Machine Learning and Eye Movements Give Insights into Neurodegenerative Disease Mechanisms

Abstract

Humans are a vision-dominated species; what we perceive depends on where we look. Therefore, eye movements (EMs) are essential to our interactions with the environment, and experimental findings show EMs are affected in neurodegenerative disorders (ND). This could be a reason for some cognitive and movement disorders in ND. Therefore, we aim to establish whether changes in EM-evoked responses can tell us about the progression of ND, such as Alzheimer’s (AD) and Parkinson’s diseases (PD), in different stages. In the present review, we have analyzed the results of psychological, neurological, and EM (saccades, antisaccades, pursuit) tests to predict disease progression with machine learning (ML) methods. Thanks to ML algorithms, from the high-dimensional parameter space, we were able to find significant EM changes related to ND symptoms that gave us insights into ND mechanisms. The predictive algorithms described use various approaches, including granular computing, Naive Bayes, Decision Trees/Tables, logistic regression, C-/Linear SVC, KNC, and Random Forest. We demonstrated that EM is a robust biomarker for assessing symptom progression in PD and AD. There are navigation problems in 3D space in both diseases. Consequently, we investigated EM experiments in the virtual space and how they may help find neurodegeneration-related brain changes, e.g., related to place or/and orientation problems. In conclusion, EM parameters with clinical symptoms are powerful precision instruments that, in addition to their potential for predictions of ND progression with the help of ML, could be used to indicate the different preclinical stages of both diseases.

Eye-tracking paradigms for the assessment of mild cognitive impairment: a systematic review

“…Indeed, previous scientific reports mentioned eye-movement impairments among AD patients while looking at naturalistic pictures. However, such observation refers primarily to the diminished curiosity aspect ( Przybyszewski et al, 2023 ). Another point for emphasis is the specific protocol of the free-viewing task, which requires participants to freely view a given scene without explicit instructions (such as a photograph of a bench in a park ).…”

“…Hence, to accelerate the transition toward a globally accessible screening procedure for MCI ( Sabbagh et al, 2020c , 2022 ; Liss et al, 2021 ), recent studies evaluating the potential utility of gaze metrics in the detection and characterization of MCI have been reviewed and discussed. Considering the multiple advantages of eye-tracking technology, it is hoped that presented compilation of impactful studies presented here, will spark interest among clinicians and foster future collaborations between neuroscience and machine learning, leading to an improved characterization of individuals along the Alzheimer’s disease trajectory ( Lagun et al, 2011 ; Zola et al, 2013 ; Wolf et al, 2021a ; Ning et al, 2022 ; Przybyszewski et al, 2023 ).…”

The effect of Immersive Virtual Reality on balance: an exploratory study on the feasibility of head-mounted displays for balance evaluation

“…Future studies could include monitoring eye-movement patterns through such cameras as adding an additional biosignal might improve the overall sensitivity and specificity of the proposed solution. Furthermore, integration of eye-trakicng and artificial intelligence into the VR software could aid in monitoring of patients with neurodegenerative diseases 26 .…”

Detecting Abnormal Eye Movements in Patients with Neurodegenerative Diseases – Current Insights

“…Whilst several studies and reviews 1 have provided an overview of ocular motor disturbance in neurodegenerative conditions, a discussion of the practical application of these findings in the differential diagnosis of neurodegenerative disorders is limited. Whether ocular motor findings can be used to feed predictive models 2,3 for differential diagnosis has not yet been established. Furthermore, ocular motor tests or paradigms can be clinical -those that can be performed at the bedside -or experimental, requiring assessments to be performed using an eye tracker and screen.…”