Artificial intelligence-based strategies to identify patient populations and advance analysis in age-related macular degeneration clinical trials

Abstract

• Machine learning models predict risk for adverse events and likelihood of dropout. • Machine learning models predict disease progression risk and response to treatment. • Predictive models can be of great use in all stages of clinical trials. • Training data sets have to be diverse to maximize generalizability. • It is key to ensure patient safety and ethical use of the models.