Related Experiment Video
Updated: Jul 2, 2025
Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable
Published on: May 17, 2024
Automated identification of abnormal infant movements from smart phone videos
E Passmore1,2,3,4, A L Kwong3,5,6, S Greenstein1
1Murdoch Children's Research Institute, Developmental Imaging, Melbourne, Australia.
Insights
A new deep-learning framework automates the General Movements (GMs) Assessment for early cerebral palsy (CP) detection. This AI tool analyzes infant videos, enabling timely diagnosis and intervention for improved outcomes in children with CP.
Area of Science:
- Neurology
- Developmental Pediatrics
- Artificial Intelligence in Healthcare
Background:
- Cerebral palsy (CP) is a leading cause of childhood physical disability, affecting approximately 2.1 per 1000 live births.
- Early diagnosis of CP is crucial for optimizing functional outcomes in affected children.
- The General Movements (GMs) Assessment is a validated tool for CP detection, but its widespread implementation is limited by the availability of trained assessors.
Purpose of the Study:
- To develop and validate a deep-learning framework for automating the General Movements (GMs) Assessment.
- To enable early and accessible screening for cerebral palsy using digital technologies.
Main Methods:
- Acquired 503 infant videos (12-18 weeks corrected age) via a smartphone app.
- Utilized deep learning to automatically label and track 18 key body points, adjusting for camera movement and infant size.
- Trained a machine learning model to predict GMs classification from body point movement data.
Main Results:
- Automated body point labeling achieved human-level accuracy (3.7 ± 5.2% error).
- The prediction model demonstrated strong performance with a cross-validated AUC of 0.80 ± 0.08 for predicting expert GMs classification.
- Achieved 76% ± 15% sensitivity for abnormal GMs and 94% ± 3% negative predictive value.
Conclusions:
- An automated deep-learning framework can accurately perform the GMs Assessment.
- This technology holds significant potential for scalable, early screening of abnormal movements indicative of CP in infants.
- Facilitates broader implementation of CP screening programs, improving access to early diagnosis and intervention.
Abstract:
Cerebral palsy (CP) is the most common cause of physical disability during childhood, occurring at a rate of 2.1 per 1000 live births. Early diagnosis is key to improving functional outcomes for children with CP. The General Movements (GMs) Assessment has high predictive validity for the detection of CP and is routinely used in high-risk infants but only 50% of infants with CP have overt risk factors when they are born. The implementation of CP screening programs represents an important endeavour, but feasibility is limited by access to trained GMs assessors. To facilitate progress towards this goal, we report a deep-learning framework for automating the GMs Assessment. We acquired 503 videos captured by parents and caregivers at home of infants aged between 12- and 18-weeks term-corrected age using a dedicated smartphone app. Using a deep learning algorithm, we automatically labelled and tracked 18 key body points in each video. We designed a custom pipeline to adjust for camera movement and infant size and trained a second machine learning algorithm to predict GMs classification from body point movement. Our automated body point labelling approach achieved human-level accuracy (mean ± SD error of 3.7 ± 5.2% of infant length) compared to gold-standard human annotation. Using body point tracking data, our prediction model achieved a cross-validated area under the curve (mean ± S.D.) of 0.80 ± 0.08 in unseen test data for predicting expert GMs classification with a sensitivity of 76% ± 15% for abnormal GMs and a negative predictive value of 94% ± 3%. This work highlights the potential for automated GMs screening programs to detect abnormal movements in infants as early as three months term-corrected age using digital technologies.
