Eye Tracking Biomarkers for Autism Spectrum Disorder Detection using Machine Learning and Deep Learning Techniques: Review

Eye tracking is a promising tool for Autism Spectrum Disorder (ASD) detection in both children and adults. An important aspect of social communication is keeping eye contact, which is something that people with ASD frequently struggle with. Eye tracking can assess the duration of eye contact and the frequency and direction of gaze movements, offering quantifiable indicators of social communication deficits. People with ASD may also demonstrate other abnormalities in visual processing, such as an increased concentration on detail, sensory sensitivity, and trouble with complicated visual activities. These variations can be measured via Eye tracking, which offers critical information for the planning of therapy and diagnosis. The primary objective of this work is to provide a thorough description of the most recent studies that use Eye tracking combined with various Machine Learning (ML) and Deep Learning (DL) models for the detection of ASD. This will provide insights into the identification, and behavioral assessment, and distinguish between autistic people and those who are Typically Developing (TD). A detailed review of the various ML and DL models with their datasets and performance criteria is presented. Different types of eye movement datasets with diagnostic standards and eye tracker devices are also discussed. Finally, the study addresses the potential of gaze prediction in ASD patients for the design of interventions.