Table 3.

Training model fit metrics for the machine learning approaches

Model	AUC	Threshold	Accuracy	Kappa	Sensitivity	Specificity
LM	1	0.093	1	1	1	1
RF	1	0.093	1	1	1	1
GBM	1	0.093	1	1	1	1
DT	1	0.093	1	1	1	1
NNET	0.996	0.093	0.991	0.998	0.981	1
XGBOOST	1	0.091	1	1	1	1

AUC, area under the receiver operating characteristic curve; Threshold, optimal probability threshold for model predictions; Accuracy, overall accuracy of model predictions; Kappa, Cohen's Kappa statistic measuring prediction agreement; Sensitivity, model sensitivity in predicting presence; Specificity, model specificity in predicting absence; RF, random forest model; XGBOOST, extreme gradient boosting model; GBM, gradient boosting machine model; LM, logistic regression model; DT, decision tree model; NNET, neural network model