Traditionally, the assessment of autism spectrum disorder (ASD) has been based on behavioral observation, with an emphasis on identifying behaviors characteristic of the disorder. However, individuals with ASD often exhibit motor abnormalities before the onset of typical symptoms. In this pilot study, we aimed to leverage digital technologies and artificial intelligence (AI) methodologies to investigate motor patterns in individuals with ASD, using raw data, specifically the raw x and y coordinates of dragging movements. We developed a custom 2D game for Windows tablet devices that involved dragging images from the center of the screen to specific targets. A total of 20 children, aged 3 to 6 years, participated in the study, including 10 neurotypical children and 10 children diagnosed with ASD. We employed AI techniques to analyze the collected data and identify characteristic motor patterns associated with ASD. By training the model with raw data, we were able to capture subtle motor abnormalities that are indicative of ASD. These findings highlight the potential of utilizing raw motor data and AI techniques for early detection and assessment of ASD.
Exploring Motor Patterns in Autism Spectrum Disorder Using Raw Data and Artificial Intelligence: A Pilot Study / Luongo, M.; Simeoli, R.; Marocco, D.; Ponticorvo, M.. - (2023), pp. 1006-1011. (Intervento presentato al convegno 2nd Edition IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering, MetroXRAINE 2023 tenutosi a ita nel 2023) [10.1109/MetroXRAINE58569.2023.10405768].
Exploring Motor Patterns in Autism Spectrum Disorder Using Raw Data and Artificial Intelligence: A Pilot Study
Luongo M.;Simeoli R.;Marocco D.;Ponticorvo M.
2023
Abstract
Traditionally, the assessment of autism spectrum disorder (ASD) has been based on behavioral observation, with an emphasis on identifying behaviors characteristic of the disorder. However, individuals with ASD often exhibit motor abnormalities before the onset of typical symptoms. In this pilot study, we aimed to leverage digital technologies and artificial intelligence (AI) methodologies to investigate motor patterns in individuals with ASD, using raw data, specifically the raw x and y coordinates of dragging movements. We developed a custom 2D game for Windows tablet devices that involved dragging images from the center of the screen to specific targets. A total of 20 children, aged 3 to 6 years, participated in the study, including 10 neurotypical children and 10 children diagnosed with ASD. We employed AI techniques to analyze the collected data and identify characteristic motor patterns associated with ASD. By training the model with raw data, we were able to capture subtle motor abnormalities that are indicative of ASD. These findings highlight the potential of utilizing raw motor data and AI techniques for early detection and assessment of ASD.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
