Automatic Classification of Adult Males With and Without Autism Spectrum Disorder by Non-contact Measurement of Autonomic Nervous System Activation

People with autism spectrum disorder (ASD) exhibit atypicality in various domains of behavior. Previous psychophysiological studies have revealed an atypical pattern of autonomic nervous system (ANS) activation induced by psychosocial stimulation. Thus, it might be feasible to develop a novel assessment tool to evaluate the risk of ASD by measuring ANS activation in response to emotional stimulation. The present study investigated whether people with ASD could be automatically classified from neurotypical adults based solely on physiological data obtained by the recently introduced non-contact measurement of pulse wave. We video-recorded faces of adult males with and without ASD while watching emotion-inducing video clips. Features reflective of ANS activation were extracted from the temporal fluctuation of facial skin coloration and entered into a machine-learning algorithm. Though the performance was modest, the gradient boosting classifier succeeded in classifying people with and without ASD, which indicates that facial skin color fluctuation contains information useful for detecting people with ASD. Taking into consideration the fact that the current study recruited only high-functioning adults who have relatively mild symptoms and probably developed some compensatory strategies, ASD screening by non-contact measurement of pulse wave could be a promising assessment tool to evaluate ASD risk.