Table 2 Prediction results for each parameter.

From: Partner relationships, hopelessness, and health status strongly predict maternal well-being: an approach using light gradient boosting machine

Model

Accuracy

Precision

Recall

F1-score

ROC-AUC

3 variables, threshold 7, LightGBM

0.88

0.92

0.95

0.93

0.83

3 variables, threshold 7, random forest

0.87

0.92

0.93

0.93

0.81

3 variables, threshold 7, XGBoost

0.87

0.92

0.94

0.93

0.81

2 variables, threshold 7, LightGBM

0.86

0.93

0.92

0.92

0.79

4 variables, threshold 7, LightGBM

0.89

0.92

0.96

0.94

0.84

3 variables, threshold 6, LightGBM

0.92

0.95

0.97

0.96

0.87

3 variables, threshold 8, LightGBM

0.78

0.85

0.86

0.85

0.79

  1. For all patterns, the machine learning models were trained and validated using 2020 data and tested on 2021 data.
  2. ROC-AUC area under the receiver operating characteristic curve, LightGBM Light Gradient Boosting Machine, XGBoost Extreme Gradient Boosting.
Back to article page