Abstract
BACKGROUND: Eye tracking (ET) is a viable marker for the recognition of cognitive disorders. We assessed the accuracy and clinical value of ET for the diagnosis of cognitive disorders in patients. METHODS: We searched the Medline, Embase, Web of Science, Cochrane Library, and Pubmed databases from inception to March 2, 2021, as well as the reference lists of identified primary studies. We included articles written in English that investigated ET for cognitive disorder patients-Mild cognitive impairment (MCI), Alzheimer's disease (AD), Amyotrophic lateral sclerosis (ALS), and dementia. Two independent researchers extracted the data and the characteristics of each study; We calculated pooled sensitivities and specificities. A hierarchical summary of receiver performance characteristics (HSROC) model was used to test the diagnostic accuracy of ET for cognitive impairment (CI). FINDINGS: 11 studies met the inclusion criteria and were included in qualitative comprehensive analysis. Meta-analysis was performed on 9 trials using Neuropsychological Cognitive Testing (NCT) as the reference standard. The comprehensive sensitivity and specificity of ET for detecting cognitive disorders were 0.75 (95% CI 0.72-0.79) and 0.73 (95% CI 0.70 to 0.76), respectively. The combined positive likelihood ratio (LR+) was 2.74 (95%CI 2.32-3.24) and the negative likelihood ratio (LR-) was 0.27 (95%CI 0.18-0.42). CONCLUSIONS: This review showed that ET technology could be used to detect the decline in CI, clinical use of ET techniques in combination with other tools to assess CI can be encouraged.