Cite this Article

Kavali Durga Prasad, Nidamanuri Hemanth Gopal, Malli Deepak, Kaligotla Veera Venkata Jitin, 2025. "Disease Prediction Using Machine Learning: Comparative Analysis of SVM, Naive Bayes, and Decision Tree Models with Gemini API Integration", International Journal of Emerging Information Technology (IJEIT) 1(1): 37-56.

Keywords

Disease Prediction, Machine Learning, Gemini API Integration, Decision Tree Models.

Abstract

This project explores the use of machine learning algorithms to pre- dict diseases based on user-input symptoms, employing three popular models: Support Vector Machine (SVM), Naive Bayes, and Decision Tree Classifier. The models are trained on this dataset, and their performance is evaluated using metrics such as accuracy, precision, recall, and F1 score. A user interface function allows individuals to input their symptoms, and the trained models predict the most likely disease with a confidence score. This comparative analysis highlights the strengths and weaknesses of each algorithm in the context of dis- ease prediction.

Introduction

The accurate prediction of diseases based on symptoms is a critical chal- lenge in the field of healthcare, as it can enable timely interventions and im- prove patient outcomes. Traditional diagnostic processes often rely heavily on medical expertise and patient history, which can be time-consuming and sometimes prone to human error. With the rapid advancements in machine learning, there is an increasing interest in utilizing data-driven approaches to enhance the accuracy and efficiency of disease diagnosis. Machine learn- ing algorithms have shown great promise in various healthcare applications, including disease prediction, patient risk assessment, and personalized treat- ment recommendations. These algorithms can analyze large datasets, iden- tify patterns, and make predictions based on the relationships between input features and target labels.