Accepted for/Published in: JMIR Formative Research
Date Submitted: Mar 15, 2024
Date Accepted: Oct 10, 2024
Predicting Age and Visual-Motor Integration Using Origami Photographs: A Deep Learning Study
ABSTRACT
Background:
Origami products may reflect children’s age and development of visual-motor integration (VMI), but remains unsupported by evidence. This study aimed to apply artificial intelligence (AI) techniques on origami products to predict children’s age and VMI development (including VMI level [standardized scores] and VMI developmental status [normal, borderline, and delayed]). A sample of 515 children aged from 2 to 6 years old were recruited. The AI models (i.e., deep learning) for predicting age z-scores and VMI z-scores were respectively trained. Generally, the variances of the two developmental indicators (i.e., age z-score, and VMI z-score) could be largely predicted by the models from the photographs of origami dog (R2 0.60¬0.72). Moreover, the predictive accuracy of VMI developmental status was about 71.0 to 76.0%. Our findings suggest that AI techniques have large potential to predict children’s development. The information provided by AI may help therapists better interpret children’s activity performance.
Objective:
Origami products may reflect children’s age and development of visual-motor integration (VMI), but remains unsupported by evidence. This study aimed to apply artificial intelligence (AI) techniques on origami products to predict children’s age and VMI development (including VMI level [standardized scores] and VMI developmental status [normal, borderline, and delayed]).
Methods:
A sample of 515 children aged from 2 to 6 years old were recruited. The AI models (i.e., deep learning) for predicting age z-scores and VMI z-scores were respectively trained.
Results:
Generally, the variances of the two developmental indicators (i.e., age z-score, and VMI z-score) could be largely predicted by the models from the photographs of origami dog (R2 0.60¬0.72). Moreover, the predictive accuracy of VMI developmental status was about 71.0 to 76.0%.
Conclusions:
Our findings suggest that AI techniques have large potential to predict children’s development. The information provided by AI may help therapists better interpret children’s activity performance.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.