Cardiovascular Disease Detection using Ensemble Learning.

Area of Science:

• Cardiology
• Artificial Intelligence
• Machine Learning

Background:

• Cardiovascular disease (CVD) poses a significant global health challenge, with early detection being critical for effective management.
• Diagnosing CVD is complex due to numerous contributing health variables like blood pressure and cholesterol levels.
• Artificial intelligence (AI) offers a promising avenue for early disease identification and treatment.

Purpose of the Study:

• To propose and evaluate an ensemble-based approach utilizing machine learning (ML) and deep learning (DL) for predicting cardiovascular disease risk.
• To enhance the accuracy and efficiency of early cardiovascular disease detection through advanced computational methods.

Main Methods:

• An ensemble approach combining six classification algorithms was developed to predict the likelihood of developing cardiovascular disease.
• A publicly available dataset of cardiovascular disease cases was used for model training and validation.
• Random Forest (RF) was employed for feature extraction to identify key indicators of cardiovascular disease.

Main Results:

• The ML ensemble model demonstrated a high prediction accuracy of 88.70% in identifying individuals at risk of cardiovascular disease.
• The study successfully leveraged ensemble methods to improve the predictive performance for cardiovascular disease.

Conclusions:

• The proposed ML ensemble model shows significant potential for early and accurate prediction of cardiovascular disease.
• This approach can aid clinicians in timely intervention, potentially reducing mortality rates associated with heart disease.