Table 3.

Performance of different algorithms in models 1 and 2.

	F1 Score	Accuracy	Sensitivity (Recall)	Specificity	AUC-PR	Precision (PPV)	NPV	Brier score
Model 1
LR	0.66	0.67	0.63	0.71	0.73	0.68	0.66	0.21
Decision Tree	0.60	0.60	0.60	0.59	0.70	0.60	0.60	0.39
Extra Trees	0.66	0.68	0.65	0.70	0.73	0.68	0.67	0.20
Gradient Boosting	0.68	0.70	0.65	0.75	0.76	0.72	0.68	0.19
KNN	0.62	0.64	0.59	0.67	0.69	0.64	0.62	0.24
Naive Bayes	0.60	0.67	0.49	0.85	0.73	0.76	0.62	0.22
Random Forest	0.67	0.68	0.65	0.70	0.73	0.68	0.67	0.20
SVM	0.67	0.70	0.62	0.77	0.75	0.73	0.67	0.20
Model 2
LR	0.72	0.73	0.71	0.73	0.79	0.72	0.72	0.18
Decision Tree	0.64	0.65	0.65	0.66	0.73	0.64	0.64	0.35
Extra Trees	0.74	0.75	0.74	0.76	0.80	0.75	0.74	0.17
Gradient Boosting	0.75	0.75	0.74	0.78	0.83	0.77	0.74	0.16
KNN	0.68	0.70	0.65	0.76	0.76	0.72	0.68	0.20
Naive Bayes	0.71	0.71	0.72	0.70	0.74	0.70	0.71	0.25
Random Forest	0.74	0.74	0.75	0.74	0.81	0.73	0.74	0.17
SVM	0.74	0.75	0.73	0.76	0.81	0.75	0.74	0.17

LR Logistic Regression, KNN K-Nearest Neighbors, AUC area under the receiver operating characteristic curve, AUC-PR area under the precision-recall curve, PPV positive predictive value, NPV negative predictive value, SVM Support Vector Machine.

Model 1 utilizes vital signs for modeling, Model 2 incorporates vital signs, demographics, medical history, and chief complaints. Note: Sensitivity and Recall refer to the same metric and are used interchangeably in the table. Similarly, Precision is equivalent to PPV.