An Improved Coronary Heart Disease Predictive System Using Random Forest

Abstract

Aims: This work aim is to develop an enhanced predictive system for Coronary Heart Disease (CHD).
 Study Design: Synthetic Minority Oversampling Technique and Random Forest.
 Methodology: The Framingham heart disease dataset was used, which was collected from a study in Framingham, Massachusetts, the data was cleaned, normalized, rebalanced. Classifiers such as random forest, artificial neural network, naïve bayes, logistic regression, k-nearest neighbor and support vector machine were used for classification.
 Results: Random Forest outperformed other classifiers with an accuracy of 98%, a sensitivity of 99% and a precision of 95.8%. Feature selection was employed for better classification, but no significant improvement was recorded on the performance of the classifier with feature selection. Train test split also performed better that cross validation.
 Conclusion: Random Forest is recommended for research in Coronary Heart Disease prediction domain.

Two-level boosting classifiers ensemble based on feature selection for heart disease prediction

“…Researchers have looked at various classifiers for predicting heart disease, both individual and meta. Meta classifiers (e.g., hybrid or ensemble) should be accommodated when an individual classifier is unable to offer satisfactory performance [12]. To forecast the final classification results, a meta-classifier trains multiple distinct classifiers, which makes them more resilient and appropriate for ailment prediction than single classifiers.…”

Applying Different Resampling Strategies In Random Forest Algorithm To Predict Lumpy Skin Disease

“…Wang (2021) in his research states that when the distance between classes and the sample variance of the expanded data is closer to the original data, the random forest classification is the best in the experiment designed [27]. One of the uses of Random Forest in the Health sector is for a coronary heart disease prediction system, where the use of Random Forest shows 98% accuracy, 99% sensitivity and 95.8% precision [28]. The results of the Parkinson's disease prediction study imply that the Random Forest Classifier with SMOTE can produce a model with higher accuracy than the Bagging Classifier with SMOTE or the Boosting Classifier with SMOTE when analyzing unbalanced data [29].…”