Learning Scan Paths Of Eye Movement In Autism Spectrum Disorder
DIGITAL PERSONALIZED HEALTH AND MEDICINE(2020)
摘要
Eye tracking studies have demonstrated deficits in attention in individuals with Autism Spectrum Disorder (ASD) for a range of different social attention-based tasks. Here we examined social attention skills in a large sample of ASD participants (n = 120), using eye tracking data from a social information processing task, and compared them with a typically developing (TD) group (n = 35). Assuming eye movement parameters are random variables generated by an underlying stochastic process, we modeled the fixation sequences of participants in ASD and TD groups with a Hidden Markov Model. The Regions of Interests (ROIs), modeled as hidden states, corresponded to the true ROIs with a prediction accuracy of >90% for each group. The transition between ROIs revealed bias towards a specific area in the scene in ASD group, which deviated from the TD group. Objective time-dynamic measures of gaze patterns can potentially serve as useful endpoints in ASD diagnosis. Clinical Trial Registration: NCT02299700.
更多查看译文
关键词
Autism Spectrum Disorder, eye tracking, Hidden Markov Model
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要