Microsaccade Dynamics During Visual Fixation as Markers for Parkinson's Disease: A Machine Learning Approach
Yiting Wang1, Panagiota Tsitsi2,3, Ioanna Markaki2,3
1Department of Clinical Neuroscience, Eye and Vision, Karolinska Institutet, Stockholm, Sweden.
Translational Vision Science & Technology
|June 16, 2026
Summary
Microsaccades, or tiny eye movements, can distinguish Parkinson's disease (PD) patients from healthy individuals. This research highlights their potential as early biomarkers for motor dysfunction in PD.
Area of Science:
- Oculomotor research
- Neuroscience
- Biomarker discovery
Background:
- Microsaccades are small, rapid eye movements crucial in visual and oculomotor research.
- Their utility as biomarkers for neurodegenerative movement disorders like Parkinson's disease (PD) is largely unexplored.
Purpose of the Study:
- To investigate if microsaccade characteristics can differentiate individuals with PD from healthy controls (HCs).
- To assess the potential of microsaccades as early diagnostic markers for Parkinson's disease.
Main Methods:
- Eye movements were recorded from 50 individuals with early-to-moderate PD and 43 HCs during a visual fixation task.
- Machine learning classifiers were trained and evaluated using microsaccade features to predict PD status.
- Analysis focused on microsaccade frequency, amplitude, and directional bias.
Main Results:
- Microsaccades in the PD group were more frequent, had larger amplitudes, and showed a stronger horizontal bias compared to HCs.
- Machine learning models significantly outperformed chance, with a polynomial Support Vector Machine (SVM) achieving 77.4% accuracy.
- Balanced sensitivity (76.1%) and specificity (78.9%) were achieved, with improved performance at the subject level by managing low-confidence predictions.
Conclusions:
- Microsaccades contain discriminative information that can distinguish individuals with PD from HCs.
- These findings support the potential of microsaccades as early indicators of motor dysfunction in Parkinson's disease.
- This study provides a foundation for developing clinical prediction models based on oculomotor behavior.
Related Concept Videos
01:24Parkinson Disease ll: Pathophysiology
Parkinson disease (PD) is a progressive neurodegenerative disorder primarily affecting movement, with additional non-motor features. Its pathophysiology involves complex interactions among genetic susceptibility, environmental exposures, and cellular dysfunction, including dopaminergic neuron loss, protein aggregation, and mitochondrial impairment.Selective NeurodegenerationA key feature is the degeneration of dopaminergic neurons in the substantia nigra pars compacta, leading to reduced...
01:15Parkinson's Disease: Overview
Neurodegenerative disorders are progressive diseases that cause irreversible damage and loss to neurons in specific brain areas. Examples of these disorders include Parkinson's disease, Alzheimer's disease, Multiple Sclerosis (MS), and Amyotrophic Lateral Sclerosis (ALS). These disorders share characteristics such as proteinopathies, selective neuronal vulnerability, and a complex interplay between genetic and environmental factors. The primary therapeutic goal for these conditions is to...
01:24Parkinson Disease l: Introduction
Parkinson’s disease is a chronic, progressive neurodegenerative disorder that primarily affects movement. It is characterized by motor symptoms such as resting tremors, muscle rigidity, bradykinesia (slowness of movement), and postural instability. Patients may notice hand tremors at rest, stiffness during movement, or a shuffling gait. In addition to motor features, non-motor symptoms include sleep disturbances, mood and behavioral changes, constipation, and cognitive impairment, all of which...