Table 5. Prediction model discrimination and calibration statistics.

Models	Discrimination	Calibration
	AUC (95% CI)	E:O	CITL	Slope
Sm	0.79 (0.78–0.81)	0.995	0.005	0.993
STm (dichotomous primary analysis)	0.92 (0.91–0.93)	0.825	0.210	1.197
STm (continuous sensitivity analysis)	0.92 (0.91–0.93)	0.820	0.220	1.199
Tm (dichotomous primary analysis)	0.91 (0.90–0.92)	0.824	0.209	1.213
Tm (continuous sensitivity analysis)	0.92 (0.91–0.93)	0.826	0.211	1.199

AUC, area under the curve; CITL, calibration in the large; E:O, ratio of expected (predicted) probability vs observed frequency of the outcome; Sm, symptoms-only model; STm, symptoms and tests model; Tm, tests-only model.

An AUC of 0.5 represents chance, and 1 represents perfect ability to discriminate between patients who will and patients who will not be diagnosed with cancer [47]. Perfect calibration has a calibration slope of 1, a CITL of 0, and an O:E ratio of 1 [41].