Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

The flowchart of the study.

Definition of abbreviations: AdaBoost, adaptive boosting; AUC, the area under the receiver operating characteristic curve; kNN, k-nearest neighbors; LIME, local interpretable model-agnostic explanations; XGBoost, extreme gradient boosting.

More »

Fig 1 Expand

Table 1.

Basic characteristics of girls who underwent the GnRHa stimulation test in discovery and testing data set.

More »

Table 1 Expand

Fig 2.

ROC curves of different algorithms in the training dataset.

Predictive model included baseline characteristics and blood sampling 30 mins post-stimulation in the training dataset. Definition of abbreviations: AUC, an area under the receiver operating characteristic curve (ROC); kNN, k-nearest neighbors; AdaBoost, adaptive boosting; XGBoost, extreme gradient boosting.

More »

Fig 2 Expand

Table 2.

Model performance of different algorithms in the training dataset (n = 432).

More »

Table 2 Expand

Fig 3.

Feature importance ranking.

This figure lists the relative importance of baseline characteristics and 30-minute post-stimulated gonadotropin levels in the developed machine learning-based model for the CPP diagnosis in girls. Definition of abbreviations: BA-CA, the difference between the bone age and the chronological age; BMI, body mass index; E2, basal estradiol; FSH, follicle-stimulating hormone; LH, luteinizing hormone.

More »

Fig 3 Expand

Fig 4.

Comparison of the performance of the three-variable proposed model in a different dataset.

Definition of abbreviations: NPV, negative predictive value; PPV, positive predictive value.

More »

Fig 4 Expand

Fig 5.

AUC values of predictive models in a different time point in the training dataset.

Model performance of the 14-variable proposed model (A) and three-variable model (B) at 0 min, 30th min, 60th min, and 120th min post-stimulation in the training dataset. Definition of abbreviation: AUC, an area under the receiver operating characteristic curve.

More »

Fig 5 Expand

Fig 6.

Performance metrics of and three-variable predictive model in the internal and external dataset.

Model performance of the three-variable model was evaluated at 0 min, 30th min, 60th min, and 120th min post-stimulation in the internal and external dataset. Definition of abbreviations: NPV, negative predictive value; PPV, positive predictive value.

More »

Fig 6 Expand

Fig 7.

LIME analysis in different populations.

LIME analysis for Vietnamese girls (A, B) and Taiwanese girls (C, D) according to positive and negative responses. Definition of abbreviations: BA-CA, the difference between the bone age and the chronological age; Basal_LH, luteinizing hormone level at baseline; CPP, central precocious puberty; LH30, luteinizing hormone level 30 min after stimulation.

More »

Fig 7 Expand