Abstract Cardiovascular disease (CVD) is a leading cause of morbidity and mortality worldwide, accounting for a significant proportion of healthcare costs. It is a major public health concern, and early detection and prevention are critical for reducing its burden. Several risk factors for CVD have been identified, including age, sex, genetics, hypertension, diabetes, smoking, and physical inactivity. Despite the identification of several risk factors, there is still a lack of understanding of the underlying mechanisms that contribute to CVD development. This study aimed to investigate the potential predictors of CVD and identify novel biomarkers that could be used for early detection and prevention. The study explored pre-processing strategies, including Synthetic Minority Oversampling Technique (SMOTE), Z-Score Normalization, and Adaptive Synthetic Sampling (ADASYN), to address class imbalance and enhance model performance. The dataset consisted of medical images labeled with different cardiovascular diseases. By integrating the strengths of Support Vector Machines (SVM) classification and Linear Discriminant Analysis (LDA), Principal Component Analysis (PCA), and PCA with ReliefF feature retrieval methods, the study investigated various feature extraction approaches for classifying cardiovascular diseases.