Artificial Intelligence (AI) utilizes the latest cutting technology to identify human diseases.
Screening for glaucoma remains challenging due to the myriad presentations of the condition. Presently, screening is regarded as economically and practically unfeasible.
However, studies are being performed to investigate the possibility of using AI to screen for glaucoma.
A study presented at the 129th annual meeting of the American Academy of Ophthalmology by Anthony Khwaja and his colleagues from the University of London, Institute of Ophthalmology and Moorefields Eye Hospital, has shown that AI can out-perform humans in screening for glaucoma.
The study used 6,304 fundus images gathered for a large, population-based cohort study (EPIC-Norfolk Eye Study) to compare the accuracy of their algorithm and a trained human grader to estimate a key measure of glaucoma, vertical cup-disc ratio. A glaucoma specialist examined the patients to confirm the diagnosis.
Results showed the algorithm correctly identified patients with glaucoma 88 to 90 percent of the time; human graders were correct 79 to 81 percent of the time. The algorithm did not differentiate between those who had glaucoma or might have glaucoma.
It remains to be seen how a single feature of glaucoma (the vertical C:D R) can be used to diagnose glaucoma patients. This feature is dependent on the ISNT rule and is often seen in only 50% of the population.






