Cardiovascular Risk Estimation in Colombia Using Artificial Intelligence Techniques

Introduction: Tere is no information on the potential of machine learning (ML)–based techniques to improve cardiovascularrisk estimation in the Colombian population. Tis article presents innovative models using fve artifcial intelligence techniques:neural networks, decision trees, support vector machines, random forests, and Gaussian Bayesian networks.Methods: Te research is based on a cohort of 847 patients free of cardiovascular disease at baseline and followed for car-diovascular disease events over 10 years at the Central Military Hospital in Bogot´a, Colombia. To enhance the robustness andreduce the risk of overftting, model evaluation was conducted using a 5-fold cross-validation on the entire dataset. Discriminatoryability was evaluated with the area under a ROC curve (AUC-ROC) for each ML-based model and the Framingham model.Results: Experimental results showed that the neural network technique had the best discriminative ability to predict car-diovascular events, with an AUC-ROC of 0.69 (CI 95% 0.622–0.759) for unbalanced data and 0.67 (CI 95% 0.601–0.754) forbalanced data. Other ML techniques also showed good discriminatory ability with AUC-ROC values between 0.56 and 0.65,superior to that observed for the Framingham model (0.53; CI 95% 0.468–0.607).Conclusion: Our study supports the fexible ML approaches to cardiovascular risk prediction as a way forward for cardiovascularrisk assessment in Colombia. Our data even suggest that risk prediction using these techniques could be even more discriminativethan widely used risk-stimulation models such as Framingham, adapted to the Colombian population. However, new prospectivestudies need to validate our data before general implementation.