Towards AI-based Depression and Social Anxiety Screening Through Eye Tracking

2025-03-22

International journal of marketing, communication and new media

AI Summary

This study addresses the need for early, non-invasive screening of depression and social anxiety disorder. Methodologically, it introduces a novel AI-assisted assessment paradigm that converts individual gaze scanpaths into grayscale trajectory images—encoding spatiotemporal attention dynamics—and feeds them into a lightweight ResNet architecture to discriminate affective disorder subtypes via visual attention pattern analysis. Key contributions include: (1) the first formulation of scanpath image representation for eye-tracking data, and (2) an end-to-end deep learning framework for multi-class affective disorder classification. Empirical evaluation yields 48% accuracy in three-way classification (depression vs. social anxiety vs. healthy controls) and 62% in binary classification (clinical disorder vs. healthy), significantly validating the discriminative power of oculomotor features. The approach offers a scalable, ecologically valid, and low-cost solution for preliminary mental health screening.

Technology Category

• Computer Vision: Multi-modal Vision
• Cognitive Modeling & Cognitive Systems: Affective Computing
• Humans and AI: Brain-Sensing and Analysis

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Well-being is a dynamic construct that evolves over time and fluctuates within individuals, presenting challenges for accurate quantification. Reduced well-being is often linked to depression or anxiety disorders, which are characterised by biases in visual attention towards specific stimuli, such as human faces. This paper introduces a novel approach to AI-assisted screening of affective disorders by analysing visual attention scan paths using convolutional neural networks (CNNs). Data were collected from two studies examining (1) attentional tendencies in individuals diagnosed with major depression and (2) social anxiety. These data were processed using residual CNNs through images generated from eye-gaze patterns. Experimental results, obtained with ResNet architectures, demonstrated an average accuracy of 48% for a three-class system and 62% for a two-class system. Based on these exploratory findings, we propose that this method could be employed in rapid, ecological, and effective mental health screening systems to assess well-being through eye-tracking.

Problem

• AI screens depression via eye-tracking attention patterns
• Detects social anxiety using CNN-analyzed gaze data
• Improves mental health screening accuracy with visual biases

Innovation

• AI analyzes eye-gaze patterns for mental health screening
• Uses residual CNNs to process visual attention data
• Achieves 62% accuracy in two-class affective disorder detection