Extracting decision-making features from the unstructured eye movements of clinicians on glaucoma OCT reports and developing AI models to classify expertise

Michelle Akerman; Sanmati Choudhary; Jeffrey M Liebmann; George A Cioffi; Royce W S Chen; Kaveri A Thakoor

doi:10.3389/fmed.2023.1251183

Extracting decision-making features from the unstructured eye movements of clinicians on glaucoma OCT reports and developing AI models to classify expertise

Front Med (Lausanne). 2023 Sep 29:10:1251183. doi: 10.3389/fmed.2023.1251183. eCollection 2023.

Authors

Michelle Akerman¹, Sanmati Choudhary², Jeffrey M Liebmann³, George A Cioffi³, Royce W S Chen³, Kaveri A Thakoor^{1

2

3}

Affiliations

¹ Department of Biomedical Engineering, Columbia University, New York, NY, United States.
² Department of Computer Science, Columbia University, New York, NY, United States.
³ Edward S. Harkness Eye Institute, Department of Ophthalmology, Columbia University Irving Medical Center, New York, NY, United States.

Abstract

This study aimed to investigate the eye movement patterns of ophthalmologists with varying expertise levels during the assessment of optical coherence tomography (OCT) reports for glaucoma detection. Objectives included evaluating eye gaze metrics and patterns as a function of ophthalmic education, deriving novel features from eye-tracking, and developing binary classification models for disease detection and expertise differentiation. Thirteen ophthalmology residents, fellows, and clinicians specializing in glaucoma participated in the study. Junior residents had less than 1 year of experience, while senior residents had 2-3 years of experience. The expert group consisted of fellows and faculty with over 3 to 30+ years of experience. Each participant was presented with a set of 20 Topcon OCT reports (10 healthy and 10 glaucomatous) and was asked to determine the presence or absence of glaucoma and rate their confidence of diagnosis. The eye movements of each participant were recorded as they diagnosed the reports using a Pupil Labs Core eye tracker. Expert ophthalmologists exhibited more refined and focused eye fixations, particularly on specific regions of the OCT reports, such as the retinal nerve fiber layer (RNFL) probability map and circumpapillary RNFL b-scan. The binary classification models developed using the derived features demonstrated high accuracy up to 94.0% in differentiating between expert and novice clinicians. The derived features and trained binary classification models hold promise for improving the accuracy of glaucoma detection and distinguishing between expert and novice ophthalmologists. These findings have implications for enhancing ophthalmic education and for the development of effective diagnostic tools.

Keywords: eye-tracking; fixations; glaucoma; neural networks; optical coherence tomography; unsupervised clustering.

Grants and funding

Supported in part by an unrestricted grant to the Columbia University Department of Ophthalmology from Research to Prevent Blindness, Inc., New York, NY, United States.