Bayesian network modeling: a case study of an epidemiologic system analysis of cardiovascular risk

Abstract

[eng] An extensive, in-depth study of cardiovascular risk factors (CVRF) seems to be of crucialimportance in the research of cardiovascular disease (CVD) in order to prevent (or reduce)the chance of developing or dying from CVD. The main focus of data analysis is on theuse of models able to discover and understand the relationships between different CVRF.In this paper a report on applying Bayesian network (BN) modeling to discover the rela-tionships among thirteen relevant epidemiological features of heart age domain in orderto analyze cardiovascular lost years (CVLY), cardiovascular risk score (CVRS), and metabolic syn-drome (MetS) is presented. Furthermore, the induced BN was used to make inference takinginto account three reasoning patterns: causal reasoning, evidential reasoning, and intercausalreasoning. Application of BN tools has led to discovery of several direct and indirect relation-ships between different CVRF. The BN analysis showed several interesting results, amongthem: CVLY was highly influenced by smoking being the group of men the one with high-est risk in CVLY; MetS was highly influence by physical activity (PA) being again the groupof men the one with highest risk in MetS, and smoking did not show any influence. BNsproduce an intuitive, transparent, graphical representation of the relationships betweendifferent CVRF. The ability of BNs to predict new scenarios when hypothetical informationis introduced makes BN modeling an Artificial Intelligence (AI) tool of special interest inepidemiological studies. As CVD is multifactorial the use of BNs seems to be an adequatemodeling tool.