Related Experiment Video
Updated: Jul 2, 2025
Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable
Published on: May 17, 2024
Comprehensive Assessment and Early Prediction of Gross Motor Performance in Toddlers With Graph Convolutional
Sulim Chun1, Sooyoung Jang1, Jin Yong Kim1
1Department of Biomedical Systems Informatics, Yonsei University College of Medicine, Seoul, Republic of Korea.
Insights
This study developed automated models using toddler videos to assess gross motor skills, identifying key movements like descending stairs for accurate developmental evaluation.
Area of Science:
- Pediatric developmental assessment
- Automated movement analysis
- Machine learning in healthcare
Background:
- Accurate developmental assessment is crucial for early intervention in children.
- Automated methods are needed due to provider shortages and imprecise parental reports.
- Toddler gross motor development predicts later childhood development.
Purpose of the Study:
- Develop a model to objectively assess toddler gross motor behavior.
- Integrate behavioral assessments to determine overall gross motor status.
- Identify critical behaviors, moments, and body parts for gross motor assessment.
Main Methods:
- Utilized behavioral videos of 147 toddlers (18-35 months) performing 4 validated gross motor skills.
- Employed graph convolutional networks (GCN) for initial behavior evaluation and extreme gradient boosting (XGBoost) for overall status prediction.
- Applied Grad-CAM and Shapley additive explanations for interpretability, identifying key movement moments and body parts.
Main Results:
- The GCN models achieved an AUROC of 0.79-0.90 for individual behaviors.
- The XGBoost model for overall gross motor status achieved an AUROC of 0.90.
- "Go down the stairs" was identified as the most significant behavior for overall assessment.
Conclusions:
- Objective, automated models were created to evaluate toddler gross motor performance from movement videos.
- Key behaviors and critical assessment moments/body parts for gross motor development were identified.
- This approach enhances the accuracy and efficiency of developmental assessments.
Background:
Accurate and timely assessment of children's developmental status is crucial for early diagnosis and intervention. More accurate and automated developmental assessments are essential due to the lack of trained health care providers and imprecise parental reporting. In various areas of development, gross motor development in toddlers is known to be predictive of subsequent childhood developments.
Objective:
The purpose of this study was to develop a model to assess gross motor behavior and integrate the results to determine the overall gross motor status of toddlers. This study also aimed to identify behaviors that are important in the assessment of overall gross motor skills and detect critical moments and important body parts for the assessment of each behavior.
Methods:
We used behavioral videos of toddlers aged 18-35 months. To assess gross motor development, we selected 4 behaviors (climb up the stairs, go down the stairs, throw the ball, and stand on 1 foot) that have been validated with the Korean Developmental Screening Test for Infants and Children. In the child behavior videos, we estimated each child's position as a bounding box and extracted human keypoints within the box. In the first stage, the videos with the extracted human keypoints of each behavior were evaluated separately using a graph convolutional networks (GCN)-based algorithm. The probability values obtained for each label in the first-stage model were used as input for the second-stage model, the extreme gradient boosting (XGBoost) algorithm, to predict the overall gross motor status. For interpretability, we used gradient-weighted class activation mapping (Grad-CAM) to identify important moments and relevant body parts during the movements. The Shapley additive explanations method was used for the assessment of variable importance, to determine the movements that contributed the most to the overall developmental assessment.
Results:
Behavioral videos of 4 gross motor skills were collected from 147 children, resulting in a total of 2395 videos. The stage-1 GCN model to evaluate each behavior had an area under the receiver operating characteristic curve (AUROC) of 0.79 to 0.90. Keypoint-mapping Grad-CAM visualization identified important moments in each behavior and differences in important body parts. The stage-2 XGBoost model to assess the overall gross motor status had an AUROC of 0.90. Among the 4 behaviors, "go down the stairs" contributed the most to the overall developmental assessment.
Conclusions:
Using movement videos of toddlers aged 18-35 months, we developed objective and automated models to evaluate each behavior and assess each child's overall gross motor performance. We identified the important behaviors for assessing gross motor performance and developed methods to recognize important moments and body parts while evaluating gross motor performance.
