Related Experiment Video
Updated: Jul 2, 2025
09:09
In Silico Clinical Trials for Cardiovascular Disease
Published on: May 27, 2022
1.7K
Empirical exploration of whale optimisation algorithm for heart disease prediction
Stephen Akatore Atimbire1, Justice Kwame Appati2, Ebenezer Owusu1
1Department of Computer Science, University of Ghana, Accra, Ghana.
Scientific Reports
|February 24, 2024
Summary
This study enhances heart disease risk prediction using the whale optimization algorithm (WOA) for feature selection. The approach improves model performance across multiple datasets, offering better early risk assessment for heart conditions.
Area of Science:
- Cardiology
- Biomedical Informatics
- Machine Learning
Background:
- Heart disease is a leading global cause of mortality.
- Accurate predictive models are crucial for early risk assessment.
- Existing models often lack comprehensive evaluation and multi-dataset validation.
Purpose of the Study:
- To develop an improved heart disease risk prediction approach.
- To leverage the whale optimization algorithm (WOA) for effective feature selection.
- To implement a comprehensive evaluation framework across diverse datasets.
Main Methods:
- Utilized five distinct heart disease datasets, including a combined set.
- Applied the whale optimization algorithm (WOA) for optimal feature selection.
- Integrated selected features into ten different classification models.
Main Results:
- Achieved significant improvements in accuracy, precision, recall, F1 score, and AUC.
- Demonstrated superior performance compared to state-of-the-art methods on the same datasets.
- Validated the effectiveness of WOA in identifying optimal features across multiple heart disease datasets.
Conclusions:
- The proposed WOA-based feature selection and comprehensive evaluation framework enhance heart disease risk prediction.
- The methodology shows robust adaptability and improved predictive performance.
- This approach offers a more reliable tool for early identification of heart disease risk.
