Our collaborative research on using machine learning to evaluate movement patterns for predicting high autistic traits has been published in Frontiers. This interdisciplinary study was led by Professor Yoshimasa Ohmoto (Shizuoka University) and Professor Hirokazu Kumazaki (Nagasaki University), advancing our understanding of motor impairments in autism spectrum disorder.

The paper, titled “Machine learning’s effectiveness in evaluating movement in one-legged standing test for predicting high autistic trait,” examines how machine learning can analyze balance coordination in children. Using data from 126 participants performing one-legged standing tests, the study achieved perfect accuracy in identifying high autistic traits by focusing on shoulder, hip, and trunk movements. This research advances the development of objective, non-invasive diagnostic tools for autism spectrum disorder.

Ohmoto, Y., Terada, K., Shimizu, H., Kawahara, H., Iwanaga, R. & Kumazaki, H. (2024). Machine learning’s effectiveness in evaluating movement in one-legged standing test for predicting high autistic trait. Frontiers in Psychiatry, 15. https://doi.org/10.3389/fpsyt.2024.1464285