Related Experiment Video
Updated: Jun 7, 2025
Author Spotlight: Ex Vivo OCT-Based Multimodal Imaging of Human Donor Eyes for Research into Age-Related Macular Degeneration
Published on: May 26, 2023
A Novel Management Challenge in Age-Related Macular Degeneration: Artificial Intelligence and Expert Prediction of
Gregor S Reiter1, Dmitrii Lachinov1, Wolf Bühl2
1Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, Austria.
Purpose:
The progression of geographic atrophy (GA) secondary to age-related macular degeneration is highly variable among individuals. Prediction of the progression is critical to identify patients who will benefit most from the first treatments currently approved. The aim of this study was to investigate the value and difference in predictive power between ophthalmologists and artificial intelligence (AI) in reliably assessing individual speed of GA progression.
Design:
Prospective, expert and AI comparison study.
Participants:
Eyes with natural progression of GA from a prospective study (NCT02503332).
Methods:
Ophthalmologists predicted yearly growth speed of GA as well as selected the potentially faster-growing lesions from 2 eyes based on fundus autofluorescence (FAF), near-infrared reflectance (NIR), and OCT. A deep learning algorithm predicted progression solely on the baseline OCT (Spectralis, Heidelberg Engineering).
Main Outcome Measures:
Accuracy, weighted κ, and concordance index (c-index) between the prediction made by ophthalmology specialists, ophthalmology residents, and the AI algorithm.
Results:
A total of 134 eyes of 134 patients from a phase II clinical trial were included; among them, 53 were from the sham arm, and 81 were from untreated fellow eyes. Four ophthalmologists performed 2880 gradings. Human experts reached an accuracy of 0.37, 0.43, and 0.41 and a κ of 0.06, 0.16, and 0.18 on FAF, NIR + OCT, and FAF + NIR + OCT, respectively. On a pairwise comparison task, human experts achieved a c-index of 0.62, 0.59, and 0.60. Automated AI-based analysis reached an accuracy of 0.48 and κ of 0.23 on the first task, and c-index of 0.69 on the second task solely utilizing OCT imaging.
Conclusions:
Prediction of individual progression will become an important task for patient counseling, most importantly with the treatments becoming available. Human gradings improved with the availability of OCT. However, automated AI performed better than ophthalmologists in several comparisons. Artificial intelligence-supported decisions improve clinical precision, access to timely care for the community, and socioeconomic feasibility in the management of the leading cause of irreversible vision loss.
Financial Disclosure(S):
The author(s) have no proprietary or commercial interest in any materials discussed in this article.
