Characteristics of the combined random forest model including default variable importance.

Hyperparameter names correspond to parameter names from the H2O package in R. Training and test evaluations as the mean squared error, root mean squared error, mean absolute error, root mean squared logarithmic error, mean of the residuals, correlation between predicted and measured postprandial plasma glucose concentrations including confidence intervals and P values, respectively, are presented. Feature importances including the corresponding confidence intervals are based on the training set, and the p values, associated with the feature importances, are calculated from a paired t-test of the absolute values of the delta values between the original and the permutation-based cross-validation predictions.
(XLSX)