Machine Learning Techniques for Predication of Heart Diseases

Heart disease, or cardiovascular illness, encompasses a wide range of disorders affecting the cardiovascular system. One of the trickiest things to do in medicine is to make predictions about cardiovascular disease. Nowadays, heart disease claims the life of almost one person every minute. Heart disease has several causes, but one of the most pressing issues is the lack of sensitive, precise methods for early identification, which makes proper management of the condition impossible. Automating the prediction process is necessary to prevent the hazards connected with cardiac disease diagnosis and to inform the patient at an early stage due to the intricacy of the condition. Data mining is extensively utilized in healthcare to forecast the occurrence of cardiovascular illness by analyzing massive and intricate medical records. To forecast cardiac problems, researchers conduct in-depth analyses of massive amounts of medical data using a wide range of data mining and machine learning algorithms. Here, we provide several heart disease characteristics and build a model using supervised learning methods like random forest and support vector machine (SVM). The Kaggle repository contains the cardiac condition dataset that is used in this research. Predicting patients' risk of heart disease is the main objective of this investigation. Confusion matrices were used for proposed system evaluation .The findings demonstrate that Random Forest achieves the highest level of accuracy, reaching 98.54 percent.