Table 4 Confusion matrices for classifiers with the best area under the receiver-operator curve (AUROC) among nulliparous patients, with the threshold set to match a 50% true positive rate

From: Validation of sleep-based actigraphy machine learning models for prediction of preterm birth

(a) Actigraphy/Logistic Regresssion

 

PN

PP

TN

0.674

0.222

TP

0.069

0.034

(b) Case Reports/Logistic Regression

 

PN

PP

TN

0.697

0.200

TP

0.069

0.034

(c) All/Logistic Regression

 

PN

PP

TN

0.683

0.214

TP

0.069

0.034

  1. PN is predicted negative, PP is predicted positive, TN is true negative, and TP is true positive.