AUTHOR=Ma Da , Pasquale Louis R. , Girard Michaël J. A. , Leung Christopher K. S. , Jia Yali , Sarunic Marinko V. , Sappington Rebecca M. , Chan Kevin C. 

TITLE=Reverse translation of artificial intelligence in glaucoma: Connecting basic science with clinical applications

JOURNAL=Frontiers in Ophthalmology

VOLUME=Volume 2 - 2022

YEAR=2023

URL=https://www.frontiersin.org/journals/ophthalmology/articles/10.3389/fopht.2022.1057896

DOI=10.3389/fopht.2022.1057896

ISSN=2674-0826

ABSTRACT=Artificial intelligence (AI) has been approved for biomedical research in diverse areas from bedside clinical study to benchtop basic scientific research. For ophthalmic research, in particular glaucoma, AI applications are rapidly growing in the clinical field given the vast data available and the introduction of federated learning, while AI for basic science remains limited despite its useful power in providing mechanistic insight. In this perspective, we discuss recent progress, opportunities, and challenges in the application of AI in glaucoma. We focus on the research paradigm of reverse translation, in which clinical data get translated into basic science studies. We elaborate on several distinctive research areas including prediction of glaucoma risk and visual field progression; optic disc and optic nerve head abnormality detection; structural and biomechanical models for glaucoma morphology; shape and texture analyses; AI in optical coherence tomography angiography; AI-derived data-driven glaucoma sub-phenotyping; as well as the applications for federated learning and explainable AI. We conclude with some thoughts on future directions.