Inherited retinal diseases lead to multiple visual impairments in children, often resulting in early-onset blindness. The healthcare sector recognizes machine learning as a crucial and widely employed concept globally. Its significance lies in its ability to aid doctors in expediting the diagnostic process. By harnessing the power of machine learning, healthcare professionals can enhance their diagnostic accuracy and provide timely and effective interventions for children affected by these debilitating conditions.

This project aims to develop a Machine Learning model for detecting genetic eye diseases by analyzing data obtained from a pupilometer. The model's objective is to predict the presence of an eye disease based on this data. The proposed approach involves utilizing neural networks, a powerful concept in machine learning. Two algorithms, SVM (Support Vector Machine) and ELM (Extreme Learning Machine), are being implemented. While SVM is an existing model, the new ELM algorithm shows promising results with higher accuracy in disease prediction. This enhanced accuracy will lead to faster disease detection, benefiting medical practitioners by serving as an effective decision support system in their clinics.