The Efficient Prediction of Diseases Using Machine Learning Algorithm

An essential aspect of medical research and treatment involves the proactive prediction of diseases, estimating the likelihood of an individual developing a specific medical condition in the future. Through the input of symptoms, users in this proposed project are provided with information regarding the potential diseases the user may have. The prediction of the disease using the symptoms has been done by using the dataset which consists of various diseases that can be prevented by using the symptoms. The ultimate goal of disease prediction is to provide people the information about the disease the user had by using the symptoms entered by the user as the input. In addition to the disease prediction, users can also get efficient prediction results for their inputs, where the main aim of this proposed project is to give the user an efficient result by comparing the accuracy of the various algorithms namely Support vector machine, Naïve Bayes, and Random Forest. The outcome will be determined by comparing which algorithm yields the highest accuracy after the accuracy of each method has been compared. The algorithm employed in this research proposal is a reliable method for predicting illness. The proposed algorithm provides better classification accuracy. The Support Vector Machine (SVM) algorithm yields 84.95, Naive Bayes (NB) provides 84.55, and the Random Forest (RF) algorithm produces 84.95 Ac-curacy.