Slanzi D, Silvestri C, Poli, I, Mayer G. In: Villani, M., Cagnoni, S., Serra, R. (eds) Artificial Life and Evolutionary Computation. WIVACE 2023. Communications in Computer and Information Science, vol 1977. Springer, Cham. March 2024.
.
Abstract
Diabetic kidney disease is a serious complication of diabetes and one of the leading causes of chronic and end-stage kidney disease worldwide. The clinical course and response to therapy is complex and heterogeneous both between and over time within individuals. Therefore it is extremely important to derive even more in-depth information on what characterizes its pathophysiology and pattern of disease progression. Statistical models can help in this task by understanding the interconnections among variables clinically considered to characterize the disease. In this work we propose to use Bayesian networks, a class of probabilistic graphical models, able to identify robust relationships among a set of variables. Furthermore, Bayesian networks are able to include expert knowledge in the modeling phase to reduce the uncertainty on the phenomenon under study. We provide some evidence that the synergy between data and expert prior information is a great source of valuable help in gaining new knowledge about Diabetic Kidney Disease.
