Predicting Early Heart Disease: A Supervised Machine Learning Approaches

Abstract

Over the past few years, worldwide, "heart-related" illnesses are now the main cause of death. The primary focus of this study is that it raises a patient's risk of cardiovascular disease (CVD) based on a variety of medical variables. Manual methods for diagnosing heart disease are inaccurate a key requirement for solving the issue is the development of a disease awareness prediction system. To identify and classify people with heart infection, machine learning processes are effective. Machine learning techniques have recently been used to help the medical field and professionals identify heart-related diseases. To diagnose cardiac disorders, by using algorithm supervised learning to build a mathematical model from a set of information that includes the necessary inputs and outputs. The supervised learning techniques including Random Forest, logistic regression, naive Bayes, K Nearest Neighbor, and decision trees are employed. This research aims to provide doctors more confidence and accuracy in their predictions by utilizing actual data from patients, both well and sick. Parameters use in cardiovascular disease focus on Sex, Sugar level, Blood pressure, Cholesterol, and Hypertension. Python language is used with the help of google colab tool for the implementation of these algorithms. Main reason of this research is that to increase the accuracy rate. This research gives accuracy 86.89% by using Random Forest Algorithms with the help of less parameter. This accuracy indicates a reasonably accurate model, it's also important to evaluate the performance in the context of the specific problem you are trying to solve.

Keywords: Machine Learning, Supervised Learning, Cardiovascular disease, Accuracy