Comparison of a Bayesian Network with a Logistic Regression Model to Forecast IgA Nephropathy

Table 3

Dependence between variable to predict (IgAN) and predictors expressed as Kullback-Leibler divergence.

Microhematuria	0.29
Gross hematuria	0.14
Serum Ig A	0.07
Proteinuria	0.06
History of diabetes	0.05
Age	0.04
GFR	0.03
History of hypertension	0.02
Family history of hematuria	0.01
Gender	0.001