Table 2 Comparison of the performance of nine machine learning methods.

From: Developing a nomogram model for predicting non-obstructive azoospermia using machine learning techniques

Machine learning methods

Area under the curve

Sensitivity

Specificity

Random Forest

0.953

1.000

0.864

Gradient Boosting Decision Trees

0.974

1.000

0.915

XGBoost

0.957

0.980

0.881

LightGBM

0.966

1.000

0.898

Naive Bayes Classifier

0.963

1.000

0.915

Support Vector Machine

0.972

0.980

0.915

Logistic Classifier

0.973

1.000

0.881

Decision Trees

0.957

0.939

0.915

Neural Networks

0.967

1.000

0.864