Skip to content
DraconiticResearch
Search Sources API
226,742 studies31 sourcesUpdated 34 min ago
Peer-reviewedCC BY 4.0Frontiers in Endocrinology

Interpretable machine learning for the non-invasive differentiation of central precocious puberty from premature thelarche in girls: a diagnostic modeling study to reduce reliance on the gonadotropin-releasing hormone stimulation test

1 more authors
6 affiliations
  1. 1Gansu Provincial Cancer Hospital
  2. 2Gansu University of Political Science and Law
  3. 3Lanzhou Institute of Technology
  4. 4Affiliated Hospital of Gansu University of Chinese Medicine
  5. 5Gansu Province Maternity and Child Health Hospital
  6. 6Gansu Provincial Hospital of Traditional Chinese Medicine

Abstract

Background: The gonadotropin-releasing hormone (GnRH) stimulation test remains the reference standard for confirming central precocious puberty (CPP), but is invasive and costly. We developed and validated an interpretable machine-learning model differentiating CPP from premature thelarche (PT) using only pre-stimulation information.

Methods: From 15,385 consecutive outpatients (2020–2026) at a tertiary hospital in northwest China, we analyzed 130 girls with early breast development, a final diagnosis of CPP (n=51) or PT (n=79), and basal luteinizing hormone (LH) and follicle-stimulating hormone (FSH) measurements. Seventeen candidate pre-stimulation predictors were reduced by LASSO regression. Six algorithms were compared by repeated stratified 5-fold cross-validation, with feature selection, imputation, and standardization refitted inside each training fold (fully nested validation). The final model was evaluated by out-of-fold AUC, calibration, decision-curve analysis, SHAP, and a pre-specified two-threshold triage.

Results: The most frequently selected predictors were age, basal FSH, and the basal LH/FSH ratio. Penalized logistic regression achieved a nested AUC of 0.813 (pooled out-of-fold 0.805, 95% CI 0.729–0.876), indistinguishable from non-linear comparators. Age alone achieved 0.818; adding hormonal variables raised the AUC to 0.855 and, at matched 90% sensitivity, specificity from 0.569 to 0.627. Calibration was moderate (slope 0.600). Under the triage rule, 38.5% of girls fell below the rule-out threshold (negative predictive value 0.900; 5 of 50 with CPP) and 21.5% exceeded the rule-in threshold (positive predictive value 0.750); an estimated 60.0% could potentially have deferred the stimulation test—a retrospective estimate, not a demonstrated reduction. Discrimination was attenuated at ages 6–8.99 years (AUC 0.707) and stable in a hardened reference-standard subset (n=101; AUC 0.787).

Conclusions: A parsimonious, hand-computable three-variable model using only pre-stimulation data stratifies girls with early breast development and could potentially defer the GnRH stimulation test in an estimated three-fifths, at the cost of initially assigning 5 girls with CPP to structured surveillance. External multicenter prospective validation with local recalibration is required before clinical use.

