Classification Techniques for Cardio-Vascular Diseases Using Supervised Machine Learning.

Area of Science:

• Cardiology
• Machine Learning
• Data Science

Background:

• Cardiovascular diseases cause 12 million deaths globally, representing half of all deaths in developed nations.
• Early prognosis of cardiovascular diseases is crucial for timely lifestyle interventions in high-risk individuals.

Purpose of the Study:

• To develop and evaluate various classification techniques for predicting cardiovascular disease risk.
• To identify the most effective models for forecasting a patient's 10-year risk of coronary heart disease (CHD).

Main Methods:

• Utilized a dataset of 4270 patients with 14 attributes from the UCI data repository.
• Employed the SMOTE technique to address class imbalance and cross-validation for performance estimation.
• Evaluated classifiers using precision, recall, F1-score, accuracy, and Area Under Curve (AUC).

Main Results:

• Multiple classification algorithms were tested for their predictive accuracy.
• The SMOTE technique was applied to handle imbalanced data, improving model robustness.
• Performance metrics including precision, recall, F1-score, accuracy, and AUC were used for comprehensive evaluation.

Conclusions:

• Random Forest and Decision Tree classifiers achieved the highest scores in predicting 10-year CHD risk.
• These models show significant potential for early identification of individuals at high risk for cardiovascular events.