Predicting Coronary Heart Disease Using Data Mining and Machine Learning Solutions.

Area of Science:

• Computational biology
• Medical informatics
• Machine learning in healthcare

Background:

• Cardiovascular disease (CVD) remains a leading cause of mortality worldwide.
• Accurate prediction of CVD risk is crucial for timely intervention and improved patient outcomes.
• Existing predictive models may benefit from advanced machine learning techniques for enhanced accuracy.

Purpose of the Study:

• To develop and evaluate an ensemble machine learning model for predicting cardiovascular disease.
• To compare the performance of integrated machine learning algorithms, including Random Forest and Gradient Boosting.
• To optimize the ensemble model using Bayesian hyperparameter tuning for superior predictive power.

Main Methods:

• Development of a novel ensemble learning model combining Linear Regression, Random Forest, and Gradient Boosting algorithms.
• Application of Bayesian hyperparameter tuning to optimize model parameters.
• Evaluation of model performance using classification accuracy and true positive rate on the Framingham dataset (4240 samples).

Main Results:

• The ensemble model demonstrated high predictive performance for cardiovascular disease outcomes.
• Gradient Boosting (GB) achieved a classification accuracy of 98.3% and a true positive rate of 98.3%.
• The GB method showed superior prediction capabilities compared to other evaluated algorithms on the Framingham dataset.

Conclusions:

• Ensemble machine learning, particularly Gradient Boosting, offers a powerful strategy for accurate cardiovascular disease prediction.
• The developed model shows significant potential for clinical application in identifying patients at high risk of CVD.
• Further validation on diverse datasets is warranted to confirm the generalizability of the findings.