Machine Learning-Based Detection of Cognitive Impairment from Eye-Tracking in Smooth Pursuit Tasks

Groznik, Vida; De Gobbis, Andrea; Georgiev, Dejan; Semeja, Aleš; Sadikov, Aleksander

doi:10.3390/app15147785

Open AccessArticle

Machine Learning-Based Detection of Cognitive Impairment from Eye-Tracking in Smooth Pursuit Tasks

by

Vida Groznik

^1,2,*

,

Andrea De Gobbis

^1,2

,

Dejan Georgiev

^1,3

,

Aleš Semeja

²

and

Aleksander Sadikov

^1,2,*

¹

Faculty of Computer and Information Science, University of Ljubljana, 1000 Ljubljana, Slovenia

²

NEUS Diagnostics d.o.o., 1000 Ljubljana, Slovenia

³

Department of Neurology, University Medical Centre Ljubljana, 1000 Ljubljana, Slovenia

^*

Authors to whom correspondence should be addressed.

Appl. Sci. 2025, 15(14), 7785; https://doi.org/10.3390/app15147785

Submission received: 31 May 2025 / Revised: 7 July 2025 / Accepted: 7 July 2025 / Published: 11 July 2025

(This article belongs to the Special Issue Artificial Intelligence Applications in Healthcare and Precision Medicine, 2nd Edition)

Download

Browse Figures

Versions Notes

Abstract

Mild cognitive impairment represents a transitional phase between healthy ageing and dementia, including Alzheimer’s disease. Early detection is essential for timely clinical intervention. This study explores the viability of smooth pursuit eye movements (SPEM) as a non-invasive biomarker for cognitive impairment. A total of 115 participants—62 with cognitive impairment and 53 cognitively healthy controls—underwent comprehensive neuropsychological assessments followed by an eye-tracking task involving smooth pursuit of horizontally and vertically moving stimuli at three different speeds. Quantitative metrics such as tracking accuracy were extracted from the eye movement recordings. These features were used to train machine learning models to distinguish cognitively impaired individuals from controls. The best-performing model achieved an area under the ROC curve (AUC) of approximately 68 %, suggesting that SPEM-based assessment has potential as part of an ensemble of eye-tracking based screening methods for early cognitive decline. Of course, additional paradigms or task designs are required to enhance diagnostic performance.

Keywords: machine learning; eye-tracking; smooth pursuit; cognitive impairment

Share and Cite

MDPI and ACS Style

Groznik, V.; De Gobbis, A.; Georgiev, D.; Semeja, A.; Sadikov, A. Machine Learning-Based Detection of Cognitive Impairment from Eye-Tracking in Smooth Pursuit Tasks. Appl. Sci. 2025, 15, 7785. https://doi.org/10.3390/app15147785

AMA Style

Groznik V, De Gobbis A, Georgiev D, Semeja A, Sadikov A. Machine Learning-Based Detection of Cognitive Impairment from Eye-Tracking in Smooth Pursuit Tasks. Applied Sciences. 2025; 15(14):7785. https://doi.org/10.3390/app15147785

Chicago/Turabian Style

Groznik, Vida, Andrea De Gobbis, Dejan Georgiev, Aleš Semeja, and Aleksander Sadikov. 2025. "Machine Learning-Based Detection of Cognitive Impairment from Eye-Tracking in Smooth Pursuit Tasks" Applied Sciences 15, no. 14: 7785. https://doi.org/10.3390/app15147785

APA Style

Groznik, V., De Gobbis, A., Georgiev, D., Semeja, A., & Sadikov, A. (2025). Machine Learning-Based Detection of Cognitive Impairment from Eye-Tracking in Smooth Pursuit Tasks. Applied Sciences, 15(14), 7785. https://doi.org/10.3390/app15147785

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Machine Learning-Based Detection of Cognitive Impairment from Eye-Tracking in Smooth Pursuit Tasks

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI