AI-Based Video Analysis for Motor Development Assessment in Children
Trial statusRecruiting
Trial phaseNot listed
Trial typeObservational
Biological sexAll
Age5-10
SponsorMedipol University
About this trial
This is a non-interventional, prospective observational study aimed at developing and validating an artificial intelligence-based system for assessing motor development in children using video analysis. Children aged 5 to 10 years will perform standardized motor tasks, which will be recorded under controlled conditions. The recorded videos will be analyzed using computer vision and deep learning techniques to extract movement patterns.
The results of the AI-based analysis will be compared with standardized motor assessment scores obtained from the Bruininks-Oseretsky Test of Motor Proficiency, Second Edition - Short Form (BOT-2 SF). Participants will be classified into typical and atypical motor development groups based on BOT-2 scores. The primary objective is to evaluate the classification performance of the AI model. Secondary analyses will examine the relationship between AI predictions and continuous motor performance scores.
The study is designed to explore whether motor development can be assessed objectively without direct clinical testing, using only short video recordings. The findings may contribute to the development of scalable and accessible digital screening tools for early identification of motor development differences in children.
Eligibility criteria
This trial accepts healthy volunteersQualifiers
Children aged between 5 and 10 years
No diagnosed neurological, developmental, or orthopedic disorders
Ability to follow verbal instructions
Informed consent obtained from parents or legal guardians
Disqualifiers
Diagnosed neurological, developmental, or orthopedic conditions (e.g., autism spectrum disorder, cerebral palsy, epilepsy)
Visual or hearing impairments affecting task performance
Severe attention or behavioral problems preventing test completion
Physical limitations preventing participation in motor tasks
Trial population
The study population consists of children aged 5 to 10 years recruited from schools and clinical settings. All participants are typically developing individuals without prior diagnoses, and they are evaluated to identify variations in motor development patterns using standardized testing and video-based analysis.
Trial design
Design model
Case-control
Time perspective
Prospective
Treatments tested in this trial
Observational Assessment Only
Other interventionThis study does not include any therapeutic or experimental intervention. The procedures are limited to observational assessment and data collection. Participants perform standardized motor tasks and are video recorded under controlled conditions. No treatment, training, or behavioral modification is applied. The collected data are analyzed using artificial intelligence-based methods to evaluate motor development patterns.
Treatment groups
60 Participants
are divided into 1 treatment groupGroup A: Typical Motor Development1 intervention
Trial outcomes
Primary outcomes
1
AI-Based Classification Accuracy of Motor Development
Classification accuracy of the artificial intelligence model in distinguishing typical versus atypical motor development based on video analysis, using the Bruininks-Oseretsky Test of Motor Proficiency, Second Edition Short Form (BOT-2 SF) total score as the reference standard. BOT-2 SF scores range from 0 to 88, with higher scores indicating better motor proficiency.
Time frame
Baseline assessment (Day 1)Secondary outcomes
1
Correlation Between AI Predictions and BOT-2 Scores
Statistical relationship between artificial intelligence-generated motor development predictions and Bruininks-Oseretsky Test of Motor Proficiency, Second Edition Short Form (BOT-2 SF) total scores. BOT-2 SF scores range from 0 to 88, with higher scores indicating better motor proficiency.
Time frame
Baseline assessment (Day 1)2
Mean Absolute Error of AI-Based Motor Score Prediction
Mean absolute error (MAE) of the artificial intelligence model in predicting continuous motor development scores based on video analysis, compared with Bruininks-Oseretsky Test of Motor Proficiency, Second Edition Short Form (BOT-2 SF) total scores.
Time frame
Baseline assessment (Day 1)3
Root Mean Square Error of AI-Based Motor Score Prediction
Root mean square error (RMSE) of the artificial intelligence model in predicting continuous motor development scores based on video analysis, compared with Bruininks-Oseretsky Test of Motor Proficiency, Second Edition Short Form (BOT-2 SF) total scores.
Time frame
Baseline assessment (Day 1)4
R-Squared Performance of AI-Based Motor Score Prediction
Coefficient of determination (R-squared) for the artificial intelligence model in predicting continuous motor development scores based on video analysis, compared with Bruininks-Oseretsky Test of Motor Proficiency, Second Edition Short Form (BOT-2 SF) total scores.
Time frame
Baseline assessment (Day 1)Sponsors and contacts
Click on the lead sponsor to view all of their trials.
Source ClinicalTrials.gov