Analysis of Diabetes and Mortality Using Bayesian Networks

Abstract

【Purpose of research】 The purpose of this study was to estimate the direct impact of diabetes itself on mortality, considering the relevance of comorbidities.

【Materials and methods】 To estimate the relationship between diseases in the National Health Insurance receipt data, we used Bayesian network structural learning.

【Results】 In the absence of concomitant metabolic disorders, the results of the analysis showed that diabetes alone had a minor impact on the incidence of mortality.

【Discussion and Conclusion】 This suggests that comprehensive disease management, including comorbidities, is important to reduce the risk of death from diabetes.