Table 6.

ROC with Boruta package analysis for data from 18-month-old samples.

Methods	AUC	Sensitivity	Specificity	PPV	NPV	p-Value
Sparse Logistic Regression	0.99 (0.96–1)	0.98 (0.89–1)	0.97 (0.86–1)	0.98	0.97	3.639 × 10−15
Random Forest	0.97 (0.94–1)	0.98 (0.89–1)	0.87 (0.72–0.96)	0.91	0.97	4.317 × 10−14
Gaussian Process	0.94 (0.89–0.99)	0.9 (0.78–0.97)	0.89 (0.75–0.97)	0.92	0.87	9.162 × 10−13
Support Vector Machine	0.94 (0.87–1)	0.98 (0.89–1)	0.89 (0.75–0.97)	0.92	0.97	9.733 × 10−13