Cardiovascular diseases (CVD) pose a significant public health concern globally, contributing to a substantial burden of morbidity and mortality. This cross-sectional analysis aims to identify significant health indicators associated with cardiovascular disease and develop predictive machine learning models. The study focused on understanding the prevalence and determinants of CVD risk factors to facilitate the development of effective interventions for reducing the burden of CVD. The dataset, obtained from Kaggle, included variables such as age, gender, blood pressure, cholesterol level, smoking, alcohol consumption, and physical activity. The logistic regression model showed significant associations between the included health indicators and the presence of cardiovascular disease. The positive coefficients for "systolic BP", "Diastolic BP", and "cholesterol" suggested a higher likelihood of cardiovascular disease, while the negative coefficients for "gluc", "smoke", "alco", and "active" indicated a lower likelihood of cardiovascular disease. The findings underscored the importance of these health indicators in assessing the risk of cardiovascular disease, providing valuable insights for healthcare professionals and policymakers to target specific risk factors and improve cardiovascular health outcomes.