Related Experiment Video
Updated: Jul 9, 2025
09:47
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
Published on: December 15, 2023
1.1K
Multi-Objective artificial bee colony optimized hybrid deep belief network and XGBoost algorithm for heart disease
Kanak Kalita1, Narayanan Ganesh2, Sambandam Jayalakshmi3
1Department of Mechanical Engineering, Vel Tech Rangarajan Dr. Sagunthala R & D Institute of Science and Technology, Chennai, India.
Frontiers in Digital Health
|November 30, 2023
Summary
A new Hybrid Deep Belief Network and XGBoost (HDBN-XG) algorithm significantly improves coronary heart disease prediction. This advanced method analyzes key physiological data, achieving 99% accuracy to aid early risk assessment.
Area of Science:
- Cardiovascular Medicine
- Artificial Intelligence in Healthcare
- Biomedical Data Analysis
Background:
- Coronary heart disease (CHD) is a leading global health concern, demanding enhanced predictive capabilities.
- Accurate risk stratification is crucial for timely intervention and patient management.
- Existing predictive models require optimization for improved diagnostic precision.
Purpose of the Study:
- To introduce and evaluate a novel algorithm, the Multi-Objective Artificial Bee Colony Optimized Hybrid Deep Belief Network and XGBoost (HDBN-XG), for superior CHD prediction.
- To leverage key physiological data, including Electrocardiogram (ECG) and blood volume measurements, for risk assessment.
- To enhance the accuracy and reliability of predictive analytics in cardiovascular disease detection.
Main Methods:
- Data preprocessing involved quality assessment and z-score normalization.
- Feature extraction was performed using the Computational Rough Set method.
- Feature subset construction utilized the Multi-Objective Artificial Bee Colony optimization approach.
- A hybrid deep belief network and XGBoost model (HDBN-XG) was developed and implemented.
Main Results:
- The HDBN-XG algorithm demonstrated exceptional predictive performance.
- Achieved accuracy of 99%, precision of 95%, specificity of 98%, sensitivity of 97%, and F1-measure of 96%.
- Outperformed conventional classification methods in predicting coronary heart disease.
Conclusions:
- The HDBN-XG algorithm offers a highly accurate and robust approach to CHD risk prediction.
- This data-driven methodology provides valuable insights for healthcare professionals and researchers.
- The study contributes a significant advancement in predictive analytics for mitigating the global burden of heart disease.
