Table 3.

Model performance comparisons. Shown is the model performance comparisons for the machine learning approaches for accuracy, AUC, sensitivity and specificity. AUC 5 area under the ROC curve; LR 5 logistic regression; MARS 5 multivariate adaptive regression splines; CART 5 classification and regression trees; RF 5 random forests.

Phenotype	Classifiers	Accuracy (%)	AUC	Sensitivity (%)	Specificity (%)
High eosinophils	LR	85	0.84	53	94
	MARS	85	0.89	46	93
	CART	67	0.48	30	74
	RF	49	0.40	46	49
High neutrophils	LR	97	0.76	60	98
	MARS	93	0.77	20	98
	CART	83	0.51	20	88
	RF	66	0.47	40	68
Bronchodilators	LR	76	0.71	23	85
	MARS	88	0.85	23	100
	CART	75	0.69	53	81
	RF	61	0.65	54	64
Hyper‐responders	LR	85	0.85	53	94
	MARS	90	0.88	73	94
	CART	79	0.68	53	86
	RF	70	0.77	73	70