Table 5.

The detailed diagnosis values of models on three datasets

Dataset	Model	Accuracy (95% CI)	Sensitivity	Specificity	PPV	NPV
Training	Clinical	0.63 (0.58–0.68)	0.31	0.84	0.56	0.65
	Semantic	0.79 (0.74–0.83)	0.79	0.79	0.71	0.85
	Volume	0.66 (0.61–0.71)	0.61	0.69	0.56	0.73
	FS	0.90 (0.86–0.93)	0.91	0.89	0.84	0.94
	Radiomics	0.82 (0.78–0.86)	0.79	0.85	0.77	0.86
	RV	0.83 (0.79–0.87)	0.79	0.86	0.78	0.86
	CSRV	0.83 (0.78–0.87)	0.80	0.85	0.77	0.87
	FSV	0.89 (0.85–0.92)	0.89	0.89	0.84	0.93
	FSRV	0.91 (0.88–0.94)	0.90	0.92	0.88	0.93
	CSFSRV	0.91 (0.87–0.94)	0.89	0.92	0.88	0.93
Testing	Clinical	0.63 (0.54–0.71)	0.23	0.90	0.59	0.64
	Semantic	0.78 (0.71–0.85)	0.68	0.85	0.75	0.80
	Volume	0.69 (0.60–0.76)	0.61	0.73	0.60	0.74
	FS	0.92 (0.87–0.96)	0.95	0.91	0.87	0.96
	Radiomics	0.79 (0.71–0.85)	0.70	0.85	0.75	0.81
	RV	0.80 (0.73–0.87)	0.74	0.85	0.76	0.83
	CSRV	0.83 (0.75–0.88)	0.77	0.86	0.79	0.85
	FSV	0.92 (0.87–0.96)	0.95	0.91	0.87	0.96
	FSRV	0.94 (0.88–0.97)	0.86	0.99	0.98	0.91
	CSFSRV	0.92 (0.87–0.96)	0.84	0.98	0.96	0.90
Validation	Clinical	0.70 (0.62–0.77)	0.18	0.91	0.47	0.73
	Semantic	0.79 (0.72–0.85)	0.68	0.84	0.64	0.86
	Volume	0.79 (0.72–0.85)	0.66	0.85	0.64	0.86
	FS	0.90 (0.84–0.94)	0.95	0.88	0.76	0.98
	Radiomics	0.85 (0.78–0.90)	0.61	0.94	0.82	0.85
	RV	0.87 (0.81–0.92)	0.68	0.95	0.86	0.88
	CSRV	0.87 (0.81–0.92)	0.73	0.93	0.82	0.89
	FSV	0.91 (0.85–0.95)	0.95	0.89	0.78	0.98
	FSRV	0.93 (0.87–0.96)	0.93	0.92	0.84	0.97
	CSFSRV	0.91 (0.86–0.95)	0.89	0.92	0.83	0.95

FS, frozen section; RV, radiomics combining with volume; CSRV, radiomics combining with clinical, semantic, and volume; FSV, frozen section combining with volume; FSRV, frozen section combining with radiomics and volume; CSFSRV, radiomics combining with clinical, semantic, volume, and frozen section; PPV, positive predictive values; NPV, negative predictive values; CI, confidence interval