Modeling the role of genetic factors in characterizing extra-intestinal manifestations in Crohn's disease patients: does this improve outcome predictions?

ABSTRACT Objective: To evaluate to what extent an inefficient statistical model affects the study of genetic factors in extra-intestinal manifestations of Crohn's disease (CD) and how clinical predictions can be improved using more adequate techniques. Materials: Extra-intestinal manifestations were studied in 152 CD patients. Three sets of variables were considered: (1) disease characteristics – presenta­tion, behavior, location; (2) generic risk factors – age, gender, smoke and familiarity; and (3) genetic polymorph­isms of the NOD2, CD14, TNF, IL12B, and IL1RN genes, whose involvement in CD is known or suspected. Methods: Six statistical classifiers and data mining models were applied: (1) logistic regression as a bench­mark; (2) generalized additive model; (3) projection pursuit regression; (4) linear dis­criminant analysis, (5) quadratic discriminant analysis; (6) artificial neural networks one-layer feed forward. Models were selected using the Akaike Information criterion and their accuracy was compared with several indexes. Results: Extra-intestinal manifestations occurred in 75 patients. The model with clinical variables only selected familiarity, gender, presentation, and behavior as signif­icantly associated with extra-intestinal manifestations, whereas when the genetic factors were also included familiarity was no longer significant, being replaced by the NOD2, TNF, and IL12B single nucleotide polymorph­isms. The projection pursuit regression performed best in predicting individual outcomes (Kappa statistics 0.078 [SE 0.09] without and 0.108 [SE 0.075] with genetic informa­tion). One-layer artificial neural networks did not show any particular improvement in terms of model accuracy over non-linear techniques. Conclusions: The correct identification of factors assoc­iated with extra-intestinal symptoms in CD, in particular the genetic ones, is highly dependent on the model chosen for the analysis. By using the most sophist­icated statistical models, the accuracy of prediction can be strengthened by 10–64%, compared with linear regression.