{"title":"Cerebral/Cortical Visual Impairment Classification and Categorization Using Eye Tracking Measures of Oculomotor Function","authors":"Melinda Y. Chang MD , Mark S. Borchert MD","doi":"10.1016/j.xops.2025.100728","DOIUrl":null,"url":null,"abstract":"<div><h3>Purpose</h3><div>Cerebral/cortical visual impairment (CVI) is a leading cause of pediatric visual impairment and is frequently associated with abnormal ocular motility. Eye tracking has previously been used to characterize oculomotor function in CVI. The purpose of this study was to evaluate the utility of eye tracking in diagnosis, categorization, and prognostication of CVI.</div></div><div><h3>Design</h3><div>Prospective longitudinal study.</div></div><div><h3>Participants</h3><div>Thirty-nine children with CVI and 41 age-matched controls.</div></div><div><h3>Methods</h3><div>Children with CVI underwent 4 eye tracking sessions over 1 year, and age-matched controls completed 1 eye tracking session. Fixations and saccades were labeled by the eye tracking software and used to compute 9 oculomotor features. In children with CVI, unsupervised data-driven clustering analysis using these 9 features was performed to identify 3 CVI eye tracking oculomotor groups. Clinical and demographic characteristics of eye tracking oculomotor groups were compared.</div></div><div><h3>Main Outcome Measures</h3><div>(1) Area under the curve (AUC) for eye tracking oculomotor features in classifying patients with CVI and controls; (2) differences between 3 CVI eye tracking oculomotor groups on clinical and demographic characteristics; and (3) change in visual acuity (VA) over 1 year in 3 CVI eye tracking oculomotor groups.</div></div><div><h3>Results</h3><div>Six oculomotor features (fixation and saccade latency, frequency, and off-screen proportion) had an AUC ≥0.90 in classifying children with CVI and controls (<em>P</em> < 0.0001). Cerebral/cortical visual impairment eye tracking oculomotor groups had significantly different VA (<em>P</em> < 0.0001) and change in VA over 1 year (<em>P</em> = 0.049). Patients in group B, who had the greatest improvement in VA, were younger and had higher rates of term hypoxic ischemic encephalopathy.</div></div><div><h3>Conclusions</h3><div>Eye tracking measures of oculomotor function accurately distinguish between children with CVI and age-matched controls. Clustering analysis revealed 3 CVI eye tracking oculomotor groups with prognostic significance. Eye tracking shows promise as an objective, quantitative measure of oculomotor function in CVI that may in future be useful in both clinical practice (for longitudinal assessment, prognostication, and guiding individualized interventions) and research (as an outcome measure or method to stratify patients in clinical trials).</div></div><div><h3>Financial Disclosure(s)</h3><div>Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.</div></div>","PeriodicalId":74363,"journal":{"name":"Ophthalmology science","volume":"5 3","pages":"Article 100728"},"PeriodicalIF":3.2000,"publicationDate":"2025-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Ophthalmology science","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2666914525000260","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"OPHTHALMOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Purpose
Cerebral/cortical visual impairment (CVI) is a leading cause of pediatric visual impairment and is frequently associated with abnormal ocular motility. Eye tracking has previously been used to characterize oculomotor function in CVI. The purpose of this study was to evaluate the utility of eye tracking in diagnosis, categorization, and prognostication of CVI.
Design
Prospective longitudinal study.
Participants
Thirty-nine children with CVI and 41 age-matched controls.
Methods
Children with CVI underwent 4 eye tracking sessions over 1 year, and age-matched controls completed 1 eye tracking session. Fixations and saccades were labeled by the eye tracking software and used to compute 9 oculomotor features. In children with CVI, unsupervised data-driven clustering analysis using these 9 features was performed to identify 3 CVI eye tracking oculomotor groups. Clinical and demographic characteristics of eye tracking oculomotor groups were compared.
Main Outcome Measures
(1) Area under the curve (AUC) for eye tracking oculomotor features in classifying patients with CVI and controls; (2) differences between 3 CVI eye tracking oculomotor groups on clinical and demographic characteristics; and (3) change in visual acuity (VA) over 1 year in 3 CVI eye tracking oculomotor groups.
Results
Six oculomotor features (fixation and saccade latency, frequency, and off-screen proportion) had an AUC ≥0.90 in classifying children with CVI and controls (P < 0.0001). Cerebral/cortical visual impairment eye tracking oculomotor groups had significantly different VA (P < 0.0001) and change in VA over 1 year (P = 0.049). Patients in group B, who had the greatest improvement in VA, were younger and had higher rates of term hypoxic ischemic encephalopathy.
Conclusions
Eye tracking measures of oculomotor function accurately distinguish between children with CVI and age-matched controls. Clustering analysis revealed 3 CVI eye tracking oculomotor groups with prognostic significance. Eye tracking shows promise as an objective, quantitative measure of oculomotor function in CVI that may in future be useful in both clinical practice (for longitudinal assessment, prognostication, and guiding individualized interventions) and research (as an outcome measure or method to stratify patients in clinical trials).
Financial Disclosure(s)
Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.