Table 3.

Prediction performance using true positive rate and true negative rate for the six problems.

Problem	SVMa			RFb			ANNc			DTd			GPe
	TPRf	TNRg	TPR		TNR	TPR		TNR	TPR		TNR	TPR		TNR
Mortality	0.78	0.78	0.79		0.77	0.79		0.78	0.60		0.79	0.75		0.76
Disability	0.78	0.72	0.78		0.71	0.75		0.75	0.78		0.69	0.71		0.67
Fracture	0.75	0.74	0.77		0.72	0.77		0.72	0.79		0.66	0.70		0.73
Urgent hospitalization	0.61	0.73	0.65		0.68	0.66		0.68	0.64		0.68	0.66		0.62
Preventable hospitalization	0.74	0.73	0.73		0.72	0.73		0.73	0.76		0.66	0.73		0.64
ED admissionh,i	0.63	0.73	0.63		0.72	0.63		0.74	0.62		0.73	0.73		0.63

^aSVM: support vector machine.

^bRF: random forest.

^cANN: artificial neural network.

^dDT: decision tree.

^eGP: genetic programming.

^fTPR: true positive rate.

^gTNR: true negative rate.

^hED: emergency department.

ⁱwith a red code.