Clinically accessible eye-tracking in thyroid-associated ophthalmopathy: exploratory classification modeling and gaze allocation to disease-related periocular images
Chunhui Yang, Ya Shen, Jian Song, Yuqing Chen, Chengcheng Zeng, Ruili Wei · 2026
Read Clinically accessible eye-tracking in thyroid-associated ophthalmopathy: exploratory classification modeling and gaze allocation to disease-related periocular images by Chunhui Yang, Ya Shen, Jian Song, Yuqing Chen, Chengcheng Zeng, Ruili Wei (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13543637.txt.
Description
Chunhui Yang and colleagues published a 2026 study testing whether ordinary eye-tracking equipment can help recognise thyroid-associated ophthalmopathy, the autoimmune eye disease that distorts the tissues around the eye. A total of 229 adults at a specialist centre, 181 patients and 48 healthy controls, completed fixation, smooth-pursuit, and picture-viewing tasks while their gaze was recorded. Machine-learning models were trained on how gaze spread across a nine-zone grid during pursuit.
Fixation steadiness was similar in both groups, though patients' gaze dispersed more widely. The pursuit-based model classified patients well, reaching an accuracy score of 0.903 with age and sex included. Viewing habits also differed: patients looked less at obvious disease features in early-stage images and more at near-recovered appearances in later ones. How eyes move, the authors suggest, betrays both the disease and the patient's attention to it.
Catalog record
| CREATOR | Chunhui Yang, Ya Shen, Jian Song, Yuqing Chen, Chengcheng Zeng, Ruili Wei |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 31546 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |