Validation of a Behavioral Approach for Measuring Saccades in Parkinson's Disease

Machine Learning and Eye Movements Give Insights into Neurodegenerative Disease Mechanisms

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.

"Feasibility and utility of a simple computerized test for measuring saccade latency in progressive supranuclear palsy- a proof-of-concept study"

Background

Reliable detection of slowed vertical saccades may help discriminate progressive supranuclear palsy (PSP) from the subset of Parkinson’s disease patients who lack tremor (akinetic-rigid or PD-postural instability and gait disorder PIGD subtype), and from age-related oculomotor changes. We investigated the feasibility of a camera-less computerized behavioral saccade latency paradigm previously validated in PD to discriminate probable PSP-Richardson syndrome (PSP-RS) from PD-PIGD and age-matched controls.

Methods

In this proof-of-concept case-control study, reflexive saccade latencies were measured in 5 subjects with probable PSP-RS, 5 subjects with PD-PIGD subtype, and 5 age-matched controls using the behavioral paradigm. The battery was repeated approximately one month later. All subjects were examined off levodopa by a movement disorders neurologist and by an ophthalmologist, who also performed a dilated eye exam.

Results

Vertical prosaccade latencies were longer in the PSP group (median = 903 ms) relative to PD (median = 268 ms) and control groups (median = 235 ms), with no overlap between groups (100% accuracy). PSP subjects also had larger vertical-horizontal discrepancies than comparison groups. Test-retest reliability for the behavioral saccade measures was good (interclass correlation coefficient = 0.948; 95% confidence interval [0.856, 0.982]), and the measures strongly correlated with clinical ratings.

Conclusions

Computerized behavioral measurement of reflexive saccade latency is feasible in PSP, and potentially discriminates probable PSP-RS from the PD-PIGD subtype. Findings from this proof-of-concept study support utility of the approach for obtaining objective saccade metrics in clinical evaluations and for tracking change in future, larger trials of moderately advanced PSP. Future studies should also examine the behavioral paradigm in earlier presentations of PSP and other subtypes of PSP.

Aging and eye tracking: in the quest for objective biomarkers

Recent applications of eye tracking for diagnosis, prognosis and follow-up of therapy in age-related neurological or psychological deficits have been reviewed. The review is focused on active aging, neurodegeneration and cognitive impairments. The potential impacts and current limitations of using characterizing features of eye movements and pupillary responses (oculometrics) as objective biomarkers in the context of aging are discussed. A closer look into the findings, especially with respect to cognitive impairments, suggests that eye tracking is an invaluable technique to study hidden aspects of aging that have not been revealed using any other noninvasive tool. Future research should involve a wider variety of oculometrics, in addition to saccadic metrics and pupillary responses, including nonlinear and combinatorial features as well as blink- and fixation-related metrics to develop biomarkers to trace age-related irregularities associated with cognitive and neural deficits.

Eye tracking - The overlooked method to measure cognition in neurodegeneration?

Eye tracking (ET) studies are becoming increasingly popular due to rapid methodological and technological advances as well as the development of cost efficient and portable eye trackers. Although historically ET has been mostly employed in psychophysics or developmental cognition studies, there is also promising scope to use ET for movement disorders and measuring cognitive processes in neurodegeneration. Particularly, ET can be a powerful tool for cognitive and neuropsychological assessments of patients with pathologies affecting motor and verbal abilities, as tasks can be adapted without requiring motor (except eye movements) or verbal responses. In this review, we will examine the existing evidence of ET methods in neurodegenerative conditions and its potential clinical impact for cognitive assessment. We highlight that current evidence for ET is mostly focused on diagnostics of cognitive impairments in neurodegenerative disorders, where it is debatable whether it has any more sensitivity or specificity than existing cognitive assessments. By contrast, there is currently a lack of ET studies in more advanced disease stages, when patients' motor and verbal functions can be significantly affected, and standard cognitive assessments are challenging or often not possible. We conclude that ET is a promising method not only for cognitive diagnostics but more importantly, for potential cognitive disease tracking in progressive neurodegenerative conditions.