2024 ASEE Annual Conference & Exposition

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition often associated with delayed motor skills. The Motor Assessment Battery for Children – Second Edition (MABC-2) is a standardized motor assessment for identifying motor delays pertaining to ASD. It evaluates fine and gross motor tasks across three domains: manual dexterity, ball skills, and balance. These tasks are categorized into three age bands: 3-6, 7-10, and 11-16. Recently, Virtual reality (VR) has emerged as a promising intervention in the ASD realm. The purpose of this study was to investigate the potential of VR to assist children with ASD in performing the gross motor skills (i.e., ball skills and balance) in the MABC-2. The children who participated in the study were attendees of a local Autism Summer Camp. Our research focused on adapting motor tasks for ages 7-10 (i.e., Age Band 2) to VR, as the majority of campers fell in this age range. Within the VR environment, children could observe avatar demonstrations and practice motor skills in a highly immersive setting.

The VR environment featured avatars demonstrating ball skills and balancing tasks. Developed with the Unity game engine, 3D software Blender, C# scripting, and mixed reality toolkits, this environment was tested on the Meta Quest 2 Oculus. The children's gross motor skill performance was scored before and after VR interactions. The test percentile scores were described as a traffic-light scoring system, including a red zone, amber zone, and green zone. A percentile score ≤5th is classified in the red zone, indicating a significant movement difficulty; a percentile score between the 5th and 15th is classified in the amber zone, indicating at risk for movement difficulty; and a percentile score >15th is classified in the green zone, indicating no movement difficulty detected. Following the VR intervention, we observed a notable improvement in the balance score (p < 0.05). Using the Random Forest ML model, we analyzed data from a total of 250 children aged 5 to 16. The analysis revealed that balance skill was crucial in classifying children with ASD with motor delays, contributing to nearly 19.5% of the model's accuracy. When the model was exclusively applied to the balance component score, it achieved an impressive accuracy rate of 85.1% in identifying children with ASD.

In summary, our findings underscore the promise of VR in enhancing balance among children with ASD. The Random Forest analysis reaffirmed the significant role of balance in identifying children with ASD. Given its precision in detecting children with ASD based on their balance performance, we anticipate the potential of future ML advancements in this field. Our research not only validates the effectiveness of a VR-based approach but also emphasizes the significance of collaborative research in providing valuable support to the underserved ASD population.