Skip to main content
. 2015 Jul;136(1):e124–e131. doi: 10.1542/peds.2015-0029

TABLE 3.

Performance of BPC Models, and Comparison With Nurses and Parents for Binary Presence/Absence of Clinically Significant Pain.

BPC
Pain Condition Metrica Machine Human
BPC BPC + Demographics BPC-Objective BPC-Objective + Demographics Nurse Parent
Ongoing AUC 0.84 ± 0.05 0.84 ± 0.06 0.91 ± 0.03 0.93 ± 0.03 0.86 ± 0.04 0.96 ± 0.02
Cohen’s κ 0.36 ± 0.10 0.34 ± 0.11 0.61 ± 0.07 0.70 ± 0.06 0.15 ± 0.06 0.50 ± 0.09
Transient AUC 0.91 ± 0.03 0.91 ± 0.03 0.94 ± 0.02 0.94 ± 0.02 0.93 ± 0.02 0.96 ± 0.01
Cohen’s κ 0.61 ± 0.07 0.61 ± 0.07 0.72 ± 0.04 0.72 ± 0.04 0.61 ± 0.07 0.72 ± 0.06

BPC, Binary Pain Classification; +Demographics, demographics included as input to model, with face vector; Objective, time since surgery used as objective ground truth for pain; Ongoing, ongoing pain condition; Transient, transient pain stimulus condition.

a

Data are expressed as mean ± SE, computed over cross 10 validation partitions. See Supplemental Information.