Table 1

Performance of machine learning models

Model		AUC	Recall	Accuracy	F1 score	Precision
Base model
AdaBoost		0.83	0.80	0.73	0.65	0.55
LightGBM		0.88	0.67	0.82	0.69	0.71
XGBoost		0.88	0.93	0.76	0.70	0.56
Gradient Boosting		0.85	0.80	0.82	0.73	0.67
Extra trees		0.86	0.80	0.76	0.67	0.57
Random forest		0.90	0.80	0.82	0.73	0.67
CatBoost		0.89	0.80	0.80	0.71	0.63
Final model
PFCML-MT	Test set	0.87	0.80	0.82	0.73	0.67
PFCML-MT	Temporal validation set	0.84	0.75	0.78	0.71	0.68

AdaBoost, adaptive boosting; AUC, area under the receiver operator characteristic curve; CatBoost, categorical boosting; LightGBM, light gradient boosting machine; XGBoost, eXtreme gradient boosting.