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

Feasibility of the Baby Moves app for remote General Movements Assessment: a prospective observational cohort study in an Italian infant population.

BMJ paediatrics open·2026
Same author

Long-term motor outcomes after parent-administered early physiotherapy in children born very preterm.

Early human development·2026
Same author

Impaired toilet training and bladder and bowel dysfunction in children with developmental coordination disorder - an underreported issue.

Journal of pediatric urology·2026
Same author

Concurrent validity and agreement of Bayley-4, AIMS, and HINE assessments in 1-year-old children.

Developmental medicine and child neurology·2026
Same author

Family: a powerful modifier of outcome.

Pediatric research·2026
Same author

Empowering parents in early motor interventions for infants born preterm: insights from the Norwegian physical therapy study in preterm infants through the lens of a critical interpretative synthesis.

Frontiers in psychology·2026

Related Experiment Video

Updated: Sep 5, 2025

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

11.0K

Development and Validation of a Deep Learning Method to Predict Cerebral Palsy From Spontaneous Movements in Infants

Daniel Groos1, Lars Adde2,3, Sindre Aubert4

  • 1Department of Neuromedicine and Movement Science, Norwegian University of Science and Technology, Trondheim, Norway.

JAMA Network Open
|July 11, 2022
PubMed
Summary

A new deep learning method accurately predicts cerebral palsy (CP) in infants using videos of their movements. This AI tool shows promise for early detection and intervention, improving outcomes for high-risk newborns.

More Related Videos

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

1.6K
Event-related Potentials During Target-response Tasks to Study Cognitive Processes of Upper Limb Use in Children with Unilateral Cerebral Palsy
08:26

Event-related Potentials During Target-response Tasks to Study Cognitive Processes of Upper Limb Use in Children with Unilateral Cerebral Palsy

Published on: January 11, 2016

12.2K

Related Experiment Videos

Last Updated: Sep 5, 2025

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

11.0K
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

1.6K
Event-related Potentials During Target-response Tasks to Study Cognitive Processes of Upper Limb Use in Children with Unilateral Cerebral Palsy
08:26

Event-related Potentials During Target-response Tasks to Study Cognitive Processes of Upper Limb Use in Children with Unilateral Cerebral Palsy

Published on: January 11, 2016

12.2K

Area of Science:

  • Neurology
  • Artificial Intelligence in Medicine
  • Developmental Pediatrics

Background:

  • Early identification of cerebral palsy (CP) is crucial for timely intervention, but current expert-based assessments are not widely accessible.
  • Conventional machine learning methods for CP prediction have shown limitations in validity.
  • There is a need for objective, scalable tools for early CP detection in high-risk infants.

Purpose of the Study:

  • To develop and externally validate a novel deep learning (DL) model for predicting CP.
  • To assess the DL model's performance using videos of infant spontaneous movements at 9 to 18 weeks' corrected age.
  • To compare the DL model's accuracy against the General Movement Assessment (GMA) tool and conventional machine learning.

Main Methods:

  • A prognostic study involving 557 high-risk infants from multiple international sites.
  • Infants underwent video recording of spontaneous movements at 9-18 weeks' corrected age.
  • A deep learning model was trained and validated using video data to predict CP status at older ages.

Main Results:

  • The DL-based CP prediction method demonstrated strong external validation performance with 71.4% sensitivity and 94.1% specificity.
  • The DL method achieved higher accuracy (90.6%) compared to conventional machine learning (72.7%) but similar accuracy to the GMA tool (85.9%).
  • The DL model showed higher sensitivity for predicting nonambulatory and spastic bilateral CP subtypes.

Conclusions:

  • A deep learning-based method shows significant predictive accuracy for CP in infants based on early movement videos.
  • This AI-driven approach offers a potential pathway for objective, early detection of CP in clinical practice.
  • Further integration of such tools could enhance early intervention strategies and improve long-term outcomes for affected children.