Automated Smart Prediction of Heart Disease Using Data Mining

In our hectic lives, we usually do not have enough time to check our health on a daily basis, and as a result, we disregard our health problems. The smart health prediction system presented in this research uses a new method that could aid us in taking care of ourselves. We can use the symptoms of our health problems as input to our system to help us predict the condition, and then we can contact a medical professional when necessary. The goal of this study is to use data mining techniques to forecast cardiac disease. Due to its ability to effectively forecast outcomes and store vast amounts of data, data mining is increasingly popular nowadays. Here, we examine the information and display each aspect of the dataset. We display the male-to-female patient ratio, the type of cardiovascular disease, type of chest discomfort, and maximum and minimum patient ages. Then, we employ a variety of machine learning approaches, including the Decision Tree Algorithm, Random Forest, Support Vector Machine, Logistic Regression, KNN, and others, to forecast the disease. The majority of the models offer us accuracy rates of over 85%. Additionally, it examines the matrix's recall and precision. Therefore, we can infer that it provides us with a positive outcome that will enable us to take the required precautions and lower the rate of mortality associated with a heart disease or heart attack.

Keywords: Decision-tree (DT), Data Mining, KNN, Logistic-regression, Precision, Random-forest (RF), Recall, Support-vector machine (SVM).