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

You might also read

Related Articles

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

Sort by
Same author

Telerehabilitation in children and adolescents with intellectual disability: a systematic review.

Frontiers in psychiatry·2026
Same author

Costs of autism spectrum disorders and access to services in Spain.

BMC health services research·2026
Same author

Mapping, displaying, and facilitating access to autism services: an Italian eHealth solution.

International journal of medical informatics·2026
Same author

Autism-like phenotypes and increased NMDAR2D expression in mice with KDM5B histone lysine demethylase deficiency.

Science advances·2026
Same author

Towards a Closed-Loop Bioengineering Framework for Immersive VR-Based Telerehabilitation Integrating Wearable Biosensing and Adaptive Feedback.

Bioengineering (Basel, Switzerland)·2026
Same author

Comprehensive geriatric assessment and management in primary care: a systematic literature review with a descriptive mapping of team composition and assessment instruments.

Frontiers in public health·2026

Related Experiment Video

Updated: May 31, 2025

Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable
09:24

Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable

Published on: May 17, 2024

1.3K

Marker-Less Video Analysis of Infant Movements for Early Identification of Neurodevelopmental Disorders.

Roberta Bruschetta1, Angela Caruso2, Martina Micai2

  • 1Italian National Research Council, Institute for Biomedical Research and Innovation, Via Leanza, Istituto Marino, 98164 Messina, Italy.

Diagnostics (Basel, Switzerland)
|January 25, 2025
PubMed
Summary

Early detection of neurodevelopmental disorders (NDDs) is possible using AI analysis of infant movements. Specific lower limb movement patterns at 10 days old can predict NDDs with high accuracy.

Keywords:
analysis of infants’ movementsartificial intelligenceautomatic motion trackingdeep learningearly identification of neurodevelopmental disordersneurodevelopmental disorders

More Related Videos

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
11:14

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

10.9K
Frame-by-Frame Video Analysis of Idiosyncratic Reach-to-Grasp Movements in Humans
10:51

Frame-by-Frame Video Analysis of Idiosyncratic Reach-to-Grasp Movements in Humans

Published on: January 15, 2018

8.3K

Related Experiment Videos

Last Updated: May 31, 2025

Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable
09:24

Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable

Published on: May 17, 2024

1.3K
A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
11:14

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

10.9K
Frame-by-Frame Video Analysis of Idiosyncratic Reach-to-Grasp Movements in Humans
10:51

Frame-by-Frame Video Analysis of Idiosyncratic Reach-to-Grasp Movements in Humans

Published on: January 15, 2018

8.3K

Area of Science:

  • Developmental neuroscience
  • Computational neuroscience
  • Pediatric neurology

Background:

  • Early identification of neurodevelopmental disorders (NDDs) is critical for timely intervention and improved outcomes.
  • Deficits in spontaneous infant movements are linked to later NDD development.
  • Marker-less AI offers a novel approach for objective infant movement assessment.

Purpose of the Study:

  • To develop and validate an AI-based system for automatic assessment of infant movements from single-camera videos.
  • To identify early kinematic markers of NDDs in high-risk infants.
  • To evaluate the accuracy and reliability of the AI system compared to existing methods.

Main Methods:

  • Utilized deep learning for marker-less automatic motion tracking of 74 high-risk infants from the NIDA database.
  • Extracted kinematic parameters from video recordings at five time points (10 days to 24 weeks).
  • Employed Support Vector Machine (SVM) for classification and compared tracking accuracy with a validated semi-automatic algorithm (Movidea).

Main Results:

  • Significant differences in lower limb movement features ('Median Velocity', 'Area differing from moving average', 'Periodicity') were observed at 10 days in infants later diagnosed with NDDs.
  • The SVM model achieved 85% accuracy, 64% sensitivity, and 100% specificity for NDD detection.
  • Movement disparities decreased over time; AI tracking showed high correlation (R=93.96%) and low RMSE (9.52 pixels) compared to Movidea.

Conclusions:

  • AI-powered movement analysis shows significant potential for the early detection of NDDs in infants.
  • Specific early-life kinematic markers in lower limb movements can aid in identifying infants at risk.
  • This non-invasive AI approach provides valuable insights into infant motor development for early intervention strategies.