Risk assessment for hypertension and hypertension complications incidences using a Bayesian network.

The Bayesian network is a useful method for modeling healthcare issues since it can graphically represent causal relationships among variables and provide probabilistic information. We apply this method to conduct hypertension and hypertension complications incidence analyses using the National Health Insurance Corporation (NHIC) sample cohort database from 2002 to 2010, which contains more than a million prescribers' information, including socio-demographic information, health check-up records, and other information related to medical treatments and medical expenses in South Korea. We select significant factors that affect hypertension and its complications incidence using Cox regression, and perform Bayesian network analysis with respect to those factors. We investigate the causality for hypertension and its complications incidence, and then calculate the conditional probabilities about nodes of interest. In addition, we evaluate performance to predict the incidence of hypertension and its complications. We conclude that the Bayesian network method has several notable advantages. Firstly, it can demonstrate which factors affect hypertension and its complications incidence and how they are related to each other. Secondly, it can calculate conditional probability; thus, we can perform qualitative and quantitative analyses at the same time. [ABSTRACT FROM PUBLISHER]