Forecasting of Heart Diseases in Early Stages Using Machine Learning Approaches

In the area of computer science, the terms “machine learning” as well as “data science” are no longer new buzzwords. People have begun to employ it in their apps. Machine Learning (ML) has become the most widely utilized method for web sites to classify visitors and provide relevant responses. ML is primarily an area of Artificial Intelligence(AI) that has been a crucial component of digitalization solutions that has gotten a lot of buzz in the digital world. In this work, ML is utilized to determine whether or not a person has cardiac disease. ML may be used to determine if a person has a cardiovascular illness based on particular characteristics such as chest discomfort, cholesterol levels, age, and other factors. Cardiovascular disease diagnosis can be simplified using ML classification algorithms that are based on supervised learning. To distinguish those with cardiac illness from those who do not, many ML algorithms are being used including K-Nearest Neighbor (KNN), Decision Tree classifier as well as Support Vector Classifiers. The dataset contains certain irrelevant features that are removed during the data cleaning stage, and the data is also standardized for better results. The results and analyses of the publicly available ML Heart Disease UCI dataset are being compared in this paper using different ML methods. The accuracy as well as confusion matrix are also being used to validate a good amount of promising outcomes.