Prediction of Heart Disease Using Various Data Analysis and Machine Learning Techniques

With the ever-evolving computing technologies, the machines are learning more and more from the data they work with. A wide range of machine algorithms and data analysis techniques are implemented in real-world applications, one of them being the medical industry. Heart attack has become a global public health concern, and it is the most vital reason for mortality in the world. To avoid further increase in the fatality rate owing to cardiac attacks, it is necessary to predict the attack at an earlier stage. So far, various different approaches and techniques for predicting heart stroke have been proposed. Despite this, millions of people still die every year around the world. The main aim of this research is to determine the best technique for predicting cardiac attacks with greater accuracy. To predict cardiac stroke with the highest accuracy, the proposed research paper has implemented both machine learning and a data analysis methodology. This study uses a variety of machine learning models, including the support vector machine (SVMs), decision tree algorithm (DT), K-nearest neighbour (KNN) method and logistic regression (LR). The proposed model has compared these algorithms on the basis of accuracy and determined the optimal model for predicting heart stroke with the highest accuracy and thus to visualize data on various parameters. The results show that SVM performs better with accuracy of 89.95%.