Related Experiment Video
Updated: Jul 28, 2025
05:54
Eye-tracking to Distinguish Comprehension-based and Oculomotor-based Regressive Eye Movements During Reading
Published on: October 18, 2018
6.3K
Clinical availability of eye movement during reading
Yasuhiro Watanabe1, Suzuha Takeuchi1, Kazutake Uehara2
1Division of Neurology, Department of Brain and Neurosciences, Faculty of Medicine, Tottori University, Yonago, Japan.
Neuroscience Research
|May 28, 2023
Summary
Analyzing eye movements aids neurological diagnosis. Vertical reading tasks effectively identified abnormalities in Parkinson
Area of Science:
- Ophthalmology
- Neurology
- Medical Diagnostics
Background:
- Ocular movement analysis offers potential for neurological diagnosis.
- Current diagnostic devices for eye movement analysis are limited.
- Investigating the efficacy of eye movement analysis is crucial.
Purpose of the Study:
- To explore the efficacy of analyzing eye movements for neurological diagnosis.
- To differentiate between patients with Parkinson's disease (PD), spinocerebellar degeneration (SCD), progressive supranuclear palsy (PSP), and healthy controls using eye movement analysis.
Main Methods:
- Participants (PD, SCD, PSP, controls) read horizontal and vertical sentences aloud.
- Extracted eye movement parameters included speed, travel distance, and fixation/saccade ratio.
- Deep learning image classification was applied to eye movement patterns.
Main Results:
- Parkinson's disease patients showed altered reading velocity and fixation/saccade ratio.
- Spinocerebellar degeneration patients exhibited dysmetria and nystagmus.
- Progressive supranuclear palsy patients displayed aberrant vertical gaze parameters.
- Vertical sentence reading was more sensitive in detecting abnormalities than horizontal reading.
- Regression and machine learning analyses achieved over 90% accuracy in group differentiation.
Conclusions:
- Eye movement analysis is a useful and easily applicable diagnostic tool for neurological disorders.
- Vertical reading tasks enhance the detection of specific neuro-ophthalmic abnormalities.
- Deep learning models demonstrate high accuracy in classifying neurological conditions based on eye movements.
