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

• Published in: Frontiers in molecular neuroscience Vol. 15; p. 889641
• Main Authors: Alateyat, Heba, Cruz, Sara, Cernadas, Eva, Tubío-Fungueiriño, María, Sampaio, Adriana, González-Villar, Alberto, Carracedo, Angel, Fernández-Delgado, Manuel, Fernández-Prieto, Montse
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Research Foundation 09.05.2022; Frontiers Media S.A
• Subjects: Aggressiveness; Algorithms; Autism; autism spectrum disorders; Behavior; behavior problems; Children & youth; Communication; Information processing; Learning algorithms; Machine learning; Molecular Neuroscience; Predictions; Questionnaires; regression; Regression analysis; Sensory integration; Sensory perception; sensory processing; Statistical analysis; Teenagers; sensory processing; autism spectrum disorders; behavior problems; machine learning; regression
• ISSN: 1662-5099; 1662-5099
• DOI: 10.3389/fnmol.2022.889641

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.