Table 3.

Diagnostic performance of eight machine learning methods for pancreatic cancer.

Methods	Validation (30%)			External validation (GSE32676)
	AUC	Se	Sp	AUC	Se	Sp
Support vector machine	0.87 (0.79–0.95)	0.92	0.84	0.90 (0.73–1.00)	0.96	0.86
Random forest	0.91 (0.86–0.97)	0.91	0.86	0.94 (0.83–1.00)	0.96	0.86
Naive Bayes	0.91 (0.86–0.96)	0.93	0.84	0.92 (0.77–1.00)	0.96	0.86
Neural network	0.91 (0.86–0.97)	0.94	0.84	0.97 (0.91–1.00)	0.84	1.00
Linear discriminant analysis	0.91 (0.86–0.96)	0.93	0.84	0.95 (0.86–1.00)	1.00	0.86
Mixture discriminant analysis	0.91 (0.87–0.96)	0.91	0.84	0.98 (0.93–1.00)	1.00	0.86
Flexible discriminant analysis	0.91 (0.85–0.96)	0.92	0.84	0.86 (0.71–1.00)	0.84	0.86
Logistic regression	0.92 (0.87–0.97)	0.93	0.84	0.97 (0.90–1.00)	0.96	0.86

AUC, receiver operating characteristic area under the curve value; Se, Sensitivity; Sp, Specificity.