To validate the artificial intelligence subsystem of the DDART medical device for the automated detection of lesions compatible with diabetic retinopathy in a random sample of retinal fundus photographs.
Secondary Objectives To determine the sensitivity and specificity of the artificial intelligence subsystem for the detection of diabetic retinopathy.
To estimate the overall diagnostic accuracy and the area under the receiver operating characteristic (ROC) curve (AUC).
To compare the performance of the algorithm with that of experienced ophthalmologists.
To evaluate the ability of the model to distinguish between different stages of disease severity