Computational Techniques for Cardiovascular Diseases Prediction: Systematic Review

Cardiovascular disease (CVD) occurs when the heart is unable to circulate the appropriate amount of blood to other parts of the body in order to perform normal functions. The purpose of this research is to conduct a systematic review of computational methods for predicting the risk of cardiovascular disease. A systematic search strategies was adopted, as reported by the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) checklist. The articles were chosen from Google Scholar, PubMed, and Web of Science and evaluated purely computational techniques for CVD risk prediction. The inclusion criteria were satisfied by 46 studies: 9 on fuzzy logic or hybrids, 5 on genetic algorithms or hybrids, 21 on machine learning, ensembles, or hybrids, 3 on data mining, 2 on intelligent systems, and 7 on neural networks and their hybridized forms. Research results indicated that better CVD prediction in humans will be assured by the use of computational techniques with higher performance accuracy.