Table 3. Diagnostic efficacy of the RF machine-learning model and tumor markers.

Variables	AUC	Sensitivity	Specificity	Youden index
CEA	0.740	0.629	0.783	0.412
CEA + CA19-9 + CA242	0.761	0.486	0.983	0.469
RF model	0.864	0.829	0.800	0.629

Data are presented as numerical value. CEA, carcinoembryonic antigen; CA19-9, carbohydrate antigen 19-9; CA242, carbohydrate antigen 242; RF, random forest; AUC, area under the curve.