Detection of Eye Diseases in Numerous Features Using Principle Component Analysis With Stacked Ensemble Method

Abstract

The function of the eyes, which assist humans in learning and gathering information from their natural environs, is crucial to existence. The prevalence of eye disease is increasing almost anywhere in the world, which necessitates a significant reaction. Prompt eye identification can be a great help in providing additional treatment to avert blindness. The main objective of this study is to create a broad architecture for better diagnosis of eye disease in a globally recognized structure to make it easier to use machine learning (ML) algorithms with an anticipated illness diagnosis using symptoms and available eye disease datasets. This leads to the proposal of an effective model that can diagnose eye illnesses employing principle component analysis (PCA) based light gradient boosting machine (LGBM) techniques. Moreover, the proposed method concentrates on evolving better self-learning.