Paper Title
THE SMART HEALTH DISEASE PREDICTION SYSTEM

Abstract
Abstract - To live a healthy and happy life, health care is essential. People today suffer from a wide variety of diseases as a result of their lifestyle choices and the environment. Because of this, it is crucial to make an early diagnosis of sickness. The systems that were already in place either had a single disease prediction system or used a single algorithm. The current system’s greatest accuracy ranges from 52% to 88%. Some of the methods used in various prediction systems include linear regression, decision trees, naive Bayes, KNN, CNN, random forest trees, etc. In our investigation, multiple diseases can be predicted concurrently. As a result, the user won't need to cycle through numerous models in order to predict the diseases. Both the time and the cost will be reduced. The creation of classifier systems using ML algorithms seeks to greatly contribute to the resolution of health issues by assisting doctors in forecasting and identifying illnesses at an early stage. 4920 patient records with diagnoses for 41 diseases were chosen as a sample for the general health study. 1025 patient data were obtained in order for analyzing the prediction of heart disease. In this paper, a disease prediction system using machine learning techniques such as the SVM, random forest, naive Bayes and gradient boosting is demonstrated. Keywords - General Health Prediction, Heart Prediction, Gradient Boosting, SVM, Random Forest Classifier, Naive Bayes, Machine Learning.