Scholarlink

<p>The human eyes are constantly moving, and gaze allocation reveals the cognitive processes underlying attention, memory, and decision-making. Although traditional laboratory-based eye-tracking protocols generate findings based on well-controlled stimuli, modern methods now allow data collection at a larger scale with more naturalistic stimuli. Powerful computational tools also enable new analyses of high-dimensional data, incorporating stimulus feature annotation, spatiotemporal analysis, and machine learning. These advances provide new insights into individual differences in both health and disease. Here we discuss four key approaches to modeling eye movement data: saliency-based attention phenotyping, data-driven gaze-pattern identification, supervised machine-learning classification, and unsupervised subgroup clustering. We highlight their advantages in psychiatry research, as they inform a better understanding of visual attention, provide more fine-grained characterization of individual differences, and make more powerful clinical predictions. Finally, we address key methodological considerations in applying these methods and discuss directions for future research.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Using computational eye-tracking to understand individual differences in psychiatric disorders

  • 期刊论文

  • 发表日期：

    2026年4月22日

查看全文
  • Qianying Wu,
  • Na Yeon Kim,
  • Ralph Adolphs

摘要

The human eyes are constantly moving, and gaze allocation reveals the cognitive processes underlying attention, memory, and decision-making. Although traditional laboratory-based eye-tracking protocols generate findings based on well-controlled stimuli, modern methods now allow data collection at a larger scale with more naturalistic stimuli. Powerful computational tools also enable new analyses of high-dimensional data, incorporating stimulus feature annotation, spatiotemporal analysis, and machine learning. These advances provide new insights into individual differences in both health and disease. Here we discuss four key approaches to modeling eye movement data: saliency-based attention phenotyping, data-driven gaze-pattern identification, supervised machine-learning classification, and unsupervised subgroup clustering. We highlight their advantages in psychiatry research, as they inform a better understanding of visual attention, provide more fine-grained characterization of individual differences, and make more powerful clinical predictions. Finally, we address key methodological considerations in applying these methods and discuss directions for future research.