TABLE 1.

Classification performance metrics for each MAP infection-predictive model^a

Algorithm	Data set	Precision	Recall	F1 score	AUC
KNN (k = 3)	Raw	0.81 ± 0.11	0.79 ± 0.11	0.79 ± 0.11	0.86 ± 0.09
	1.5 power	0.80 ± 0.06	0.78 ± 0.05	0.77 ± 0.06	0.87 ± 0.06
	Exp	0.83 ± 0.11	0.82 ± 0.11	0.82 ± 0.11	0.86 ± 0.08
LinearSVC	Raw	0.76 ± 0.11	0.75 ± 0.10	0.75 ± 0.10	0.84 ± 0.06
	1.5 power	0.86 ± 0.09	0.84 ± 0.09	0.84 ± 0.09	0.91 ± 0.07
	Exp	0.78 ± 0.06	0.76 ± 0.07	0.75 ± 0.07	0.84 ± 0.08
Random forest	Raw	0.90 ± 0.07	0.89 ± 0.08	0.89 ± 0.08	0.93 ± 0.05
	1.5 power	0.88 ± 0.05	0.84 ± 0.08	0.84 ± 0.08	0.96 ± 0.04
	Exp	0.88 ± 0.07	0.86 ± 0.07	0.85 ± 0.08	0.94 ± 0.05
SVM	Raw	0.80 ± 0.09	0.77 ± 0.08	0.77 ± 0.08	0.87 ± 0.07
	1.5 power	0.82 ± 0.07	0.80 ± 0.08	0.79 ± 0.09	0.91 ± 0.05
	Exp	0.80 ± 0.04	0.79 ± 0.04	0.79 ± 0.05	0.86 ± 0.06

^aFor each experiment, the precision, recall, F1 score, and AUC value of the ROC curves were considered to quantify the performance. Values are means and SD for the predictive model that applied 10-fold cross-validation (training set, n = 49; testing set, n = 5) based on the labeled information for each sample.