Table 2.

Proportion of children with a severe disease course (severe controlled and severe persisting combined) in the test data across 50 re-samples, according to their decile of risk. Model 1 was selected as the preferred model. The last column reports results if JIA category assigned by the physician at diagnosis was to be used on its own to predict disease course.

Decile of Risk*(1) Logistic Regression(2) Random Forest(3) K-nearest Neighbor(4) Neural Network(5) JIA Category Alone
First (lowest risk)0.050.040.160.110.05
Second0.030.030.130.100.04
Third0.050.050.050.090.06
Fourth0.070.060.150.100.07
Fifth0.090.100.110.110.21
Sixth0.100.130.170.100.32
Seventh0.140.120.230.110.30
Eight0.210.220.280.220.34
Ninth0.430.450.290.410.36
Tenth (highest risk)0.910.880.510.740.37
C-index**0.85 (0.80, 0.90)0.85 (0.82, 0.88)0.67 (0.59, 0.75)0.75 (0.71, 0.79)0.71 (0.65, 0.79)
Maximum** likelihood−51 (−43, −59)−58 (−49, −66)−81 (−61, −100)−107 (−99, −116)−69 (−60, −77)
Pearson statistic**47 (34, 61)45 (37, 53)12 (3, 20)26 (18, 33)13 (7, 19)
• * Because the overall frequency of a severe disease course in the cohort was 20.5%, a method in which all deciles of risk had observed frequencies close to 20% has no predictive value, while a method in which deciles 1 to 8 had a frequency of 0% and deciles 9 and 10 had a frequency of 100% would be perfect.

• ** Numbers are the mean of 50 re-samples and (95% CI). The c-index of 0.85 for Model 1 reported in this table is the mean of 50 re-samples. When the final logistic model was refit to all the data the c-index was 0.87. JIA: juvenile idiopathic arthritis.