Related

  1. Triptorelin-stimulated gonadotropin concentrations for precocious puberty
    Eunjung Koh, Chan Jong Kim
    Annals of Pediatric Endocrinology & MetabolismPeer-reviewedCC BY-NC 4.0Full textObstetrics, gynaecology & paediatricsPMC
  2. Long-term clinical outcomes in females with precocious puberty treated with gonadotropin-releasing hormone analogues.
    Nahla Khawaja, Khalid Karaki, Mohammad K Ruba'i +8
    Frontiers in endocrinologyPeer-reviewedCC BYFull textObstetrics, gynaecology & paediatricsEurope PMCCrossref
  3. Estimating individualized gonadotropin starting doses in women with PCOS: a target-driven machine learning model for GnRH-antagonist stimulation
    Wenjia Meng, Ye Pan, Moxuan Zhang +7
    BMC Pregnancy and ChildbirthPeer-reviewedCC BY 4.0Full textObstetrics, gynaecology & paediatricsPMC
  4. Real-world implementation of AI-assisted starting gonadotropin dosing in routine ovarian stimulation: an exposure-defined, propensity score-matched observational cohort study
    Huiyu Xu, Congcong Ma, Guoshuang Feng +7
    Frontiers in EndocrinologyPeer-reviewedCC BY 4.0Endocrinology & metabolismCrossref
  5. The Diagnostic Value of Pituitary MRI Radiomics Combined with Clinical Features for Central Precocious Puberty in Girls
    Yan Li, Wan Chen, Fangying Liu +6
    Current Medical ImagingPeer-reviewedCC BY 4.0Full textObstetrics, gynaecology & paediatricsPMC
BibTeX
@article{da2026interpretable,
  title = {{Interpretable machine learning for the non-invasive differentiation of central precocious puberty from premature thelarche in girls: a diagnostic modeling study to reduce reliance on the gonadotropin-releasing hormone stimulation test}},
  author = {Zhenqiang Da and Jiaxin Chai and Yanan Liu and Yaxiong Gao and Ying Zhu and Jiayue Li and Lei Huang and Yang Gao and Dandan Lu and Tingting Li and Weikai Wang and Xingwen Xie and Nan Nan},
  journal = {Frontiers in Endocrinology},
  year = {2026},
  month = nov,
  doi = {10.3389/fendo.2026.2008437},
  url = {https://www.frontiersin.org/articles/10.3389/fendo.2026.2008437/full},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Interpretable machine learning for the non-invasive differentiation of central precocious puberty from premature thelarche in girls: a diagnostic modeling study to reduce reliance on the gonadotropin-releasing hormone stimulation test
AU  - Zhenqiang Da
AU  - Jiaxin Chai
AU  - Yanan Liu
AU  - Yaxiong Gao
AU  - Ying Zhu
AU  - Jiayue Li
AU  - Lei Huang
AU  - Yang Gao
AU  - Dandan Lu
AU  - Tingting Li
AU  - Weikai Wang
AU  - Xingwen Xie
AU  - Nan Nan
PY  - 2026
DA  - 2026/11/16
JO  - Frontiers in Endocrinology
DO  - 10.3389/fendo.2026.2008437
UR  - https://www.frontiersin.org/articles/10.3389/fendo.2026.2008437/full
AB  - Background: The gonadotropin-releasing hormone (GnRH) stimulation test remains the reference standard for confirming central precocious puberty (CPP), but is invasive and costly. We developed and validated an interpretable machine-learning model differentiating CPP from premature thelarche (PT) using only pre-stimulation information.  Methods: From 15,385 consecutive outpatients (2020–2026) at a tertiary hospital in northwest China, we analyzed 130 girls with early breast development, a final diagnosis of CPP (n=51) or PT (n=79), and basal luteinizing hormone (LH) and follicle-stimulating hormone (FSH) measurements. Seventeen candidate pre-stimulation predictors were reduced by LASSO regression. Six algorithms were compared by repeated stratified 5-fold cross-validation, with feature selection, imputation, and standardization refitted inside each training fold (fully nested validation). The final model was evaluated by out-of-fold AUC, calibration, decision-curve analysis, SHAP, and a pre-specified two-threshold triage.  Results: The most frequently selected predictors were age, basal FSH, and the basal LH/FSH ratio. Penalized logistic regression achieved a nested AUC of 0.813 (pooled out-of-fold 0.805, 95% CI 0.729–0.876), indistinguishable from non-linear comparators. Age alone achieved 0.818; adding hormonal variables raised the AUC to 0.855 and, at matched 90% sensitivity, specificity from 0.569 to 0.627. Calibration was moderate (slope 0.600). Under the triage rule, 38.5% of girls fell below the rule-out threshold (negative predictive value 0.900; 5 of 50 with CPP) and 21.5% exceeded the rule-in threshold (positive predictive value 0.750); an estimated 60.0% could potentially have deferred the stimulation test—a retrospective estimate, not a demonstrated reduction. Discrimination was attenuated at ages 6–8.99 years (AUC 0.707) and stable in a hardened reference-standard subset (n=101; AUC 0.787).  Conclusions: A parsimonious, hand-computable three-variable model using only pre-stimulation data stratifies girls with early breast development and could potentially defer the GnRH stimulation test in an estimated three-fifths, at the cost of initially assigning 5 girls with CPP to structured surveillance. External multicenter prospective validation with local recalibration is required before clinical use.
SN  - 1664-2392
ER  -