SVM-based model for disease prediction

Abstract— The field of disease prediction systems has gained significant attention in recent years, with the goal of accurately predicting the likelihood of a disease based on symptoms provided by the patient. The Naive Bayes Classifier has been commonly used in such systems to calculate the probability of the disease. However, with the growth of big data in the biomedical and healthcare communities, the accuracy of disease prediction can be improved through the use of more advanced techniques such as Support Vector Machines (SVM). In this research paper, we propose the use of SVM-based models for disease prediction, which can effectively analyze medical data and provide early detection and improved patient care. Our approach involves training SVM models on large datasets to predict the likelihood of various diseases such as Diabetes, Malaria, Jaundice, Dengue, and Tuberculosis. The proposed system shows promising results in accurately predicting the likelihood of disease, outperforming traditional methods such as linear regression and decision trees. The use of SVM-based models in disease prediction can greatly benefit the healthcare industry and improve patient outcomes.