Table 15 Statistical parameters of the classification annotated using NICHD guidelines

From: A machine learning pipeline to classify foetal heart rate deceleration with optimal feature set

Classifier

TP

FP

Prec.

Rec.

F-S

ROC

Sen.

Spec.

Class

Random Forest

0.600

0.263

0.615

0.600

0.608

0.668

0.66

0.737

Early

0.600

0.404

0.612

0.600

0.606

0.598

0.60

0.61

Variable

0

1.0

0

0

0

0.450

  

Late

MLP

0.650

0.316

0.591

0.650

0.619

0.699

0.66

0.49

Early

0.660

0.298

0.702

0.660

0.680

0.729

0.66

0.70

Variable

0

0.067

0

0

0

0.656

  

Late

Naïve Bayes

0.450

0.193

0.621

0.450

0.522

0.646

0.45

0.80

Early

0.660

0.511

0.579

0.660

0.617

0.591

0.66

0.49

Variable

0

0.122

0

0

0

0.601

  

Late

Simple logistics

0.525

0.263

0.583

0.525

0.553

0.659

0.58

0.73

Early

0.660

0.532

0.569

0.660

0.611

0.602

0.66

0.46

Variable

0

0.033

0

0

0

0.368

  

Late

  1. TP: True Positive, FP: False Positive, Prec.: Precision, Rec.: Recall, F-S: F-Score, ROC: Receiver Operator Characteristic, Sen.: Sensitivity, Spec.: Specificity.