Table 2.

A comparison of the prediction accuracy using dynLoDA and dynCI schemes

		dynCI	dynCI	dynCI	dynCI
	dynLoDA	99% HPDCI	95% HPDCI	90% HPDCI	50% HPDCI
Cutoff	0.83	0.83	0.83	0.83	0.83
Sensitivity (classified data)	0.93	0.95	0.95	0.94	0.93
Sensitivity	0.93	0.86	0.89	0.89	0.93
Specificity (classified data)	0.92	0.95	0.94	0.93	0.91
Specificity	0.92	0.91	0.91	0.91	0.90
PCC (classified data)	0.92	0.95	0.94	0.93	0.91
PCC	0.92	0.90	0.90	0.90	0.90
AUC	0.97	0.98	0.98	0.97	0.97
PPV	0.56	0.69	0.63	0.61	0.55
NPV	0.99	0.99	0.99	0.99	0.99
Proportion unclassified	0.00	0.05	0.04	0.03	0.01
Mean lead time (days)	675	565	595	614	661
Mean prediction time (days)	857	972	942	918	872

Note. The sensitivities and specificities highlighted in bold are calculated without considering the unclassified patients.

AUC, area under curve; HPDCI, highest posterior density credible interval; NPV, negative predictive value; PCC, probability of correct classification; PPV, positive predictive value.