Currently, an active search for new approaches to building expert systems for diagnosing retinal pathologies based on artificial intelligence methods (fuzzy logic methods, neural network approaches, modern classification methods, simulation models) is underway. The effectiveness of such expert systems depends entirely on the completeness of the available space of diagnostic features. The classical calculation of the amplitude and time parameters of the components of an electroretinogram (ERG) and their relations (indices), as well as the analysis of the frequency spectrum of the signal, becomes insufficient for interpreting the data obtained in the developed expert systems.