Automatic Assessment of Motor Impairments in Autism Spectrum Disorders: A Systematic Review

Autism spectrum disorder (ASD) is mainly described as a disorder of communication and socialization. However, motor abnormalities are also common in ASD. New technologies may offer quantitative and automatic metrics to measure movement difficulties. We sought to identify computational methods to automatize the assessment of motor impairments in ASD. We systematically searched for the terms ’autism’, ’movement’, ’automatic’, ’computational’ and ’engineering’ in IEEE (Institute of Electrical and Electronics Engineers), Medline and Scopus databases and reviewed the literature from inception to 2018. We included all articles discussing: (1) automatic assessment/new technologies, (2) motor behaviours and (3) children with ASD. We excluded studies that included patient’s or parent’s reported outcomes as online questionnaires that focused on computational models of movement, but also eye tracking, facial emotion or sleep. In total, we found 53 relevant articles that explored static and kinetic equilibrium, like posture, walking, fine motor skills, motor synchrony and movements during social interaction that can be impaired in individuals with autism. Several devices were used to capture relevant motor information such as cameras, 3D cameras, motion capture systems, accelerometers. Interestingly, since 2012, the number of studies increased dramatically as technologies became less invasive, more precise and more affordable. Open-source software has enabled the extraction of relevant data. In a few cases, these technologies have been implemented in serious games, like “Pictogram Room”, to measure the motor status and the progress of children with ASD. Movement computing opens new perspectives for patient assessment in ASD research, enabling precise characterizations in experimental and at-home settings, and a better understanding of the role of sensorimotor disturbances in the development of social cognition and ASD. These methods would likely enable researchers and clinicians to better distinguish ASD from other motors disorders while facilitating an improved monitoring of children’s progress in more ecological settings (i.e. at home or school).