Table 4.

Performance of machine learning models using different sets of features as predictors (logistic regression).

Algorithm	Accuracy, mean (SD)	Sensitivity, mean (SD)	Specificity, mean (SD)	AUCa, mean (SD)	Macro F1, mean (SD)
115 features	0.8400 (0.0100)	0.7767 (0.0321)	0.8933 (0.0416)	0.9188 (0.0048)	0.8367 (0.0153)
67 features	0.8400 (0.0200)	0.8333 (0.0945)	0.8333 (0.0643)	0.9177 (0.0066)	0.8367 (0.0252)
22 features	0.8567 (0.0208)	0.8100 (0.0173)	0.8933 (0.0503)	0.9108 (0.0045)	0.8567 (0.0208)

^aAUC: area under the curve.