Automatic Screening of Parkinson's Disease from Visual Explorations
By: Maria F. Alcala-Durand , J. Camilo Puerta-Acevedo , Julián D. Arias-Londoño and more
Potential Business Impact:
Finds Parkinson's early by watching how eyes move.
Eye movements can reveal early signs of neurodegeneration, including those associated with Parkinson's Disease (PD). This work investigates the utility of a set of gaze-based features for the automatic screening of PD from different visual exploration tasks. For this purpose, a novel methodology is introduced, combining classic fixation/saccade oculomotor features (e.g., saccade count, fixation duration, scanned area) with features derived from gaze clusters (i.e., regions with a considerable accumulation of fixations). These features are automatically extracted from six exploration tests and evaluated using different machine learning classifiers. A Mixture of Experts ensemble is used to integrate outputs across tests and both eyes. Results show that ensemble models outperform individual classifiers, achieving an Area Under the Receiving Operating Characteristic Curve (AUC) of 0.95 on a held-out test set. The findings support visual exploration as a non-invasive tool for early automatic screening of PD.
Similar Papers
A digital eye-fixation biomarker using a deep anomaly scheme to classify Parkisonian patterns
CV and Pattern Recognition
Finds Parkinson's early by watching eye movements.
Machine Learning-Based Differential Diagnosis of Parkinson's Disease Using Kinematic Feature Extraction and Selection
Machine Learning (CS)
Helps doctors tell Parkinson's from similar diseases.
Guidelines for Gaze-based Neural Preliminary Diagnosis
Human-Computer Interaction
Tracks eyes to spot brain problems early.