Dataset Information

Face-Based Attention Recognition Model for Children with Autism Spectrum Disorder.

ABSTRACT: Attention recognition plays a vital role in providing learning support for children with autism spectrum disorders (ASD). The unobtrusiveness of face-tracking techniques makes it possible to build automatic systems to detect and classify attentional behaviors. However, constructing such systems is a challenging task due to the complexity of attentional behavior in ASD. This paper proposes a face-based attention recognition model using two methods. The first is based on geometric feature transformation using a support vector machine (SVM) classifier, and the second is based on the transformation of time-domain spatial features to 2D spatial images using a convolutional neural network (CNN) approach. We conducted an experimental study on different attentional tasks for 46 children (ASD n=20, typically developing children n=26) and explored the limits of the face-based attention recognition model for participant and task differences. Our results show that the geometric feature transformation using an SVM classifier outperforms the CNN approach. Also, attention detection is more generalizable within typically developing children than within ASD groups and within low-attention tasks than within high-attention tasks. This paper highlights the basis for future face-based attentional recognition for real-time learning and clinical attention interventions.

Supplementary information

The online version contains supplementary material available at 10.1007/s41666-021-00101-y.

SUBMITTER: Banire B

PROVIDER: S-EPMC8982782 | biostudies-literature | 2021 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Face-Based Attention Recognition Model for Children with Autism Spectrum Disorder.

Banire Bilikis B Al Thani Dena D Qaraqe Marwa M Mansoor Bilal B

Journal of healthcare informatics research 20210715 4

Attention recognition plays a vital role in providing learning support for children with autism spectrum disorders (ASD). The unobtrusiveness of face-tracking techniques makes it possible to build automatic systems to detect and classify attentional behaviors. However, constructing such systems is a challenging task due to the complexity of attentional behavior in ASD. This paper proposes a face-based attention recognition model using two methods. The first is based on geometric feature transfor ...[more]

PMID: 35415454

Similar Datasets

Project description:Attention Deficit Hyperactivity Disorder (ADHD) and Autism Spectrum Disorders (ASD) are two of the most represented neurodevelopmental conditions in childhood. The diagnostic shift introduced by the DSM-5, allowing a combined diagnosis of ADHD and ASD, poses different clinical challenges related to diagnostic overshadowing, accuracy of clinical judgment and potential delay in an ASD diagnosis in children presenting with ADHD. Here we tried to disentangle the clinical phenotype and specificity of the two co-occurring conditions in relation to autism traits and empathy, by comparing children with ASD with and without comorbid ADHD with children presenting ADHD only and children with typical development. The child versions of the Autism Quotient (C-AQ) and Empathy Quotient (C-EQ) were administered to a total sample of 198 male children between 6 and 14 years old with age appropriate language skills and normal intelligence. Univariate analysis demonstrated no significant differences in the C-AQ total and subscale scores as well as the C-EQ between children with ASD and children with ASD + ADHD, while children with ADHD alone presented an intermediate phenotype between ASD and TD. Furthermore, a receiver operating characteristic (ROC) analysis was applied to discriminate among the different phenotypes. We found that the C-AQ and C-EQ were accurate at distinguishing with satisfactory reliability between: (a) ASD vs. non- ASD (N-ASD) groups comprising both ADHD and TD children (Area Under the Curve AUC 88% for C-AQ and 81% for C-EQ); (b) ASD and TD (AUC 92% for C-AQ and 95% for C-EQ); (c) ASD and ADHD (AUC 80% for C-AQ and 68% for C-EQ). Our data confirm the reliability of the C-AQ and C-EQ as behavioral markers to differentiate ASD (regardless of comorbid ADHD) from an ADHD condition and TD. Interestingly, in our sample an ADHD condition does not increase the severity of the clinical phenotype in terms of autism traits distribution and empathy, suggesting that the psychological measures detected by the two quantitative instruments are independent of ADHD traits. This evidence will contribute to the translational efforts in developing better tailored treatments and preventive strategies.

Project description:ImportanceEnhanced selective attention toward nonsocial objects and impaired attention to social stimuli constitute key clinical features of autism spectrum disorder (ASD). Yet, the mechanisms associated with atypical selective attention in ASD are poorly understood, which limits the development of more effective interventions. In typically developing individuals, selective attention to social and nonsocial stimuli is associated with the informational value of the stimuli, which is typically learned over the course of repeated interactions with the stimuli.ObjectiveTo examine value learning (VL) of social and nonsocial stimuli and its association with selective attention in preschoolers with and without ASD.Design, setting, and participantsThis case-control study compared children with ASD vs children with developmental delay (DD) and children with typical development (TD) recruited between March 3, 2017, and June 13, 2018, at a university-based research laboratory. Participants were preschoolers with ASD, DD, or TD.Main outcomes and measuresProcedure consisted of an eye-tracking gaze-contingent VL task involving social (faces) and nonsocial (fractals) stimuli and consisting of baseline, training, and choice test phases. Outcome measures were preferential attention to stimuli reinforced (high value) vs not reinforced (low value) during training. The hypotheses were stated before data collection.ResultsIncluded were 115 preschoolers with ASD (n = 48; mean [SD] age, 38.30 [15.55] months; 37 [77%] boys), DD (n = 31; mean [SD] age, 45.73 [19.49] months; 19 [61%] boys), or TD (n = 36; mean [SD] age, 36.53 [12.39] months; 22 [61%] boys). The groups did not differ in sex distribution; participants with ASD or TD had similar chronological age; and participants with ASD or DD had similar verbal IQ and nonverbal IQ. After training, the ASD group showed preference for the high-value nonsocial stimuli (mean proportion, 0.61 [95% CI, 0.56-0.65]; P < .001) but not for the high-value social stimuli (mean proportion, 0.51 [95% CI, 0.46-0.56]; P = .58). In contrast, the DD and TD groups demonstrated preference for the high-value social stimuli (DD mean proportion, 0.59 [95% CI, 0.54-0.64]; P = .001 and TD mean proportion, 0.57 [95% CI, 0.53-0.61]; P = .002) but not for the high-value nonsocial stimuli (DD mean proportion, 0.52 [95% CI, 0.44-0.59]; P = .64 and TD mean proportion, 0.50 [95% CI, 0.44-0.57]; P = .91). Controlling for age and nonverbal IQ, autism severity was positively correlated with enhanced learning in the nonsocial domain (r = 0.22; P = .03) and with poorer learning in the social domain (r = -0.26; P = .01).Conclusions and relevanceIncreased attention to objects in preschoolers with ASD may be associated with enhanced VL in the nonsocial domain. When paired with poor VL in the social domain, enhanced value-driven attention to objects may play a formative role in the emergence of autism symptoms by altering attentional priorities and thus learning opportunities in affected children.

Dataset Information

Face-Based Attention Recognition Model for Children with Autism Spectrum Disorder.

Supplementary information

Publications

Face-Based Attention Recognition Model for Children with Autism Spectrum Disorder.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets