基于自然情绪感知下异常眼动轨迹的孤独症预测模型  

Autism Spectrum Disorder Prediction Model Based on Gaze Trajectory of Natural Emotional Perception

作　　者：黄敏 王端 宋光辉 梁岩 苏荣锋 陈艳妮[3,4] 王岚 燕楠[2,6] HUANG Min;WANG Duan;SONG Guanghui;LIANG Yan;SU Rongfeng;CHEN Yanni;WANG Lan;YAN Nan(School of Resources and Environment,University of Electronic Science and Technology of China,Chengdu 611731,China;Shenzhen Institute of Advanced Technology,Chinese Academy of Sciences,Shenzhen 518055,China;Child Healthcare Department,Xi’an Children’s Hospital(The Affiliated Children’s Hospital of Xi’an Jiaotong University),Xi’an 710003,China;Health Science Center,Xi’an Jiaotong University,Xi’an 710049,China;University of Chinese Academy of Sciences,Beijing 100049,China;Key Laboratory of Human-Machine Intelligence-Synergy Systems,Chinese Academy of Sciences,Shenzhen 518055,China)

机构地区：[1]电子科技大学资源与环境学院,成都611731 [2]中国科学院深圳先进技术研究院,深圳518055 [3]西安市儿童医院(西安交通大学附属儿童医院)儿童保健中心,西安710003 [4]西安交通大学医学部,西安710049 [5]中国科学院大学,北京100049 [6]中国科学院人机智能协同系统重点实验室,深圳518055

出　　处：《集成技术》2023年第4期64-76,共13页Journal of Integration Technology

基　　金：深圳市科技计划项目(KQTD20200820113106007,JCYJ20210324115810030,JCYJ20220818101217037);国家自然科学基金项目(81371900,62271477,U1736202);陕西省重点研发计划项目(2020GXLH-Y-013,2021SF-194);陕西中医药大学中西医结合防治脑发育障碍性疾病创新团队(2019-YL07);陕西省自然科学基础研究计划项目(2022JQ-979);国家重点研发计划项目(2020YFC2004100);西安市科技计划项目(20YXYJ0006(4));陕西省科技研发计划项目(2013SF2-09)。

摘　　要：孤独症谱系障碍(autism spectrum disorder,ASD)是一类以社会交流、刻板行为和狭隘兴趣为主要特征的神经发育障碍性疾病,致残率较高,严重影响着儿童的健康成长。ASD主观临床诊断存在耗时长、主观性强等问题。因此,迫切需要一种快速、经济、有效的客观筛查方法。研究发现,ASD儿童具有非典型的情绪视觉感知模式,有望将眼动追踪技术用于ASD的辅助诊断。该文提出一个在自然场景下,ASD非典型情绪视觉感知模式结合机器学习的自动筛查ASD患者的模型。该模型可提取自然场景下感知情绪的眼动轨迹特征,通过机器学习模型进行建模,以实现根据眼动轨迹自动识别ASD患儿。实验结果表明,该方法的准确率为79.71%,有望成为一种ASD儿童早期筛查的辅助工具。Autism spectrum disorder(ASD)is a neurodevelopmental disorder characterized by impaired social communication,repetitive behaviors,and restricted interests.Signs of autism usually appear by age 3,but the cinical diagnosis is time-consuming and subjective.Therefore,a rapid and cost-effective assessment method is urgently needed.Children with ASD have atypical gaze patterns when they precept emotional stimuli,which suggests a great potential use of eye-tracking technology as an assessment method for ASD detection.This paper proposes a model for automatically assessing children with ASD based on atypical gaze patterns.The model extracts the eye movement trajectory features of perceived emotions in natural scenes,and uses the machine learning model to learn to automatically identify ASD according to the eye movement trajectory features.Results show that the accuracy reaches 79.71%,which has potentially become an early ASD children screening approach.

关 键 词：孤独症谱系障碍 眼动追踪 机器学习 情绪感知 

分 类 号：R749.94[医药卫生—神经病学与精神病学] TP181[医药卫生—临床医学]