Multiple Disease Prediction System using Machine Learning Algorithm

Abstract

The advancement of machine learning techniques has significantly contributed to the development of intelligent healthcare applications that support disease prediction and clinical decision-making. This study presents a Multiple Disease Prediction System (MDPS) that predicts the likelihood of various diseases using patient health information and medical datasets. The proposed system integrates multiple machine learning and deep learning models to identify diseases such as Heart Disease, Diabetes, Kidney Disease, Liver Disease, Breast Cancer, Malaria, and Pneumonia within a unified platform. The framework involves data collection, preprocessing, feature analysis, model training, and performance evaluation using standard classification techniques. Algorithms, including Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, and Convolutional Neural Networks, are employed to develop disease-specific prediction models. The trained models are deployed via a Flask-based web application, allowing users to enter relevant medical parameters and obtain predictions efficiently. Experimental findings demonstrate that the proposed system achieves satisfactory predictive performance across multiple disease categories and can serve as a supportive tool for preliminary health assessment. By facilitating early disease identification, the system has the potential to assist healthcare professionals in making timely diagnoses and planning treatment. Future work will focus on expanding the range of diseases, incorporating larger healthcare datasets, and improving prediction accuracy through advanced machine learning methodologies.