Table 1 Hyperparameters of the models.

From: Development of risk models for early detection and prediction of chronic kidney disease in clinical settings

Model

Risk model in women

Risk model in men

Random Forest

variable, n_estimator = 500, criterion = gini, max_depth = 49, max_features = 8, min_samples_leaf = 15, min_samples_split = 15

variable, n_estimator = 500, criterion = gini, max_depth = 79, max_features = 8, min_samples_leaf = 10, min_samples_split = 10

Neural Network

Activation function = sigmoid, layers = 2, neurons at each layer= (5,3), linear.output = FALSE, threshold = 0.1, learning rate = 30,000

Activation function = sigmoid, hidden layers = 2, neurons at each layer= (7,3), linear.output = FALSE, threshold = 0.1, learning rate = 35,000