A Web-Based Disease Prediction System Using Machine Learning Algorithms and PCA

This work presents a web-based disease prediction system to diagnose diseases using machine learning algorithms and principal component analysis (PCA). Using web technology made the system accessible from any place, at any time. An ensemble of classifiers such as Gaussian Naive Bayes, Support Vector Machines, and Random Forest, have been applied to predict the diseases. Also, PCA is utilized to find influential symptoms for a certain type of disease. The performance of the system is evaluated before and after applying PCA to the dataset in terms of accuracy, precision, recall, and F1-score. As a result, the impact of PCA on the system performance is illustrated.