Classification and staging of Parkinson's disease using video-based eye tracking

Donald C Brien; Heidi C Riek; Rachel Yep; Jeff Huang; Brian Coe; Corson Areshenkoff; David Grimes; Mandar Jog; Anthony Lang; Connie Marras; Mario Masellis; Paula McLaughlin; Alicia Peltsch; Angela Roberts; Brian Tan; Derek Beaton; Wendy Lou; Richard Swartz; ONDRI Investigators; Douglas P Munoz

doi:10.1016/j.parkreldis.2023.105316

Classification and staging of Parkinson's disease using video-based eye tracking

Parkinsonism Relat Disord. 2023 May:110:105316. doi: 10.1016/j.parkreldis.2023.105316. Epub 2023 Feb 8.

Authors

Donald C Brien¹, Heidi C Riek², Rachel Yep³, Jeff Huang⁴, Brian Coe⁵, Corson Areshenkoff⁶, David Grimes⁷, Mandar Jog⁸, Anthony Lang⁹, Connie Marras¹⁰, Mario Masellis¹¹, Paula McLaughlin¹², Alicia Peltsch¹³, Angela Roberts¹⁴, Brian Tan¹⁵, Derek Beaton¹⁶, Wendy Lou¹⁷, Richard Swartz¹⁸; ONDRI Investigators; Douglas P Munoz¹⁹

Affiliations

¹ Centre for Neuroscience Studies, Queen's University, Kingston, ON, Canada. Electronic address: [email protected].
² Centre for Neuroscience Studies, Queen's University, Kingston, ON, Canada. Electronic address: [email protected].
³ Centre for Neuroscience Studies, Queen's University, Kingston, ON, Canada. Electronic address: [email protected].
⁴ Centre for Neuroscience Studies, Queen's University, Kingston, ON, Canada. Electronic address: [email protected].
⁵ Centre for Neuroscience Studies, Queen's University, Kingston, ON, Canada. Electronic address: [email protected].
⁶ Centre for Neuroscience Studies, Queen's University, Kingston, ON, Canada. Electronic address: [email protected].
⁷ Ottawa Hospital, uOttawa Brain and Mind Research Institute, Ottawa, ON, Canada. Electronic address: [email protected].
⁸ PF Centre of Excellence, London Movement Disorders Centre, Lawson Health Research Institute, London, ON, Canada. Electronic address: [email protected].
⁹ Edmond J. Safra Program in Parkinson's Disease, University Health Network and the Department of Medicine, Division of Neurology, University of Toronto, Toronto, ON, Canada. Electronic address: [email protected].
¹⁰ Toronto Western Hospital Movement Disorders Centre and the Edmond J Safra Program in Parkinson's Disease, University of Toronto, Toronto, ON, Canada. Electronic address: [email protected].
¹¹ Sunnybrook Health Sciences Centre, Medicine (Neurology), Toronto, ON, Canada. Electronic address: [email protected].
¹² Centre for Neuroscience Studies, Queen's University, Kingston, ON, Canada; Nova Scotia Health, Halifax, NS, Canada; Department of Psychology and Neuroscience, Department of Medicine (Geriatrics), Dalhousie University, Halifax, NS, Canada. Electronic address: [email protected].
¹³ Faculty of Engineering and Applied Science, Queen's University, Kingston, ON, Canada. Electronic address: [email protected].
¹⁴ School of Communication Sciences and Disorders, Department of Computer Science, University of Western Ontario, London, ON, Canada. Electronic address: [email protected].
¹⁵ Rotman Research Institute, Baycrest Health Sciences, Toronto, ON, Canada. Electronic address: [email protected].
¹⁶ Data Science & Advanced Analytics (DSAA), St. Michael's Hospital, Unity Health Toronto, Toronto, ON, Canada. Electronic address: [email protected].
¹⁷ Dalla Lana School of Public Health, University of Toronto, Toronto, ON, Canada. Electronic address: [email protected].
¹⁸ Hurvitz Brain Sciences Program, Sunnybrook Health Sciences Centre; Faculty of Medicine, Department of Medicine (Neurology), University of Toronto, Toronto, ON, Canada. Electronic address: [email protected].
¹⁹ Centre for Neuroscience Studies, Queen's University, Kingston, ON, Canada; Department of Biomedical and Molecular Sciences, Queen's University, Kingston, ON, Canada. Electronic address: [email protected].

PMID: 36822878
DOI: 10.1016/j.parkreldis.2023.105316

Abstract

Introduction: 83% of those diagnosed with Parkinson's Disease (PD) eventually progress to PD with mild cognitive impairment (PD-MCI) followed by dementia (PDD) - suggesting a complex spectrum of pathology concomitant with aging. Biomarkers sensitive and specific to this spectrum are required if useful diagnostics are to be developed that may supplement current clinical testing procedures. We used video-based eye tracking and machine learning to develop a simple, non-invasive test sensitive to PD and the stages of cognitive dysfunction.

Methods: From 121 PD (45 Cognitively Normal/45 MCI/20 Dementia/11 Other) and 106 healthy controls, we collected video-based eye tracking data on an interleaved pro/anti-saccade task. Features of saccade, pupil, and blink behavior were used to train a classifier to predict confidence scores for PD/PD-MCI/PDD diagnosis.

Results: The Receiver Operator Characteristic Area Under the Curve (ROC-AUC) of the classifier was 0.88, with the cognitive-dysfunction subgroups showing progressively increased AUC, and the AUC of PDD being 0.95. The classifier reached a sensitivity of 83% and a specificity of 78%. The confidence scores predicted PD motor and cognitive performance scores.

Conclusion: Biomarkers of saccade, pupil, and blink were extracted from video-based eye tracking to create a classifier with high sensitivity to the landscape of PD cognitive and motor dysfunction. A complex landscape of PD is revealed through a quick, non-invasive eye tracking task and our model provides a framework for such a task to be used as a supplementary screening tool in the clinic.

Keywords: Blink; Classification; Dementia; Functional data analysis; Machine learning; Parkinson's disease; Pupil; Saccade.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Biomarkers
Cognitive Dysfunction* / diagnosis
Cognitive Dysfunction* / etiology
Cognitive Dysfunction* / psychology
Dementia* / diagnosis
Eye-Tracking Technology
Humans
Neuropsychological Tests
Parkinson Disease*

Substances

Biomarkers

Grants and funding

FDN-148418/CIHR/Canada