Classification of MCI patients using vergence eye movements and pupil responses obtained during a visual oddball test

In the current study, we tested the hypothesis that Mild Cognitive Impairment (MCI) patients can be identified based on the analysis of vergence eye movements and pupil responses. We recorded vergence and pupil responses in MCI patients (N = 22) and cognitive healthy elderly (N = 18) while performing a visual oddball task. Based on selected features, a classifier model computed probability scores predicting MCI. MCI patients were re-evaluated in a follow-up visit of 12–18 months. For validating the model, patients with Alzheimer's Disease (AD) (N = 9) were tested. High classification accuracy was obtained (AUC: 0.93). In addition, the probability scores showed significant predictive power of MCI conversion into possible AD. Our results show that MCI can be detected by assessing vergence and pupil responses during a simple and short task. Therefore, these responses could potentially be used as a marker tool for MCI diagnosis and to identify the risk of developing Alzheimer's Disease.
This research was supported by grants from Spanish Ministry of Science (PGC2018–096074-B I00) and from AGAUR, Generalitat de Catalunya (2018-DI-75 & 2017-SGR-48)
Peer Reviewed
Postprint (published version)