Table 3.

Performance on hold-out test data for algorithm predictions up to 3 hours in advance.

Performance metric	3 hours before onset	2 hours before onset	1 hour before onset	0 hours before onset
AUROCa	0.84	0.82	0.82	0.85
AUPRCb	0.68	0.67	0.65	0.67
Accuracy (95% CI)c	0.81 (0.73, 0.89)	0.79 (0.71, 0.87)	0.79 (0.71, 0.87)	0.79 (0.71, 0.87)
Sensitivity	0.74	0.63	0.63	0.63
Specificity	0.83	0.83	0.83	0.83
Positive predictive value	0.50	0.46	0.46	0.46
Proportion of predicted sepsis	0.29	0.27	0.27	0.27

^aAUROC: area under the receiver operating characteristic curve.

^bAUPRC: area under the precision-recall curve.

^cOperating points for the algorithm were chosen during training and internal validation to keep sensitivity at approximately 0.80.