Glaucoma Diagnosis Through the Integration of Optical Coherence Tomography/Angiography and Machine Learning Diagnostic Models

Abstract

Karanjit S Kooner,1,2 Ashika Angirekula,1 Alex H Treacher,3 Ghadeer Al-Humimat,1,4 Mohamed F Marzban,5 Alyssa Chen,1 Roma Pradhan,1 Nita Tunga,1 Chuhan Wang,1 Pranati Ahuja,1 Hafsa Zuberi,1 Albert A Montillo3,6,7 1Department of Ophthalmology, University of Texas Southwestern Medical Center, Dallas, TX, USA; 2Department of Ophthalmology, Veteran Affairs North Texas Health Care System Medical Center, Dallas, TX, USA; 3Lyda Hill Department of Bioinformatics, University of Texas Southwestern Medical Center, Dallas, TX, USA; 4Department of Ophthalmology, King Hussein Medical Center, Amman, Jordan; 5Department of Electrical Engineering, University of Texas at Dallas, Dallas, TX, USA; 6Department of Radiology, University of Texas Southwestern Medical Center, Dallas, TX, USA; 7Advanced Imaging Research Center, University of Texas Southwestern Medical Center, Dallas, TX, USACorrespondence: Karanjit S Kooner, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX, 75390-9057, USA, Tel [phone], Fax [phone], Email [email protected] Albert A Montillo, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX, 75390-9057, USA, Email [email protected]: To establish optical coherence tomography (OCT)/angiography (OCTA) parameter ranges for healthy eyes (HE) and glaucomatous eyes (GE) for a North Texas based population; to develop a machine learning (ML) tool and to identify the most accurate diagnostic parameters for clinical glaucoma diagnosis.Patients and Methods: In this retrospective cross-sectional study, we included 1371 eligible eyes, 462 HE and 909 GE (377 ocular hypertension, 160 mild, 156 moderate, 216 severe), from 735 subjects. Demographic data and full OCTA parameters were collected. A Kruskal–Wallis test was used to produce the normative database. Models were trained to solve a two-class problem (HE vs GE) and four-class problem (HE vs mild vs moderate vs severe GE). A rigorous nested, stratified, group, 5× 10 fold cross-validation strategy was applied to partition the data. Six ML algorithms were compared using classical and deep learning approaches. Over 2500 ML models were optimized using random search, with performance compared using mean validation accuracy. Final performance was reported on held-out test data using accuracy and F1 score. Decision trees and feature importance were produced for the final model.Results: We found differences across glaucoma severities for age, gender, hypertension, Black and Asian race, and all OCTA parameters, except foveal avascular zone area and perimeter (p< 0.05). The XGBoost algorithm achieved the highest test performance for both the two-class (F1 score 83.8%; accuracy 83.9%; standard deviation 0.03%) and four-class (F1 score 62.4%; accuracy 71.3%; standard deviation 0.013%) problem. A set of interpretable decision trees provided the most important predictors of the final model; inferior temporal and inferior hemisphere vessel density and peripapillary retinal nerve fiber layer thickness were identified as key diagnostic parameters.Conclusion: This study established a normative database for our North Texas based population and created ML tools utilizing OCT/A that may aid clinicians in glaucoma management.Keywords: glaucoma, optical coherence tomography angiography, deep learning

Keywords

• glaucoma
• optical coherence tomography angiography
• deep learning