Table 3.

Performance metrics between SASA scoring system and other machine learning-based models using VitalDB.

	Candidate Models
	SASA	LASSO	DNN	RF	XGB
AUROC	0.73	0.73	0.84	0.74	0.82
AUPRC	0.06	0.26	0.35	0.24	0.30

AUROC, area under receiver operating curve; AUPRC, area under precision recall curve; SASA, Surgical Apgar Score combined with the ASA-PS classification; LASSO, least absolute shrinkage and selection operator logistic regression; DNN, deep neural network; RF, random forest; XGB, extreme gradient boosting.