Table 4 Model performance on the entire independent test set and complete-case independent test set.

From: An explainable machine learning-based clinical decision support system for prediction of gestational diabetes mellitus

Model

Test cases

AUC-PR

AUC-ROC

Sensitivity

Specificity

Balanced accuracy

1

All (110 cases)

0.485

0.792

0.733

0.768

0.751

1

Complete (77 cases)

0.551

0.860

0.833

0.754

0.794

2

All (110 cases)

0.208

0.659

0.6

0.6

0.6

2

Complete (77 cases)

0.256

0.690

0.583

0.6

0.592

3

All (110 cases)

0.199

0.656

0.533

0.674

0.604

3

Complete (77 cases)

0.320

0.687

0.5

0.708

0.604

  1. Model 1: feature-agnostic model. Features: family history of diabetes mellitus, weight, white cell count, fasting glucose, insulin.
  2. Model 2: clinical routine model. Features: gestational age, maternal age, family history of diabetes mellitus, weight, white cell count.
  3. Model 3: remotely usable model. Features: gestational age, maternal age, family history of diabetes mellitus, weight.
Back to article page