Table 2 Optimal cut-off point, specificity, sensitivity, and area under the curve of the UPAPS and random forest algorithm.

From: Proposing a short version of the Unesp-Botucatu pig acute pain scale using a novel application of machine learning technique

Parameters

UPAPS#

Random forest&

P-value

Optimal cut-off point

02.50 (01.50–03.50)

62.08 (30.94–77.05)

 

Specificity (%)

88.00 (78.00–96.00)

90.00 (78.00–98.00)

 

Sensitivity (%)

90.00 (80.00–98.00)

88.00 (78.00–98.00)

 

AUC (%)

90.58 (84.32–96.84)

91.38 (85.58–97.18)

0.8545

  1. UPAPS is Unesp-Botucatu Pig Composite Acute Pain Scale; # is total sum; & is probability of needing analgesia based on the algorithm; AUC is area under the curve; comparison between two AUCs was conducted with the DeLong test; the optimal cut-off point was determined by the Youden index (Specificity + Sensitivity – 1).
Back to article page