Cardiovascular diseases (CVDs) represent a global health challenge, being the leading cause of mortality worldwide in 2023. This study constructs predictive models to estimate an individual's risk of developing CVD. The study population comprises users of the Centro de Salud Familiar Portezuelo (CESFAM) through the 2023 chronic and preventive program. Four predictive models were employed: Decision Tree, Neural Network, Support Vector Machine (SVM), and Naive Bayes. The SVM algorithm demonstrated superior performance, achieving over 85% in the evaluated metrics. High-importance attributes were identified, categorized as modifiable behavioral and metabolic factors, with an optimal threshold value of 0.45 to distinguish between patients likely and unlikely to develop CVD. These findings enable the development of a preventive plan to reduce the CVD rate in the study population. In conclusion, the predictive model proves to be an effective complementary tool for clinical decision-making.