Exploring sensory alterations and repetitive behaviors in children with autism spectrum disorder from the perspective of artificial neural networks

Restrictive repetitive behaviors (RRBs) and sensory processing disorders are core symptoms of autism spectrum disorder (ASD). Their relationship is reported, but existing data are conflicting as to whether they are related but distinct, or different aspects of the same phenomenon. This study investigates this relationship using artificial neural networks (ANN) analysis and an innovative data mining analysis known as Auto Contractive Map (Auto-CM), which allows to discover hidden trends and associations among complex networks of variables (e.g. biological systems). The Short Sensory Profile and the Repetitive Behavior Scale-Revised were administered to 45 ASD children’s caregivers (M 78 %; F 22 %; mean age 6 years). Questionnaires’ scores, clinical and demographic data were collected and analyzed applying Auto-CM, and a connectivity map was drawn. The main associations shown by the resulting maps confirm the known relationship between RBBs and sensory abnormalities, and support the existence of sensory phenotypes, and important links between RRBs and sleep disturbance in ASD. Our study demonstrates the usefulness of ANNs application and its easy handling to research RBBs and sensory abnormalities in ASD, with the aim to achieve better individualized rehabilitation technique and improve early diagnosis. Restricted, repetitive patterns of behaviors and interests and alteration of sensory elaboration are core symptoms of ASD; their impact on patients’ quality of life is known. This study introduces two main novelties: 1) the simultaneous and comparative use of two parent questionnaires (SSP and RBS-R) utilized for RRBs and alteration of sensory profile; 2) the application of ANNs to this kind of research. ANNs are adaptive models particularly suited for solving non-linear problems. While they have been widely used in the medical field, they have not been applied yet to the analysis of RRBs and sensory abnormalities in general, much less in children with ASD. The application of Auto Contractive Map (Auto-CM), a fourth generation ANNs analysis, to a dataset previously explored using classical statistical models, confirmed and expanded the associations emerged between SSP and RBS-R subscales and demographic-clinical variables. In particular, the Low Energy subscale has proven to be the central hub of the system; interesting links have emerged between the subscale Self-Injurious Behaviors and the variable intellectual disability and between sleep disturbance and v