Predicting wet age-related macular degeneration (AMD) using DARC (detecting apoptosing retinal cells) AI (artificial intelligence) technology

OBJECTIVES: To assess a recently described CNN (convolutional neural network) DARC (Detection of Apoptosing Retinal Cells) algorithm in predicting new Subretinal Fluid (SRF) formation in Age-related-Macular-Degeneration (AMD). METHODS: Anonymized DARC, baseline and serial OCT images (n = 427) from 29 AMD eyes of Phase 2 clinical trial (ISRCTN10751859) were assessed with CNN algorithms, enabling the location of each DARC spot on corresponding OCT slices (n = 20,629). Assessment of DARC in a rabbit model of angiogenesis was performed in parallel. RESULTS: A CNN DARC count >5 at baseline was significantly (p = 0.0156) related to development of new SRF throughout 36 months. Prediction rate of eyes using unique DARC spots overlying new SRF had positive predictive values, sensitivities and specificities >70%, with DARC count significantly (p < 0.005) related to the magnitude of SRF accumulation at all time points. DARC identified earliest stages of angiogenesis in-vivo. CONCLUSIONS: DARC was able to predict new wet-AMD activity. Using only an OCT-CNN definition of new SRF, we demonstrate that DARC can identify early endothelial neovascular activity, as confirmed by rabbit studies. Although larger validation studies are required, this shows the potential of DARC as a biomarker of wet AMD, and potentially saving vision-loss.