown; however, in up to 25% of cases, a genetic cause can be identified. Detecting ASD as early as possible is desirable because early detection of ASD enables timely interventions in children with ASD. Identification of ASD based on objective pathogenic mutation screening is the major first step toward early intervention and effective treatment of affected children.ObjectiveRecent investigation interrogated genomics data for detecting and treating autism disorders, in addition to the conventional clinical interview as a diagnostic test. Since deep neural networks perform better than shallow machine learning models on complex and high-dimensional data, in this study, we sought to apply deep learning to genetic data obtained across thousands of simplex families at risk for ASD to identify contributory mutations and to create an advanced diagnostic classifier for autism screening.MethodsAfter preprocessing the genomics data from the Simons Simplex Collection, we extracted top ranking common variants that may be protective or pathogenic for autism based on a chi-square test. A convolutional neural network-based diagnostic classifier was then designed using the identified significant common variants to predict autism. The performance was then compared with shallow machine learning-based classifiers and randomly selected common variants.ResultsThe selected contributory common variants were significantly enriched in chromosome X while chromosome Y was also discriminatory in determining the identification of autistic individuals from nonautistic individuals. The ARSD, MAGEB16, and MXRA5 genes had the largest effect in the contributory variants. Thus, screening algorithms were adapted to include these common variants. The deep learning model yielded an area under the receiver operating characteristic curve of 0.955 and an accuracy of 88% for identifying autistic individuals from nonautistic individuals. Our classifier demonstrated a considerable improvement of ~13% in terms of classification accuracy compared to standard autism screening tools.ConclusionsCommon variants are informative for autism identification. Our findings also suggest that the deep learning process is a reliable method for distinguishing the diseased group from the control group based on the common variants of autism.

Dataset Information

A Novel Deep Learning Approach for Recognizing Stereotypical Motor Movements within and across Subjects on the Autism Spectrum Disorder.

Publications

A Novel Deep Learning Approach for Recognizing Stereotypical Motor Movements within and across Subjects on the Autism Spectrum Disorder.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets