Automated eye-tracking for Parkinson's disease diagnosis: a proof-of-concept cascade classifier study
Clinical Parkinsonism & Related Disorders · 2026 · 15 · 100509
DOI: 10.1016/j.prdoa.2026.100509 ↗Kurz gefasst
Fachartikel in der Zeitschrift Clinical Parkinsonism & Related Disorders, 2026. Verfasst von J Michael Menke und 4 weiteren Autor:innen. Beteiligte Einrichtung: University of Arizona, Tucson, AZ 85721, USA. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background
Parkinson's disease (PD) is a progressive neurodegenerative disorder of increasing prevalence, with diagnostic accuracy of approximately 26% in early symptomatic patients. There is a need for accurate, non-invasive biomarkers to aid in disease diagnosis.
Methods
This proof-of-concept study enrolled 90 participants (PD n = 30, other movement disorders [OM] n = 30, healthy controls [HC] n = 30) at a single institution. Participants completed two 10-min eye- tracking sessions using the SaccadeDX™ 250-Hz binocular system. A two-level cascade classifier was fitted using elastic-net feature selection followed by logistic regression on the selected features, validated by 10-fold cross-validation. The cascade distinguished HC from movement disorders (Level 1) and PD from OM (Level 2), with the objective of establishing clinical validity - that an eye-tracking signal correlates reliably with PD diagnosis.
Results
Level 1 achieved an area under the curve (AUC) of 0.818 (95% CI: 0.71, 0.91), with a sensitivity of 83% and specificity of 63%. Level 2 achieved an AUC of 0.670 (95% CI: 0.52, 0.80), with a sensitivity of 68% and specificity of 63%. As a proof-of-concept study, the observed performance positions the device as an adjunctive screening tool. Diagnostic discrimination can only be achieved through a much larger Phase III study. Five adverse events were recorded (three cases of dizziness, one of nausea, and one of dry eyes); one participant withdrew from the study.
Conclusions
Preliminary evidence supports clinical validity pending confirmatory Phase III study: reproducible eye-tracking signal for PD is detectable using a two-level cascade classifier. A multi-center confirmatory study is warranted before assessment of clinical utility.
Trial registration
ClinicalTrials.govNCT04925622.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- University of Arizona, Tucson, AZ 85721, USA.
- Barrow Neurological Institute, 240 West Thomas Road, Suite 301, Phoenix, AZ 85013, USA.
- Johns Hopkins University, 3400 North Charles Street, Baltimore, MD 21218, USA.
- Consultant, Cleveland, OH, USA.
Zitieren
APA
Menke, J. M., Aslam, S., Rieiro, H., Waldorf, R., & Shill, H. A. (2026). Automated eye-tracking for Parkinson's disease diagnosis: a proof-of-concept cascade classifier study. Clinical Parkinsonism & Related Disorders, 15, 100509. https://doi.org/10.1016/j.prdoa.2026.100509
Vancouver
Menke JM, Aslam S, Rieiro H, Waldorf R, Shill HA. Automated eye-tracking for Parkinson's disease diagnosis: a proof-of-concept cascade classifier study. Clinical Parkinsonism & Related Disorders. 2026;15:100509. doi:10.1016/j.prdoa.2026.100509
BibTeX
@article{Menke2026,
author = {Menke, J Michael and Aslam, Sana and Rieiro, Hector and Waldorf, Ron and Shill, Holly A},
title = {Automated eye-tracking for Parkinson's disease diagnosis: a proof-of-concept cascade classifier study},
journal = {Clinical Parkinsonism & Related Disorders},
year = {2026},
volume = {15},
pages = {100509},
doi = {10.1016/j.prdoa.2026.100509}
}
EUVIMED