Algorithm 1: Model training and hyperparameter optimization for the standard AI models.

Require: Sets of model hyperparameter values to evaluate      ▹ Cartesian product

Ensure: Average model performance across all folds

1:for each external fold iteration do                ▹ External 5-fold CV 2:    Hold-out the samples of this fold (i.e., the test set) 3:    Use the rest of samples as calibration set 4:    for each hyperparameter set do 5:        for each internal fold iteration in the calibration set do    ▹ Internal 5-fold CV 6:           Hold-out the samples of this fold (i.e., the validation set) 7:           Fit the model on the rest (i.e., the training set) 8:           Use the model to predict the held-out samples 9:           Calculate and store an accuracy metric for this fold 10:        end for 11:        Calculate the average performance across all folds 12:    end for 13:    Determine the optimal hyperparameter set 14:    Fit the final model using the calibration set with the optimal hyperparameters 15:    Use the model to predict the held-out samples 16:    Calculate and store accuracy metrics for this fold 17:end for 18:Calculate the average performance across all folds