Temporal and Amplitude Characteristics of ERG Signals in Retinal Degenerative Disorders

Electroretinogram (ERG) signals are critical for diagnosing various retinal diseases. This study aims to identify abnormalities in ERG signals by analyzing the amplitudes and time implicits of a-wave and b-wave components. The ERG signals were obtained from the OculusGraphy: Pediatric and Adults Electroretinograms Database, which includes maximum response, flicker response, photopic response, and scotopic response. A logistic regression model is employed to classify the signals. We extracted features from ERG signals, including the amplitudes of a-wave and b-wave, and the time implicits of these waves. These features were then used as input to the logistic regression classifier. The model's performance was evaluated using accuracy, sensitivity, and specificity metrics. Our results indicate that the logistic regression classifier effectively identifies abnormalities in ERG signals, demonstrating its potential as a diagnostic tool for retinal conditions. Further research may involve expanding the dataset and incorporating additional features to improve classification accuracy.