机器学习联合眼动注视模式在孤独症早期诊断中的应用  

The application of machine learning in combination with eye-tracking technology in the early identification of autism

作　　者：常天怡 孟凡超 田音 陈旭[1] 郑毅[1] Chang Tianyi;Meng Fanchao;Tian Yin;Chen Xu;Zheng Yi(National Clinical Research Center for Mental Disorders,National Center for Mental Disorders,Beijing Anding Hospital,Capital Medical University,Beijing 100088,China)

机构地区：[1]首都医科大学附属北京安定医院,国家精神疾病医学中心,国家精神心理疾病临床医学研究中心,北京100088

出　　处：《中华精神科杂志》2024年第9期623-628,共6页Chinese Journal of Psychiatry

基　　金：北京市医院管理中心“扬帆”计划临床技术创新项目(YGLX202340);北京市医院管理中心青年人才培养“青苗”计划(QML20231906)。

摘　　要：孤独症谱系障碍(autism spectrum disorder,ASD)的早期诊断和早期干预至关重要,有利于改善患者的预后。目前由于缺乏客观的生物标志物,对ASD的评估基本上依赖于行为观察。软件和硬件多媒体技术的最新进展为早期检测ASD提供了工具。有研究显示,眼球追踪技术有望成为早期辅助诊断ASD的工具。本文中综述了眼球追踪信息联合机器学习用于诊断ASD的研究,并提出了目前研究的局限性和未来研究的方向。Early and objective assessment,as well as early intervention,are of particular importance for autism spectrum disorder(ASD)to improve the long-term outcome.However,due to a lack of objective biomarkers,the current assessment of ASD depends mainly on limited behavioral observation.Recent advancements in software and hardware multimedia technologies provide new ways to identify ASD early.Evidence supports that the combination of machine learning with eye-tracking technology is expected to be a useful tool for the early and objective diagnosis of ASD.The current study reviewed the research on the combination of machine learning with eye-tracking technology for the identification of ASD.The limitations and future directions have also been proposed.

关 键 词：孤独性障碍 诊断 分类 机器学习 眼动追踪 

分 类 号：R749.94[医药卫生—神经病学与精神病学]