Citation: Kanhirakadavath, M.R.;
Chandran, M.S.M. Investigation of
Eye-Tracking Scan Path as a
Biomarker for Autism Screening
Using Machine Learning Algorithms.
Diagnostics 2022, 12, 518. https://
doi.org/10.3390/diagnostics12020518
Academic Editors: Keun Ho Ryu and
Nipon Theera-Umpon
Received: 27 January 2022
Accepted: 12 February 2022
Published: 17 February 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
Investigation of Eye-Tracking Scan Path as a Biomarker for
Autism Screening Using Machine Learning Algorithms
Mujeeb Rahman Kanhirakadavath
1,2
and Monica Subashini Mohan Chandran
3,
*
1
School of Electronics Engineering, Vellore Institute of Technology, Vellore 632014, India;
m.rahman@ajman.ac.ae
2
Department of Biomedical Engineering, Ajman University, Ajman P.O. Box 346, United Arab Emirates
3
School of Electrical Engineering, Vellore Institute of Technology, Vellore 632014, India
* Correspondence: monicasubashini.m@vit.ac.in
Abstract:
Autism spectrum disorder is a group of disorders marked by difficulties with social skills,
repetitive activities, speech, and nonverbal communication. Deficits in paying attention to, and
processing, social stimuli are common for children with autism spectrum disorders. It is uncertain
whether eye-tracking technologies can assist in establishing an early biomarker of autism based on
the children’s atypical visual preference patterns. In this study, we used machine learning methods
to test the applicability of eye-tracking data in children to aid in the early screening of autism. We
looked into the effectiveness of various machine learning techniques to discover the best model for
predicting autism using visualized eye-tracking scan path images. We adopted three traditional
machine learning models and a deep neural network classifier to run experimental trials. This study
employed a publicly available dataset of 547 graphical eye-tracking scan paths from 328 typically
developing and 219 autistic children. We used image augmentation to populate the dataset to prevent
the model from overfitting. The deep neural network model outperformed typical machine learning
approaches on the populated dataset, with 97% AUC, 93.28% sensitivity, 91.38% specificity, 94.46%
NPV, and 90.06% PPV (fivefold cross-validated). The findings strongly suggest that eye-tracking data
help clinicians for a quick and reliable autism screening.
Keywords:
ASD screening; autism spectrum disorder; machine learning; convolutional neural
network (CNN); eye-tracking scan path images
1. Introduction
Autism spectrum disorder (ASD) is a neurodevelopmental disorder characterized by
deficits in verbal and nonverbal communication, reciprocal social interaction, accompanied
by certain repetitive and stereotyped behaviors [
1
]. The severity of symptoms and the
effects of ASD varies from case to case. According to the Centers for Disease Control
and Prevention (CDC), 1 in 54 children has been diagnosed with ASD; it affects people of
all races, ethnicities, and socioeconomic backgrounds. Moreover, ASD is diagnosed four
times more frequently in boys than in girls; compared to boys, many girls with ASD show
fewer visible signs [
2
]. Autism is a chronic illness that lasts a lifetime [
3
]. Therefore, early
identification of ASD is crucial, and individuals with ASD diagnosed early in childhood can
significantly impact from appropriate interventions for a long-term positive outcome [4].
We currently lack a diagnostic test to confirm ASD, such as a blood test or a brain scan.
A behavioral assessment would be required to diagnose ASD in a child. The American
Academy of Pediatrics (AAP) recommends that all children be screened for developmental
delays and disabilities at 9, 18, and 30 months during routine doctor visits. However, at 18
and 24 months, every child should be screened for ASD using autistic-specific screening
tools based on the Diagnostic and Statistical Manual for Disorders—DSM_V [5].
ASD diagnosis is still a challenging task requiring several cognitive tests and hours of
clinical examinations and follow-up. Furthermore, the heterogeneities in the symptoms of
Diagnostics 2022, 12, 518. https://doi.org/10.3390/diagnostics12020518 https://www.mdpi.com/journal/diagnostics
