Application of VR eye movement cognitive assessment in the early screening of cognitive impairment

Abstract

Background: Dementia is a rapid growing global health challenge, and early screening in the preclinical stage is necessary. Mild cognitive impairment (MCI) is considered a transitional stage preceding dementia, and current diagnostic markers for AD are limited by cost and invasiveness. Neuropsychological tests (such as MMSE, MoCA) are valid but neither simple nor efficient enough to serve as large-scale dementia screening tools. Eye-tracking data can be encoded as cognitive activity and states, which provides quantitative and multi-dimensional attributes of cognitive function. Its application to cognitive assessment has shown promise in identifying patients with MCI or dementia. Immersive environments of virtual reality technology guarantee the integrity of eye-tracking data and the portability of VR headset enables efficient large-scale early screening of cognitive impairment in communities. Objective: Develop a 5-minute dementia screening tool — VR Eye Movement Cognitive Assessment to help physicians detect cognitive impairment as an alternative approach of traditional paper-based instruments. Methods: 201 subjects from Shenzhen Baoan Chronic Hospital were administered MoCA and VR eye movement cognitive assessments. Raw gaze data was captured by eye tracker of the VR headset and filtered as eye movements which would be encoded as features. Machine learning models were established as the predictor of MoCA score and the classifier of cognitive impairment of three education-based groups within which optimal cut-off score was given. Results: Support vector regression was proposed as the VR-AI model and achieved high correlation of 0.9 with MoCA score, greater than baseline model of 0.58. Optimal cut-off scores (less than 6 years of education: 14/15; 6 to 9 years of education: 18/19; more than 9 years of education: 23/24) can well distinguish normal and cognitively impaired subjects — with overall sensitivity of 88.5% and specificity of 83%. Conclusion: VR eye movement cognitive assessment is a portable, efficient, and quantitative dementia screening tool, which can be used for early screening of mild cognitive impairment and dementia.