After gathering optical coherence tomography (OCT) images of 38 patients’ retinas with early/intermediate AMD — every three months for a minimum of 15 months — researchers used the algorithm to accurately predict the occurrence of drusen regression within the next 12 months. While the presence of lipid/protein deposits called drusen is the hallmark of early/intermediate age–related macular degeneration (AMD), their sudden regression is strongly associated with the onset of late AMD.

Currently, there are no treatments for early/intermediate AMD. Anti–VEGF treatments for late AMD can prevent disease progression, but only after some vision loss has occurred. By pinpointing the moment of transition from early/intermediate to late AMD, the researchers state that machine learning will substantially contribute to the development of new therapeutics that target slowing AMD progression.

Abstract presented at the 2017 Annual Meeting of the Association for Research in Vision and Ophthalmology (ARVO) was titled, "Personalized prognosis in early/intermediate age–related macular degeneration based on drusen regression."