Using Technology to Identify Children With Autism Through Motor Abnormalities.

Roberta Simeoli,Davide Marocco,Nicola Milano,Angelo Rega

doi:10.3389/fpsyg.2021.635696

Abstract

Autism is a neurodevelopmental disorder typically assessed and diagnosed through observational analysis of behavior. Assessment exclusively based on behavioral observation sessions requires a lot of time for the diagnosis. In recent years, there is a growing need to make assessment processes more motivating and capable to provide objective measures of the disorder. New evidence showed that motor abnormalities may underpin the disorder and provide a computational marker to enhance assessment and diagnostic processes. Thus, a measure of motor patterns could provide a means to assess young children with autism and a new starting point for rehabilitation treatments. In this study, we propose to use a software tool that through a smart tablet device and touch screen sensor technologies could be able to capture detailed information about children’s motor patterns. We compared movement trajectories of autistic children and typically developing children, with the aim to identify autism motor signatures analyzing their coordinates of movements. We used a smart tablet device to record coordinates of dragging movements carried out by 60 children (30 autistic children and 30 typically developing children) during a cognitive task. Machine learning analysis of children’s motor patterns identified autism with 93% accuracy, demonstrating that autism can be computationally identified. The analysis of the features that most affect the prediction reveals and describes the differences between the groups, confirming that motor abnormalities are a core feature of autism.

Highlights

Autism spectrum disorder (ASD) is a neurodevelopmental disorder notoriously characterized by communication impairment, a lack of social interaction, and the presence of restricted, repetitive, and stereotyped behaviors
The study was attended by 60 children aged between 5 and 10 years, divided into two groups: 30 children with an average age of 7 years, standard deviation 1.4, clinically diagnosed with ASD according to the Diagnostic and Statistical Manual of Mental Disorders (5th ed.); and 30 children, aged 6 years and 8 months, standard deviation 1, with typical development (TD)
The artificial neural network (ANN) used for the ASD/TD classification was a feedforward multilayer perceptron, composed of an input layer of 17 neurons, an output layer of two neurons, and a hidden layer whose number of neurons has been selected through grid search optimization with cross-validation, in a descending search starting from 10 hidden neurons, as we tried to keep to the model as simple as possible in order to reduce overfitting

Summary

Introduction

Autism spectrum disorder (ASD) is a neurodevelopmental disorder notoriously characterized by communication impairment, a lack of social interaction, and the presence of restricted, repetitive, and stereotyped behaviors. Autism includes a very variable repertoire of symptoms and manifestations. The different target behaviors occur for each child with different degrees of severity. The etiology of the disorder is still unknown, and it can involve both genetic and environmental factors. Because of these variabilities, many specialists are assuming that autism can be classified into different types, each of which may have different etiology and response to treatment. Recent studies have defined ASD as the most frequently observed neurodevelopmental disorder with an incidence estimate of 60–70/10,000 (Fombonne, 2009).

Objectives

Methods

Results

Discussion

Conclusion