Integrating Multi-Task Eye Tracking and Interpretable Machine Learning for High-Accuracy Screening of Amblyopia in Pediatric Populations
Journal of Eye Movement Research · 02.03.2026 · 19 (2) · 26
DOI: 10.3390/jemr19020026 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Eye Movement Research, online erschienen am 02.03.2026. Verfasst von Xiumei Song und 9 weiteren Autor:innen. Beteiligte Einrichtung: Beijing Tongren Eye Center, Beijing Tongren Hospital, Beijing Ophthalmology & Visual Science Key Laboratory, Capital Medical University, Beijing 1007…. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Wu Jieping Medical Foundation, National Key R&D Program of China, Key Project on Diagnosis & Treatment Equipment and Biomedical Materials, U.K. Research and Innovation.
Abstract (Originalsprache)
Amblyopia is a developmental disorder of spatial vision in which abnormal visual experience leads to persistent reductions in acuity and contrast sensitivity, even after optimal optical correction. We introduce a brief, child-friendly battery of task-evoked eye tracking that probes fixation stability, fine pattern processing, and smooth pursuit control across three simple paradigms. Oculomotor traces are transformed into physiologically interpretable markers—fixation dispersion and saccadic strategy, orientation-dependent drift and stability, pursuit gain, and tracking error—and used to train a compact classifier with subject-wise validation and probability calibration. In a cohort of school-aged participants with clinically diagnosed unilateral amblyopia and age-matched visually normal controls tested under best-corrected viewing conditions, the approach consistently separated groups with stable performance across folds; feature-importance analyses indicated that pursuit- and orientation-dependent markers contributed most. The protocol runs in minutes, is objective and noninvasive, and is well tolerated in pediatric settings. By quantifying functional consequences of amblyopic vision that complement conventional acuity testing, this work positions task-evoked eye movements as practical biomarkers for screening and monitoring, and lays the groundwork for prospective validation and age-stratified norms in community and school-based vision care.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Beijing Tongren Eye Center, Beijing Tongren Hospital, Beijing Ophthalmology & Visual Science Key Laboratory, Capital Medical University, Beijing 100730, China.
- School of Instrumentation and Optoelectronics Engineering, Beihang University, Beijing 100191, China.
- Department of Engineering, University of Cambridge, Cambridge CB3 0FA, UK.
- West China Medical Center, Sichuan University, Chengdu 610065, China.
- Faculty of Medical Sciences, University College London, London WC1E 6DD, UK.
- Darwin College, University of Cambridge, Cambridge CB3 9EU, UK.
ORCID-Profile: Yunhan Zhang, Chenyu Tang, Hubin Zhao, Luigi G Occhipinti, Changbin Zhai
Förderung
- Wu Jieping Medical Foundation
- National Key R&D Program of China, Key Project on Diagnosis & Treatment Equipment and Biomedical Materials
- U.K. Research and Innovation
- U.K. Engineering and Physical Research Council
- British Council UKIERI
- HALEON-Cambridge Advanced Photonics and Electronics (CAPE) partnership
Zitieren
APA
Song, X., Zhang, Y., Chen, H., Tang, C., Yao, B., Zhao, H., Occhipinti, L. G., Nathan, A., Zhai, C., & Gao, S. (2026). Integrating Multi-Task Eye Tracking and Interpretable Machine Learning for High-Accuracy Screening of Amblyopia in Pediatric Populations. Journal of Eye Movement Research, 19(2), 26. https://doi.org/10.3390/jemr19020026
Vancouver
Song X, Zhang Y, Chen H, Tang C, Yao B, Zhao H, et al. Integrating Multi-Task Eye Tracking and Interpretable Machine Learning for High-Accuracy Screening of Amblyopia in Pediatric Populations. Journal of Eye Movement Research. 2026;19(2):26. doi:10.3390/jemr19020026
BibTeX
@article{Song2026,
author = {Song, Xiumei and Zhang, Yunhan and Chen, Hongyu and Tang, Chenyu and Yao, Bohan and Zhao, Hubin and Occhipinti, Luigi G and Nathan, Arokia and Zhai, Changbin and Gao, Shuo},
title = {Integrating Multi-Task Eye Tracking and Interpretable Machine Learning for High-Accuracy Screening of Amblyopia in Pediatric Populations},
journal = {Journal of Eye Movement Research},
year = {2026},
volume = {19},
number = {2},
pages = {26},
doi = {10.3390/jemr19020026}
}
EUVIMED