Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Naturalistic Observations02:30

Naturalistic Observations

If you want to understand how behavior occurs, one of the best ways to gain information is to simply observe the behavior in its natural context. However, people might change their behavior in unexpected ways if they know they are being observed. How do researchers obtain accurate information when people tend to hide their natural behavior? As an example, imagine that your professor asks everyone in your class to raise their hand if they always wash their hands after using the restroom. Chances...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Epilepsy in autism spectrum disorder: examining prevalence and associated factors in a large cross-sectional study.

Journal of neurodevelopmental disorders·2026
Same author

Impact of COVID-19 pandemic on autism spectrum disorder service providers in Qatar: challenges, insights, and lessons learned.

Frontiers in psychiatry·2026
Same author

A multi-method phenotypic study of sex differences in pragmatic language in autism.

Frontiers in psychiatry·2026
Same author

Development and Validation of a Short Version Eye-Tracking Paradigm for the Screening and Diagnosis of Autism Spectrum Disorder in Qatar.

Autism research : official journal of the International Society for Autism Research·2026
Same author

Real-world application of an eye-tracking device for autism screening and diagnosis: a short report from public demonstrations in Qatar, Dubai and the U.S.

BMC psychiatry·2026
Same author

Exploring the Association Between Parental Age and Autism Spectrum Disorder Risk in Qatar.

Journal of autism and developmental disorders·2026

Related Experiment Video

Updated: Jun 30, 2026

Eye Tracking Young Children with Autism
09:03

Eye Tracking Young Children with Autism

Published on: March 27, 2012

A naturalistic, non-invasive method for capturing biometric data during autism evaluations.

Khaleel Kamal1, Janka Hatvani1, Máté Pethő1

  • 1Argus Cognitive, Inc., Hanover, NH, United States.

Frontiers in Psychiatry
|June 29, 2026
PubMed
Summary

A new machine learning tool accurately analyzes social communication features to help diagnose autism spectrum disorder (ASD) in children. This technology shows promise for supporting clinical assessments in diverse populations.

Keywords:
ASDautism spectrum disorderbehavioral analysisbiometric datadiagnostic supportmachine learningpediatrics

More Related Videos

A Familiarization Protocol Facilitates the Participation of Children with ASD in Electrophysiological Research
08:42

A Familiarization Protocol Facilitates the Participation of Children with ASD in Electrophysiological Research

Published on: July 31, 2017

EEG Mu Rhythm in Typical and Atypical Development
11:50

EEG Mu Rhythm in Typical and Atypical Development

Published on: April 9, 2014

Related Experiment Videos

Last Updated: Jun 30, 2026

Eye Tracking Young Children with Autism
09:03

Eye Tracking Young Children with Autism

Published on: March 27, 2012

A Familiarization Protocol Facilitates the Participation of Children with ASD in Electrophysiological Research
08:42

A Familiarization Protocol Facilitates the Participation of Children with ASD in Electrophysiological Research

Published on: July 31, 2017

EEG Mu Rhythm in Typical and Atypical Development
11:50

EEG Mu Rhythm in Typical and Atypical Development

Published on: April 9, 2014

Area of Science:

  • Computational psychiatry
  • Developmental neuroscience
  • Machine learning in healthcare

Background:

  • Autism spectrum disorder (ASD) diagnosis relies on observing social communication deficits.
  • Current diagnostic methods can be subjective and time-consuming.
  • Objective, quantitative tools are needed to aid in ASD assessment.

Purpose of the Study:

  • To evaluate a machine learning tool for non-intrusively analyzing biometric data (gaze, facial expressions, vocalizations) during autism assessments.
  • To determine the diagnostic accuracy of this multimodal tool in identifying ASD in a diverse cohort of children.
  • To assess the tool's ability to differentiate ASD from neurotypical (NT) individuals and other neurodevelopmental conditions.

Main Methods:

  • Enrolled 546 participants (ages 2-12) across the USA and Qatar, with 458 included in the analysis.
  • Utilized Random Forest classifiers trained on 97 biometric features from video, audio, and gaze data.
  • Employed a developmentally-adaptive approach with separate models for different speech development groups.
  • Assessed performance using leave-one-out cross-validation and an independent hold-out test set.

Main Results:

  • Achieved 77.8% sensitivity and specificity for classifying ASD versus non-ASD in the initial set.
  • Distinguishing ASD from NT participants alone yielded 82.0% sensitivity and specificity.
  • In the hold-out test set, the model showed 62.3% sensitivity and 81.4% specificity for ASD vs. non-ASD.
  • Performance varied by sex, with males showing higher sensitivity and females higher specificity.

Conclusions:

  • Semi-automated multimodal computational analysis is feasible for quantifying autism-related social communication behaviors.
  • The tool shows promise in distinguishing ASD from NT individuals in diverse clinical and ethnic samples.
  • Further development is needed to address differential diagnosis challenges with non-ASD neurodevelopmental conditions.