A Machine Learning Approach in Autism Spectrum Disorders: From Sensory Processing to Behavior Problems

Abstract

Atypical sensory processing described in autism spectrum disorders (ASDs) frequently cascade into behavioral alterations: isolation, aggression, indifference, anxious/depressed states, or attention problems. Predictive machine learning models might refine the statistical explorations of the associations between them by finding out how these dimensions are related. This study investigates whether behavior problems can be predicted using sensory processing abilities. Participants were 72 children and adolescents (21 females) diagnosed with ASD, aged between 6 and 14 years (M = 7.83 years; SD = 2.80 years). Parents of the participants were invited to answer the Sensory Profile 2 (SP2) and the Child Behavior Checklist (CBCL) questionnaires. A collection of 26 supervised machine learning regression models of different families was developed to predict the CBCL outcomes using the SP2 scores. The most reliable predictions were for the following outcomes: total problems (using the items in the SP2 touch scale as inputs), anxiety/depression (using avoiding quadrant), social problems (registration), and externalizing scales, revealing interesting relations between CBCL outcomes and SP2 scales. The prediction reliability on the remaining outcomes was “moderate to good” except somatic complaints and rule-breaking, where it was “bad to moderate.” Linear and ridge regression achieved the best prediction for a single outcome and globally, respectively, and gradient boosting machine achieved the best prediction in three outcomes. Results highlight the utility of several machine learning models in studying the predictive value of sensory processing impairments (with an early onset) on specific behavior alterations, providing evidences of relationship between sensory processing impairments and behavior problems in ASD.

An Exploratory Study of the Associations Between Sensory Processing Patterns and Emotional/Behavioral Problems in Children with Autism Spectrum Disorder

“…In other words, our results suggest that some items in the sensory processing patterns of ASD patients are strongly associated with emotional/behavioral problems, while others are weakly associated with emotional/behavioral problems. These findings are consistent with a recent study in Spain that examined the ability of machine learning to predict behavioral problems from sensory profiles [16]: 72 ASD-affected children (51 boys, 21 girls) aged 6-14 years were included, and their parents' responses to the SP2 and CBCL were used to predict CBCL outcomes from SP2 scores. The results showed that (i) sensory avoiding in the SP2 predicted 'anxious/depressed' and aggressive behavior in the CBCL, and (ii) low registration in the SP2 predicted 'withdrawn/depressed,' social problems, and internalizing [16].…”