Table 3. AUCs for logistic model performance on test data.

AUC values for prediction of shock success on N = 484 test patients (954 shocks with CPR, 884 shocks without CPR) are significantly higher for Prior ROR combined with waveform measures versus waveform measures alone. Differences may not sum due to rounding. (AMSA = Amplitude Spectrum Area; AUC = Area under the Receiver Operating Characteristic Curve; CI = Confidence Interval; CPR = Cardiopulmonary Resuscitation; MS = Median Slope.)

Logistic Model	AUC [95% CI] with CPR	AUC [95% CI] without CPR
AMSA only	0.66 [0.63–0.70]	0.71 [0.67–0.74]
AMSA + Prior ROR	0.73 [0.70–0.76]	0.76 [0.72–0.79]
(Change)	0.07 [0.04–0.10]*	0.04 [0.02–0.07]*
MS only	0.68 [0.64–0.71]	0.71 [0.68–0.75]
MS + Prior ROR	0.74 [0.71–0.77]	0.76 [0.72–0.79]
(Change)	0.06 [0.04–0.09]*	0.05 [0.03–0.07]*

^*p<0.001 for change