Eye movement control is impaired in some neurological conditions, but the impact of COVID-19 on eye movements remains unknown. This study aims to investigate differences in oculomotor function and pupil response in individuals who suffer post-COVID-19 condition (PCC) with cognitive deficits. Saccades, smooth pursuit, fixation, vergence and pupillary response were recorded using an eye tracker. Eye movements and pupil response parameters were computed. Data from 16 controls, 38 COVID mild (home recovery) and 19 COVID severe (hospital admission) participants were analyzed. Saccadic latencies were shorter in controls (183 ± 54 ms) than in COVID mild (236 ± 83 ms) and COVID severe (227 ± 42 ms) participants (p = 0.017). Fixation stability was poorer in COVID mild participants (Bivariate Contour Ellipse Area of 0.80 ± 1.61°² vs 0.36 ± 0.65 °² for controls, p = 0.019), while percentage of pupil area reduction/enlargement was reduced in COVID severe participants (39.7 ± 12.7%/31.6 ± 12.7% compared to 51.7 ± 22.0%/49.1 ± 20.7% in controls, p < 0.015). The characteristics of oculomotor alterations found in PCC may be useful to understand different pathophysiologic mechanisms.

The online version contains supplementary material available at 10.1038/s41598-025-34664-2.

The Trail Making Test (TMT) is a neuropsychological test to assess cognitive impairment. Although it is widely used in clinical practice, it presents some limitations such as the lack of timeliness. The oculomotor system is altered with cognitive impairment; thus, the objective of this work was to study whether the analysis of eye movements during the test can provide further information for an earlier diagnosis. Five healthy participants were recruited the study and performed the TMT while their eye movements were recorded. The results showed relations between saccadic and fixational parameters and time to completion, suggesting the potential of eye tracking technology to complement the test and potentially overcome its limitations.

Cognitive impairment is common in Post-COVID-19 Condition (PCC), yet full neuropsychological testing remains resource-intensive. Because eye movements are known to be altered in certain cognitive disorders, Eye-Tracking (ET) offers a fast, non-invasive complementary approach for large-scale screening. This study aimed to predict neuropsychological test scores of participants with PCC from ET metrics using machine and deep learning models. ET data was collected from 172 participants performing a battery of visual tasks designed to elicit smooth pursuit and fixational eye movements, as well as pupil responses to light. Cognitive performance was assessed through established neuropsychological tests. We applied regression and classification models (e.g., Random Forest, XGBoost, and deep neural networks) to predict neuropsychological performance. Models were trained using ET data alone and in combination with the Montreal Cognitive Assessment (MoCA) scores, a widely used neuropsychological test for global cognitive screening. Although predicting individual test scores was challenging, combining them into a global composite measure improved performance. Model sensitivity and specificity reached 88% and 34% using ET data alone, and 87% and 60% when integrating ET with MoCA. This last trained model outperformed the conventional MoCA, highlighting the potential of ET as a rapid screening support tool for cognitive assessment.