人工智能辅助的自闭症早期患者的筛查与诊断

Early screening and diagnosis of autism spectrum disorder assisted by artificial intelligence

自闭症谱系障碍(Autistic Spectrum Disorders,ASD)的症状早在婴幼儿期就会显现,越早发现,越早干预,治疗效果越好。传统自闭症早期筛查与诊断在评估方法、流程上存在局限,无法满足大规模筛查和诊断需求。随着人工智能技术的快速发展,使用智能化方法进行自闭症早期大规模无感筛查与诊断逐渐成为可能。近10年间,国内外对自闭症智能化识别方法的探索在经典任务行为、面部表情和情绪、眼动、脑影像、运动控制和运动模式、多模态6个领域积累了丰富的研究成果。未来研究应围绕构建国内自闭症早期智能医学筛查与诊断体系,开发针对婴幼儿患者的筛查工具,构建融合多模态数据的自闭症婴幼儿智能化识别模型,建立结合脑影像技术的自闭症精细化诊断方法等方面来开展。

Symptoms of Autistic Spectrum Disorders(ASD)manifest as early as infancy,and the earlier detection and intervention can lead to better therapeutic results.The traditional tools of early screening and diagnosis of autism have limitations in evaluation methods and procedures,which cannot meet the needs of large-scale screening and diagnosis.With the rapid artificial intelligence technological advancement,using an intelligent approach for large-scale non-inductive early screening and diagnosis of autism has become possible.In the past decade,a myriad of research findings on intelligent detection technology of autism were generated domestically and internationally in six aspects:behaviors in classic tasks,facial expressions and emotions,eye gaze data,brain imaging,motor control and movement patterns,and multimodal data.Future research should focus on constructing a domestic intelligent medical screening and diagnosis system for early autism,developing screening tools for infants and young children,constructing an automated recognition model for autistic infants by integrating multimodal data,establishing a refined autism diagnosis method combined with brain imaging technology,and other aspects.