Research on Eye Movement Analysis for Early Detection of Mild Cognitive Impairment
ZUO Haiwei
LIAO Yinping
LI Zhenjun
Abstract：Early detection of mild cognitive impairment(MCI)is crucial in the initial stages to provide timely treatment and control.In traditional diagnostic methods,physicians manually assess MCI by asking patients to perform multiple rounds of text reading and gatning exercises.Due to varying professional experience,the quantification of this manual assessment may be subjec-tive and require further verification using brain imaging techniques.This paper proposes an automated digital MCI assessment meth-od using a Tobii eye tracker to evaluate patients' conditions by tracking their eye movements during text reading.First,eye move-ment patterns are captured using the Tobii eye tracker during text reading.The recorded eye movements are then converted into the frequency domain to study the frequency components during the reading process.The simulation of MCI symptoms is set up by prompting subjects to read text in their familiar native language and an unfamiliar language.The results show significant differences in eye movement patterns between native and unfamiliar language reading.The subject group reading unfamiliar language exhibits random eye movements with lower visual processing efficiency.This pattern is similar to that of patients suffering from MCI symp-toms.Furthermore,frequency features are extracted to study their correlation with reading comprehension performance to detect ear-ly MCI conditions.
Keywords：mild cognitive impairmentearly diagnosiseye trackingfrequency-domain analysis
Publication Date：2025-08-20
Online Publishing Date：2025-12-12(First online date of this platform, not the publication date of the document)
Pages：6( 2083-2088 )