Related Experiment Video
Updated: Dec 6, 2025
Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable
Published on: May 17, 2024
Computer Vision to Automatically Assess Infant Neuromotor Risk
Insights
This study introduces an automated method using video analysis to detect infants at risk for neuromotor impairment. The open-source toolkit offers a low-cost, accessible solution for early detection, improving outcomes for at-risk infants.
Area of Science:
- Pediatrics
- Developmental Neuroscience
- Biomedical Engineering
Background:
- Neuromotor impairment risk in infants is typically assessed via manual clinical observation.
- Current methods often miss at-risk infants, especially in resource-limited settings.
- Automated, quantitative assessments using accessible technology are needed.
Purpose of the Study:
- To develop an automated method for assessing infant neuromotor impairment risk.
- To utilize body pose and movement kinematics from mobile device videos.
- To establish a quantitative, low-cost screening tool.
Main Methods:
- Extracted body poses and movement kinematics from videos of at-risk infants (N=19).
- Calculated deviation from healthy infants (N=85) using a Naïve Gaussian Bayesian Surprise metric.
- Pre-registered all Bayesian Surprise calculations for transparency.
Main Results:
- Infants identified as high-risk for neuromotor impairment showed significant deviation from the healthy cohort.
- The Bayesian Surprise metric effectively differentiated at-risk infants.
- The method demonstrated promise in identifying developmental risks.
Conclusions:
- Automated video analysis offers a viable approach for early neuromotor impairment detection.
- The developed open-source toolkit provides a scalable and affordable screening solution.
- This technology can improve early intervention accessibility for at-risk infants globally.
Abstract:
An infant's risk of developing neuromotor impairment is primarily assessed through visual examination by specialized clinicians. Therefore, many infants at risk for impairment go undetected, particularly in under-resourced environments. There is thus a need to develop automated, clinical assessments based on quantitative measures from widely-available sources, such as videos recorded on a mobile device. Here, we automatically extract body poses and movement kinematics from the videos of at-risk infants (N = 19). For each infant, we calculate how much they deviate from a group of healthy infants (N = 85 online videos) using a Naïve Gaussian Bayesian Surprise metric. After pre-registering our Bayesian Surprise calculations, we find that infants who are at high risk for impairments deviate considerably from the healthy group. Our simple method, provided as an open-source toolkit, thus shows promise as the basis for an automated and low-cost assessment of risk based on video recordings.
