Diagnosis of Chronic Diseases using Machine Learning

Authors:

Soham Krishna Vishvambhar, Abhishek Sandeep Jadhav

Department of Computer Science and Design MET’s Institute of Technology (Polytechnic) B.Tech, Nashik, India

Project Guide: Prof. S. S. Shaikh

Abstract— This research presents a machine learning-based framework for the diagnosis of chronic diseases such as diabetes, Parkinson’s disease, and heart disease using a unified prediction platform. Traditional diagnosis methods are often time-consuming, expensive, and inaccessible in rural regions. The proposed system integrates supervised machine learning algorithms including Support Vector Machine (SVM), Logistic Regression, and Random Forest to improve prediction accuracy and assist in early disease detection. The system utilizes healthcare datasets obtained from the UCI Machine Learning Repository and Kaggle. Data preprocessing techniques such as normalization, missing value handling, and feature scaling were applied before model training. A user-friendly Streamlit-based interface was developed to allow users to input medical parameters and obtain instant prediction results. Experimental evaluation demonstrates that SVM achieved reliable prediction accuracy with low error rates and fast response generation. The proposed solution highlights the role of artificial intelligence in healthcare by offering a cost-effective, scalable, and accessible disease prediction system.

Keywords— Machine Learning, Chronic Disease Prediction, Support Vector Machine, Healthcare Analytics, Streamlit, Disease Diagnosis, Artificial Intelligence