Table 3. Accuracy, AUROC, AUPRC, sensitivity, specificity, PPVs, NPVs, and F1 scores for the multivariable logistic regression model in the internal validation dataset, the external validation dataset and the cardiac subgroups of the internal validation and the external validation datasets.

Population	Dataset	Accuracy (95% CI)	AUROC (95% CI)	AUPRC (95% CI)	Sensitivity (95% CI)	Specificity (95% CI)	PPV (95% CI)	NPV (95% CI)	F1 score
Original analysis	Internal validation	0.9051 (0.8590–0.9512)	0.8777 (0.8239–0.9315)	0.9374 (0.9015–0.9734)	0.7632 (0.6280–0.8983)	0.9500 (0.9110–0.9890)	0.8286 (0.7037–0.9534)	0.9268 (0.8808–0.9729)	0.9383
	External validation	0.8421 (0.7716–0.9126)	0.8095 (0.7318–0.8871)	0.8337 (0.7613–0.9061)	0.8235 (0.6954–0.9517)	0.8500 (0.7718–0.9283)	0.7000 (0.5580–0.8420)	0.9189 (0.8567–0.9811)	0.8831
Cardiac subgroup analysis	Internal validation	0.8305 (0.7258–0.9352)	0.8318 (0.7275–0.9361)	0.7969 (0.6832–0.9106)	0.8000 (0.6569–0.9431)	0.8621 (0.7366–0.9876)	0.8571 (0.7275–0.9868)	0.8065 (0.6674–0.9455)	0.8333
	External validation	0.8000 (0.6678–0.9322)	0.8083 (0.6784–0.9383)	0.6621 (0.5044–0.8197)	0.8846 (0.7618–1.0000)	0.7083 (0.5265–0.8902)	0.7667 (0.6153–0.9180)	0.8500 (0.6935–1.0000)	0.7727

The cutoff probability scores for unfavorable neurological outcomes were set at 0.5 for the logistic regression model.

AUROC = area under the receiver operating characteristic curve, AUPRC = area under the precision-recall curve, PPV = positive predictive value, NPV = negative predictive value, CI = confidence interval.