Clinically accessible eye-tracking in thyroid-associated ophthalmopathy: exploratory classification modeling and gaze allocation to disease-related periocular images.
Eye-tracking model distinguishes thyroid eye disease patients from healthy controls with high accuracy
Clinically accessible eye-tracking in thyroid-associated ophthalmopathy: exploratory classification modeling and gaze allocation to disease-related periocular images.
Thyroid-associated ophthalmopathy (thyroid-associated ophthalmopathy) is an autoimmune orbital disease that may cause ocular motility abnormalities, altered periocular appearance, and psychosocial burden.
This study aimed to evaluate whether clinically accessible eye-tracking could support auxiliary classification of thyroid-associated ophthalmopathy and characterize visual attention patterns toward disease-related periocular images.
In this cross-sectional study, 229 adults from a tertiary ophthalmology center were enrolled, including 181 patients with thyroid-associated ophthalmopathy and 48 healthy controls.
AUC of 0.903 means the eye-tracking model very accurately told patients with thyroid eye disease apart from healthy people
Fixation stability did not differ significantly between groups, but patients with thyroid-associated ophthalmopathy showed increased gaze dispersion.
In image-viewing tasks, gaze allocation differed between groups: compared with controls, patients with thyroid-associated ophthalmopathy paid less attention to more obvious pathological periocular features in earlier-stage images and more attention to near-recovery appearances in later-stage images.
Clinically accessible eye-tracking may provide behavioral markers for auxiliary thyroid-associated ophthalmopathy classification and reveal altered visual attention to thyroid-associated ophthalmopathy-related periocular appearance.
Further validation in larger, independent cohorts is needed.