Table 1.
Characteristics of the included studies.
| Author | Year | Sex (F/M) | CPP group | Non-CPP group | Feature | Classifier | Optimal classifier |
SPE | SEN | AUC | ||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| N | Age (mean ± SD), y | N | Age (mean ± SD), y | |||||||||
| Pan et al. (16) | 2020 | F | 1153 | 7.056 ± 1.13 | 1370 | 7.476 ± 1.09 | General features, Clinical features, Laboratory features, BA,US |
XGBoost | XGBoost | 77.88 | 85.71 | 0.88 |
| Huynh et al. (17) | 2022 | F | 524 | 7.2 ± 1.8 | 90 | 7.5 ± 1.5 | General features, Clinical features, Laboratory features, BA |
kNN, GNB, LR, RF, XGBoost | RF | 89.30 | 96.60 | 0.97 |
| Pang et al. (18) | 2022 | F | 408 | 10.9 | 5119 | 10.8 | General features, Clinical features, Laboratory features |
LR,DT, Adaboost, SVM, RF,kNN,GBM,GNB,et al |
GBM | 93.22 | 34.39 | 0.79 |
| Pan et al. (19) | 2019 | F | 791 | 7.52 ± 0.99 | 966 | 7.07± 1.11 | General features, Clinical features, Laboratory features |
XGBoost,RF,SVM,DT | XGBoost | 85.39 | 77.94 | 0.89 |
| Chen et al. (20) | 2023 | F | 137 | 8.51 | 24 | 8.55 | General features, Clinical features, Laboratory features |
LR, RF, GBM, XGBoost | LR | 85.7 | 95.2 | 0.88 |
| Zou et al. (21) | 2023 | F | 185 | 7.52± 0.56 | 307 | 7.21± 0.76 | General features, Clinical features, Laboratory features US, MRI Radiomics |
RF, DT, SVM, GNB, LR | LR | 85.7 | 72.7 | 0.86 |
F, female; M, male; N, number of patients; CPP, central precocious puberty; BA, bone age; US, ultrasonography; MRI, magnetic resonance imaging; XGBoost, extreme gradient boosting; kNN, k- nearest neighbor algorithm; GNB, gaussian naive bayes; LR, logistic regression; RF, random forest; DT, decision tree; SVM, support vector machine; GBM, gradient boosting machine; SPE, Specificity; SEN, Sensitivity; AUC, area under the curve.