Enhanced Cardiovascular Disease Dataset with Data Augmentation

This dataset comprises 2 million synthetic samples generated using the Variational Autoencoder-Generative Adversarial Network (VAE-GAN) technique. The dataset is designed to facilitate cardiovascular disease prediction through various demographic, physical, and health-related attributes. It contains essential physiological and behavioral indicators that contribute to cardiovascular health.

Dataset Description The dataset consists of the following features:

• Age (int, days): The age of the individual.

• Height (int, cm): The height of the individual in centimeters.

• Weight (float, kg): The weight of the individual in kilograms.

• Body Mass Index (BMI) (float): Calculated as , providing an indicator of body fat.

• Gender (categorical code): Encoded as 1 for female and 2 for male.

• Systolic Blood Pressure (ap_hi) (int): The maximum arterial pressure during heartbeats.

• Diastolic Blood Pressure (ap_lo) (int): The minimum arterial pressure between heartbeats.

• Cholesterol (categorical): 1 for normal, 2 for above normal, and 3 for well above normal levels.

• Glucose (categorical): 1 for normal, 2 for above normal, and 3 for well above normal levels.

• Smoking (binary): 1 if the individual smokes, 0 otherwise.

• Alcohol Intake (binary): 1 if the individual consumes alcohol, 0 otherwise.

• Physical Activity (binary): 1 if the individual engages in regular physical activity, 0 otherwise.

Target Variable

• Cardiovascular Disease (cardio) (binary): The presence (1) or absence (0) of cardiovascular disease.

This dataset provides a comprehensive set of features that can be used for machine learning models in cardiovascular disease prediction, enabling research and analysis on health-related risk factors and prevention strategies.