A highly efficient and scalable prediction approach based on random forest that is capable of handling enormous data sets

Cardiovascular illnesses include elevated blood pressure, stroke, heart failure, and heart disease. They are the leading causes of premature mortality all over the globe, especially in economically disadvantaged and countries with middle incomes. The diagnosis of these conditions at an earlier stage might lead to a drop in the number of untimely deaths. Health care is an incredibly important and promising application of data mining. The medical field has benefited substantially from data mining. Heart Disease is a challenging but manageable chronic disease that people around the world are diligently striving to manage. There are a total of 70,000 samples in the dataset, and its qualities may be broken down into 12 categories. Data was then examined in a jupyter notebook (anaconda-3) environment. Random forest, a machine learning approach, is used to do both classification and analysis of the data sets. Percentages representing accuracy, sensitivity, and specificity are used to illustrate the dataset's findings. Employing the random forest technique, we were able to enhance our accuracy at foreseeing cardiac issues by 86.9%. Furthermore, the sensitivity was 80.6%, while the specificity was 82.7 percent. After conducting an analysis of random forest's operational features, we found that it has a medical accuracy of 85 % when it comes to forecasting the outcome of cardiovascular illness. It has been shown that the random forest is the most efficient algorithm for identifying cardiac diseases consequently, which is included in the suggested technique.