Skip to main content

Table 3 The testing result of XGBoost classification algorithm on suicide attempts among patients with MDD

From: Can cognition help predict suicide risk in patients with major depressive disorder? A machine learning study

 

Sensitivity

Specificity

Accuracy

AUC*

PPV*

NPV*

XGBoost-1

0.600 (0.323,0.837)

0.737 (0.488,0.909)

0.677 (0.495,0.826)

0.779 (0.627,0.934)

0.643 (0.351,0.872)

0.700 (0.457,0.881)

XGBoost-2

0.600 (0.323,0.837)

0.790 (0.544,0.940)

0.706 (0.525,0.849)

0.819 (0.675,0.964)

0.692 (0.386,0.909)

0.714 (0.478,0.887)

  1. *AUC Area under the curve, PPV Positive predictive value, NPV Negative predictive value
Back to article page

BMC Psychiatry

ISSN: 1471-244X

Contact us