Abstract
This is a protocol for a Cochrane Review (diagnostic). The objectives are as follows: To determine the diagnostic accuracy of artificial intelligence (AI) as a triaging tool for exudative age‐related macular degeneration (eAMD). SECONDARY OBJECTIVES: To compare the performance of different AI algorithms with respect to eAMD diagnosis. To explore potential causes of heterogeneity in diagnostic performance according to the following: index test methodology (core AI method); sources of input to train algorithms (number of training and testing cases); imaging modality (optical coherence tomography, fundus photos, optical coherence tomography angiography, etc, or any combination); characteristics of test set (difficulty of test set, proportion of positive versus negative cases); population characteristics (symptomatic versus asymptomatic, age, etc.); study design (cross‐sectional versus longitudinal studies).