Gaze-based classification of autism spectrum disorder

Fabiano, Diego; Canavan, Shaun; Agazzi, Heather; Hinduja, Saurabh; Goldgof, Dmitry B.

doi:10.1016/j.patrec.2020.04.028

Cited by 14 publications

(20 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, gaze integration is already a prominent goal in early intervention programs [ 21 ]. Learning appropriate gaze modulation early in social interaction may enhance success in many domains and potentially improve intervention outcomes of young children with ASD [ 29 , 30 ].…”

Section: Introductionmentioning

confidence: 99%

“…Additionally, examples of the role of gaze patterns in defining different shadings of the spectrum are also lacking in terms of a functional perspective. Most studies focused on discriminating between those diagnosed with ASD and typically developing peers [ 30 , 34 , 42 ]. To the best of our knowledge, very few studies have investigated the role of gaze in stratifying the autism spectrum.…”

Section: Introductionmentioning

confidence: 99%

“…The results of this work confirm that gaze analysis may have an interesting clinical role, both in addressing spectrum heterogeneity and as a predictor of outcome [ 43 ]. In a different approach, Fabiano and colleagues [ 30 ] used a combination of hand-crafted and raw gaze variables with demographic characteristics [ 44 , 45 ], such as age and gender, to classify multiple levels of ASD risk. Features included the location and duration of gaze fixations measured by eye-tracking in children between 6 and 132 months of age.…”

Section: Introductionmentioning

confidence: 99%

“…The results confirmed the potential of gaze as an indicator that needs to be further explored by investigating the presence of sub-groups within children with ASD. In addition, the analyses showed that age is an important factor in classifying ASD risk, resulting in an overall accuracy of 93.45% [ 30 ]. More recently, Latrèche and colleagues [ 46 ] investigated the role of social orientation in modulating treatment outcomes in preschool children with ASD.…”

Section: Introductionmentioning

confidence: 99%

“…Overall, the results are promising and highlight the importance of social-attentive skills in categorizing the autism spectrum and for predicting treatment outcomes [ 30 , 43 , 46 ]. Gazing may be a relevant feature, but further investigations and less intrusive methodologies are needed.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

EYE-C: Eye-Contact Robust Detection and Analysis during Unconstrained Child-Therapist Interactions in the Clinical Setting of Autism Spectrum Disorders

2021

View full text Add to dashboard Cite

The high level of heterogeneity in Autism Spectrum Disorder (ASD) and the lack of systematic measurements complicate predicting outcomes of early intervention and the identification of better-tailored treatment programs. Computational phenotyping may assist therapists in monitoring child behavior through quantitative measures and personalizing the intervention based on individual characteristics; still, real-world behavioral analysis is an ongoing challenge. For this purpose, we designed EYE-C, a system based on OpenPose and Gaze360 for fine-grained analysis of eye-contact episodes in unconstrained therapist-child interactions via a single video camera. The model was validated on video data varying in resolution and setting, achieving promising performance. We further tested EYE-C on a clinical sample of 62 preschoolers with ASD for spectrum stratification based on eye-contact features and age. By unsupervised clustering, three distinct sub-groups were identified, differentiated by eye-contact dynamics and a specific clinical phenotype. Overall, this study highlights the potential of Artificial Intelligence in categorizing atypical behavior and providing translational solutions that might assist clinical practice.

show abstract

Section: Introductionmentioning

confidence: 99%