Classification of Autism spectrum disorder severity using eye tracking data based on visual attention model

We proposed a supervised method to classify autism spectrum disorder in two groups (severe and nonsevere) by using eye-tracking data processed based on a computational Model of Visual Attention.
The use of eye tracking to classify subgroups of ASD may contribute to aid in decision making from diagnosis to treatment definition. Further studies, using larger sample sizes, other phenotypic data, such as the presence of comorbidities, behavioral profile, as well as using more free viewing images are necessary so that the use of eye tracking technique could be used to subgroup patients in clinical practice.

本研究提出了一种基于计算视觉注意模型处理的眼动数据监督分类方法，以将自闭症谱系障碍分为两组（严重和非严重）。利用眼动技术对自闭症谱系障碍亚组进行分类，有助于从诊断到治疗方案确定的决策过程。为进一步扩大样本量，纳入其他表型数据，如合并症的存在、行为特征，以及使用更多自由观看图像的研究，是必要的，以确保眼动技术在临床实践中能够用于对患者的亚组划分。