Accepted for/Published in: JMIR mHealth and uHealth
Date Submitted: Sep 2, 2025
Date Accepted: Jun 26, 2026
Utility of Tablet-Based Eye-Tracking for Early Screening of Post-Stroke Cognitive Impairment: A Diagnostic Cohort Study
ABSTRACT
Background:
Post-stroke cognitive impairment (PSCI) commonly complicates stroke recovery and significantly affects long-term outcomes. Current cognitive assessment tools have limitations in accessibility, cost, and standardization, particularly during early screening. Portable, quantitative technologies offer a promising approach to improve PSCI detection and intervention.
Objective:
This study aimed to evaluate the clinical utility of a tablet-based eye-tracking application for the early screening of PSCI. We quantitatively analyzed oculomotor-cognitive correlations to develop and validate a screening model that provides an economical, accessible, and standardized tool for early PSCI detection, thereby supporting rehabilitation planning and improving prognosis.
Methods:
We enrolled a prospective cohort of 122 patients with acute cerebral infarction. Based on 3-month cognitive assessments (MMSE and MoCA), we classified patients into PSCI and non-PSCI (NPSCI) groups. We compared demographic, clinical, and oculomotor parameters between groups. We developed a multivariable logistic regression model to predict PSCI risk and performed stratified analyses according to white matter hyperintensity (WMH) severity and infarct volume. We also compared 20 healthy controls with NPSCI patients.
Results:
The tablet-based eye-tracking system revealed significant oculomotor differences between the PSCI and NPSCI groups, including prolonged saccadic latency, reduced velocity, increased error rate, and decreased novelty preference. The model incorporating age, education, NIHSS score, and correct saccade latency showed strong discriminative ability (AUC = 0.860, 95% CI: 0.793–0.927). Oculomotor patterns did not differ significantly between NPSCI patients and healthy controls. WMH severity and infarct volume correlated with specific oculomotor alterations.
Conclusions:
Key predictors of 3-month PSCI included age, education, NIHSS score, and correct saccade latency. A nomogram based on these variables demonstrated high accuracy and clinical utility for early PSCI identification. The tablet-based eye-tracking system provides a practical and scalable screening tool for post-stroke cognitive assessment. Clinical Trial: not applicable.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.