Researchers from the Emory Empathetic AI Health Institute (Emory AI.Health) and Cleveland Clinic have developed an AI tool to identify potentially serious eye inflammation caused by the use of anti-vascular endothelial growth factor (VEGF) drugs for neovascular age-related macular degeneration (nAMD).
Also known as wet macular degeneration, nAMD is caused by the growth of abnormal blood vessels under the retina. Leakage from these vessels can lead to irreversible blindness if left untreated.
The team noted that the use of anti-VEGF drugs can inhibit the growth of these blood vessels, but the treatment can also cause severe intraocular inflammation. To predict which patients will experience this inflammatory response, the researchers aimed to develop an AI model that could flag patterns of intraocular inflammation in eye images.
To develop the tool, the researchers used machine learning (ML) to evaluate routine optical coherence tomography (OCT) scans taken of the vitreous (the gel-like substance inside the eye) before and during anti-VEGF treatment.
The research team used OCT scans of the eyes of 67 nAMD patients who participated in a retrospective clinical trial to test the model's ability to identify inflammatory patterns before they became clinically visible.
The analysis revealed that the ML tool accurately flagged which patients would develop inflammation 76% of the time before anti-VEGF treatment and 81% of the time after treatment.
The research team emphasized that these findings may help improve nAMD treatment in the future.
“Macular degeneration is close to home for me because my father has it, and as our population ages, more people will have nAMD. Anti-VEGF drugs can slow the progression of macular degeneration, but they also come with risks,” Dr. Anant Madabhushi, executive director of Emory AI.Health and principal investigator of the study, said in a news release. “Our study provides valuable data to help physicians make better treatment decisions, potentially reducing medication dosage or combining it with anti-inflammatory medications to prevent serious complications.”
Moreover, the success of ML models demonstrates the potential of predictive analytics to prevent adverse outcomes.
“This study validates our AI algorithm in a retrospective clinical trial and highlights the potential of precision medicine in ophthalmology,” said Sudeshna Sir Kar, PhD, first author of the study and an associate scientist at Emory AI.Health. “Next, we hope to incorporate our algorithm into prospective clinical trials to identify patients at risk of developing these adverse events in real time.”
Shania Kennedy has been covering healthcare IT and analytics related news since 2022.
