Abstract:
Globally, the leading cause of mortality among both men and women is coronary heart disease. This disease is widely recognized as the primary killer worldwide, and its early detection poses a significant challenge. Given the current state of affairs, it is crucial to promptly identify heart disease in its initial stages to ensure successful patient treatment. Despite numerous attempts by various researchers to develop hybrid and ensemble models for early detection, the desired outcomes have not been achieved. Consequently, the machine learning and algorithmic research community has directed its focus towards improving these methodologies. In this particular study, six supervised machine learning classifiers, namely Random_Forest, extreme gradient boost, Logistic of Regression, Decision_Tree, KNN, and N-Bayes, were employed. The UCI repository dataset was utilized as the sample data, comprising attributes and corresponding values. Data preprocessing techniques were employed to eliminate any missing values. An ensemble model incorporating three algorithms, namely DT (decision-tree), RF (random-forest), and XGB, was constructed. Remarkably, the ensemble model achieved an impressive accuracy rate of 95.33% for predicting coronary heart disease.
Page(s):
149-159
DOI:
DOI not available
Published:
Journal: VFAST Transactions on Software Engineering, Volume: 11, Issue: 2, Year: 2023
Keywords:
Logistic regression
,
Heart failure
,
decision tree
,
KNN
,
Machine Learning classifiers
,
Heart disease
,
Naive
,
Machine Learning model
,
XGB
,
Ensemble model