Exploring Gaze Pattern Differences Between Autistic and Neurotypical Children: Clustering, Visualisation, and Prediction

TL;DR

This study investigates whether internal cluster validity indices derived from gaze data can effectively distinguish between autistic and neurotypical children, achieving high predictive accuracy in ASD diagnosis.

Contribution

It introduces a novel approach using internal cluster validity indices for ASD detection from gaze patterns, validated across multiple datasets.

Findings

High predictive accuracy (81% AUC) in ASD diagnosis.

Internal cluster validity indices correlate with ASD diagnosis.

Clustering algorithms effectively differentiate gaze patterns.

Abstract

Autism Spectrum Disorder (ASD) affects children's social and communication abilities, with eye-tracking widely used to identify atypical gaze patterns. While unsupervised clustering can automate the creation of areas of interest for gaze feature extraction, the use of internal cluster validity indices, like Silhouette Coefficient, to distinguish gaze pattern differences between ASD and typically developing (TD) children remains underexplored. We explore whether internal cluster validity indices can distinguish ASD from TD children. Specifically, we apply seven clustering algorithms to gaze points and extract 63 internal cluster validity indices to reveal correlations with ASD diagnosis. Using these indices, we train predictive models for ASD diagnosis. Experiments on three datasets demonstrate high predictive accuracy (81\% AUC), validating the effectiveness of these indices.