Table 4.

Averaged MLA performance in comparison with the performance of the MMSE classifier at 48 months.

Performance Metrics	Averaged MLA	MMSE Classifier at 48 Months ⧧
AUROC (95% CI)	0.965 (0.927–0.990)	0.713 (0.601–0.813)
Sensitivity (95% CI)	0.800 (0.734–0.866)	0.655 (0.518–0.791)
Specificity (95% CI)	0.955 (0.915–0.993)	0.727 (0.584–0.870)
PPV (95% CI)	0.957 (0.920–0.993)	0.750 (0.617–0.883)
NPV (95% CI)	0.792 (0.724–0.861)	0.627 (0.483–0.772)
Accuracy (95% CI)	0.869 (0.827–0.910)	0.687 (0.688–0.786)

^⧧ Note: The MMSE classifier uses a threshold score value of 27. AUROC = area under the receiver operator characteristic curve; CI = confidence interval; PPV = positive predictive value; NPV = negative predictive value.