Deep learning based digital pathology for predicting treatment response to first-line PD-1 blockade in advanced gastric cancer

Table 3 Evaluation Metrics of ICIsNet in internal test cohort and external test cohort

	ACC	AUC	PPV	NPV	SENS	SPEC	F1 score
Internal test cohort	0.848	0.952	0.762	1.000	1.000	0.706	0.865
FAH-NCU	0.870	0.920	0.860	0.880	0.876	0.863	0.867
SAH-SYSU	0.932	0.962	0.926	0.941	0.962	0.889	0.943
ACH-GZMU	0.900	1.000	1.000	0.857	0.750	1.000	0.857

ACC: accuracy; AUC: area under the curve; PPV: positive predictive value; NPV: negative prediction value; SENS: sensitivity; SPEC: specificity

ISSN: 1479-5876