Breaking new ground in cardiovascular heart disease Diagnosis K-RFC: An integrated learning approach with K-means clustering and Random Forest classifier

Abstract

The ability to accurately anticipate heart failure risks in a timely manner is essential because heart failure has been identified as one of the leading causes of death. In this paper, we propose a novel method for identifying cardiovascular heart disease by utilizing a K-means clustering and Random Forest classifier combination. Based on their clinical and demographic traits, patients were classified into either healthy or diseased groups using the Random Forest classifier after being clustered using the K-means method. The performance of the proposed hybrid approach was evaluated using a dataset of patient records and compared with traditional diagnostic methods, namely support vector machine (SVM), logistic regression, and Naive Bayes classifiers. The outcomes indicated that the proposed hybrid method attained a high accuracy in diagnosing heart disease, with an overall accuracy of 96.8%. Additionally, the method showed a good performance in classifying patients at high risk of heart disease: the sensitivity reached 96.3% and the specificity reached 97.2%. In conclusion, the proposed method of combining K-means clustering and a Random Forest classifier is a promising approach for the accurate and efficient identification of heart disease. Further studies are needed to validate the proposed method in larger and more diverse patient populations.

Keywords

• classifier
• k-means clustering
• heart disease
• random forest
• diagnosing