Development of a disease diagnostic model to predict the occurrence of central precocious puberty of female

Abstract Objective To develop a clinical model for predicting the occurrence of Central Precocious Puberty based on the breast development outcomes in chinese girls. Methods We established a retrospective cohort of girls with early breast development aged 6–9 years who visited the outpatient clinic of Beijing Children's Hospital from January 2017 to October 2022. Based on their breast development outcomes, the patients were divided into a pubertal development(PD) group and a premature thelarche (PT) group. Anthropometry, clinical, laboratory, and imaging variables ascertained were screened using Least Absolute Shrinkage and Selection Operator (LASSO) and logistic regression to construct a disease diagnostic model. Accuracy of the model was measured by the area under the receiver operating characteristic curve (AUC). Results The development cohort included 1001 girls aged 6–9 years. The mean (SD) age of patients was 7.86 (0.54) years, 36.4% of patients were finally diagnosed with PD, the other 63.6% were diagnosed with PT. From 14 potential predictors, 4 variables (bone age (BA)/chronological age (CA), basal luteinizing hormone (LH) level, uterine diameter and ovarian volume) were independent predictive factors. Body mass index (BMI) were considered to have some clinical significance. So the 5 variables included in the disease diagnostic model. BA/CA (OR, 2.04; 95% CI, 0.80–4.56; P < 0.001), basal LH level (OR, 8.08; 95% CI, 3.63–11.03; P < 0.001), uterine diameter (OR, 0.59; 95% CI, 0.34–1.22; P = .0006), ovarian volume (OR, 0.41; 95% CI, 0.03–1.09; P = 0.07), BMI (OR, 0.06; 95% CI, -0.06-0.15; P = 0.27), The mean AUC in the development cohort was 0.97 (95% CI, 0.88–1.05) and the AUC in the validation cohort was 0.94 (95% CI, 0.79–1.08). Conclusions : In this study, a disease diagnostic model was developed that may help predict a girl’s risk of diagnosing central precocious puberty.