TY - JOUR
T1 - A Dynamic Bayesian Network model for long-term simulation of clinical complications in type 1 diabetes
AU - Marini, Simone
AU - Trifoglio, Emanuele
AU - Barbarini, Nicola
AU - Sambo, Francesco
AU - Di Camillo, Barbara
AU - Malovini, Alberto
AU - Manfrini, Marco
AU - Cobelli, Claudio
AU - Bellazzi, Riccardo
PY - 2015/10/1
Y1 - 2015/10/1
N2 - The increasing prevalence of diabetes and its related complications is raising the need for effective methods to predict patient evolution and for stratifying cohorts in terms of risk of developing diabetes-related complications. In this paper, we present a novel approach to the simulation of a type 1 diabetes population, based on Dynamic Bayesian Networks, which combines literature knowledge with data mining of a rich longitudinal cohort of type 1 diabetes patients, the DCCT/EDIC study. In particular, in our approach we simulate the patient health state and complications through discretized variables. Two types of models are presented, one entirely learned from the data and the other partially driven by literature derived knowledge. The whole cohort is simulated for fifteen years, and the simulation error (i.e. for each variable, the percentage of patients predicted in the wrong state) is calculated every year on independent test data. For each variable, the population predicted in the wrong state is below 10% on both models over time. Furthermore, the distributions of real vs. simulated patients greatly overlap. Thus, the proposed models are viable tools to support decision making in type 1 diabetes.
AB - The increasing prevalence of diabetes and its related complications is raising the need for effective methods to predict patient evolution and for stratifying cohorts in terms of risk of developing diabetes-related complications. In this paper, we present a novel approach to the simulation of a type 1 diabetes population, based on Dynamic Bayesian Networks, which combines literature knowledge with data mining of a rich longitudinal cohort of type 1 diabetes patients, the DCCT/EDIC study. In particular, in our approach we simulate the patient health state and complications through discretized variables. Two types of models are presented, one entirely learned from the data and the other partially driven by literature derived knowledge. The whole cohort is simulated for fifteen years, and the simulation error (i.e. for each variable, the percentage of patients predicted in the wrong state) is calculated every year on independent test data. For each variable, the population predicted in the wrong state is below 10% on both models over time. Furthermore, the distributions of real vs. simulated patients greatly overlap. Thus, the proposed models are viable tools to support decision making in type 1 diabetes.
KW - CVD
KW - Dynamic Bayesian Network
KW - Nephropaty
KW - Simulation
KW - Tabu search
KW - Type 1 diabetes
UR - http://www.scopus.com/inward/record.url?scp=84949501612&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84949501612&partnerID=8YFLogxK
U2 - 10.1016/j.jbi.2015.08.021
DO - 10.1016/j.jbi.2015.08.021
M3 - Article
AN - SCOPUS:84949501612
VL - 57
SP - 369
EP - 376
JO - Journal of Biomedical Informatics
JF - Journal of Biomedical Informatics
SN - 1532-0464
ER -