Skip to main content

Table 1 Hyperparameters for models

From: Discussion on machine learning technology to predict tacrolimus blood concentration in patients with nephrotic syndrome and membranous nephropathy in real-world settings

Model

Core Hyperparameters

LR

Penalty; class_weight; C

RF

min_samples_split; n_estimators; max_features; min_samples_leaf; max_depth

Adaboost

n_estimators; learning_rate

GBDT

n_estimators; learning_rate; subsample; loss; max_depth; min_samples_split; min_samples_leaf; max_features

XGBoost

learning_rate; max_depth; subsample; n_estimators; scale_pos_weight; min_child_weight; gamma

LGBM

learning_rate; max_depth; subsample; n_estimators; min_child_weight; min_child_samples; num_levels; colsample_bytree; boost_type

  1. LR logistic regression; RF random forest; GBDT gradient boost decision tree; LGBM LightGBM
Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us