Overview on How Data Mining Tools May Support Cardiovascular Disease Prediction

Terms as knowledge discovery or KnowledgeDiscovery from Databases (KDD), Data Mining (DM), ArtificialIntelligence (AI), Machine Learning (ML), Artificial Neuralnetworks (ANN), decision tables and trees, gain from day to day,an increasing significance in medical data analysis. They permitthe identification, evaluation, and quantification of some lessvisible, intuitively unpredictable, by using generally large sets ofdata. Cardiology represents an extremely vast and importantdomain, having multiple and complex social and humanimplications. These are enough reasons to promote theresearches in this area, becoming shortly not just national orEuropean priorities, but also world-level ones. The profoundand multiple interwoven relationships among the cardiovascularrisk factors and cardiovascular diseases – but still far to becompletely discovered or understood – represent a niche forapplying IT&C modern and multidisciplinary tools in order tosolve the existing knowledge gaps.This paper’s aim is to present, by emphasizing their absoluteor relative pros and cons, several opportunities of applying DMtools in cardiology, more precisely in endothelial dysfunctiondiagnostic and quantification the relationships between theseand so-called “classical” cardiovascular risk factors.