Outcome prediction of cardiac arrest with automatically computed gray-white matter ratio on computed tomography images

Table 2 Comparison of the performance between the manual method and the automated method in the derivation and validation sets

	AUC (95% C.I.)	Sensitivity (95% C.I.)	Specificity (95% C.I.)	PPV (95% C.I.)	NPV (95% C.I.)	Cutoff value
Derivation
Manual_b	0.71 (0.64–0.78)	0.75 (0.65–0.85)	0.64 (0.57–0.71)	0.46 (0.37–0.55)	0.86 (0.81–0.92)	1.217
Manual_s	0.72 (0.65–0.78)	0.66 (0.55–0.77)	0.71 (0.64–0.77)	0.48 (0.39–0.58)	0.84 (0.78–0.89)	1.252
Automated_b	0.75 (0.69–0.81)	0.74 (0.64–0.83)	0.65 (0.58–0.72)	0.47 (0.38–0.56)	0.86 (0.80–0.91)	1.217
Automated_s	0.79 (0.74–0.85)	0.81 (0.71–0.89)	0.70 (0.63–0.76)	0.52 (0.43–0.61)	0.90 (0.85–0.94)	1.204
Validation
Manual_b	0.67 (0.58–0.76)	0.66 (0.52–0.79)	0.54 (0.45–0.62)	0.36 (0.26–0.46)	0.80 (0.71–0.88)	1.217
Manual_s	0.68 (0.60–0.77)	0.62 (0.49–0.75)	0.65 (0.57–0.73)	0.41 (0.30–0.52)	0.81 (0.73–0.89)	1.252
Automated_b	0.71 (0.62–0.79)	0.60 (0.47–0.74)	0.59 (0.51–0.68)	0.37 (0.26–0.47)	0.79 (0.71–0.87)	1.217
Automated_s	0.78 (0.70–0.85)	0.78 (0.66–0.89)	0.67 (0.59–0.75)	0.48 (0.37–0.59)	0.89 (0.82–0.95)	1.204

Values in bold demonstrates the best performance of the corresponding metrics in the derivation and validation sets
C.I. confidence interval, PPV positive predictive value, NPV negative predictive value

ISSN: 1364-8535