Researchers from the Emory Empathetic AI for Health Institute (AI Health) and the Cleveland Clinic in the US have pioneered an AI-powered method to detect inflammation caused by anti-VEGF drugs before it becomes severe.  

The research team aimed to predict which patients might develop inflammation in response to anti-VEGF treatment by combining routine optical coherence tomography (OCT) retinal scans with machine learning. Having identified patterns indicative of early inflammation allowed for timely adjustments in treatment to prevent vision loss, they said. 

Published in Heliyon, the study analysed a subset of images of 67 eyes involving patients with nAMD. Focusing on texture-based features of the vitreous, the AI model successfully identified inflammation before it was clinically visible, achieving 76% accuracy before treatment and 81% accuracy at the time of injection. 

“Our study provides valuable data for clinicians to make better treatment decisions, potentially reducing the dosage or combining these agents with anti-inflammatory drugs to prevent severe complications,” said Dr Anant Madabhushi, AI Health’s executive director and the study’s principal investigator.  

First author Dr Sudeshna Sil Kar added that they hoped to embed their algorithms into prospective clinical trials to identify patients likely to develop these adverse events in real time.