PREDICTION OF HEPATITIS DISEASE USING K-NEAREST NEIGHBORS, NAIVE BAYES, SUPPORT VECTOR MACHINE, MULTI-LAYER AND RANDOM FOREST

Abstract

Hepatitis is a serious liver disease that can lead to severe health complications if not detected early. Accurate prediction and diagnosis of hepatitis using machine learning techniques can assist healthcare professionals in making timely decisions. This project proposes a comparative analysis of various machine learning algorithms, including K-Nearest Neighbors (KNN), Naïve Bayes, Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), and Random Forest, for predicting hepatitis disease. The dataset used in this study consists of medical attributes such as age, sex, bilirubin levels, liver enzyme values, and other clinical features. Data preprocessing techniques such as handling missing values, normalization, and feature selection are applied to improve model performance. Each algorithm is trained using 80% of the dataset and tested on the remaining 20%. The models are evaluated using performance metrics such as accuracy, precision, recall, F1-score, and confusion matrix. Experimental results show that ensemble and neural network-based models provide higher accuracy compared to traditional methods. The proposed system demonstrates the effectiveness of machine learning techniques in early hepatitis detection, improving healthcare outcomes.