Skip to main content

Table 7 Model parameter settings

From: Risk prediction of hyperuricemia based on particle swarm fusion machine learning solely dependent on routine blood tests

Model

Parameters

Logistic

max_iter = 1000,C = 100

SVM

kernel = ‘rbf’, gamma = 0.1, C = 1.0,probability = True

RF

n_estimators = 106, max_depth = 12, max_features = 0.569, min_samples_leaf = 3,min_samples_split = 8

XGBoost

max_depth = 8,learning_rate = 0.2,n_estimators = 171, subsample = 0.9,colsample_bytree = 0.8

DNN

batch_size = 32,epochs = 100,learning_rate = 0.001,optimizer = adam,loss = CrossEntropyLoss