Skip to main content

Table 5 different feature sets fed to the classifiers as their input variables to predict stillbirth

From: Proposing a machine-learning based method to predict stillbirth before and during delivery and ranking the features: nationwide retrospective cross-sectional study

Feature Set

Included Features

FFS

All features

FSC22

The union of the features belonging to the higher-ranked clusters (CF21 and CS21) while all features are clustered into two clusters

FSC43

The union of the features belonging to the higher-ranked clusters (CF31, CF32, CS41, CS42 and CS43) while all features are clustered into four clusters for the first-step classification and three clusters for the second-step classification

FSC67

The union of the features belonging to the higher-ranked clusters (CF61, CF62, CF63, CF64, CF65, CS71, CS72, CS73, CS74, CS75 and CS76) while all features are clustered into six clusters for the first-step classification and seven clusters for the second-step classification