Decision trees' viability and efficiency in forecasting coronary heart disease

Cardiovascular disease is one of the most prevalent disease categories and a major global health concern. For therapy to be effective and survival chances to increase, early identification is essential. A decision tree in this instance is a trustworthy Classification technique for calculating cardiovascular disease hazard as well as gathering data for the clinical decision-making process. However, it may be difficult to find a more accurate simulation of cardiovascular illness due to scalability issues. Therefore, the performance and scalability of decision trees for the prediction of cardiovascular illness are investigated in this study. The study assessed a decision tree's ability to predict cardiovascular disease. The model complexity, cross-validation score, ratings of training result from augmented training samples, and error matrix were castoff to measure the enactment. The proceeding claims that model of decision tree had an accuracy with 89.8% in predicting the occurrence of cardiovascular disease. As a result, decision trees are useful for predicting and identifying cardiovascular disease incidents among patients early on.