![]() ![]() The detection limits of basal LH and FSH were 0.01 and 0.05 IU/L, respectively. The basal LH, follicular-stimulating hormone (FSH) and estradiol levels were measured by immuno-chemiluminescence assay on all participants in a fasting state between 8:00 am and 8:30 am. ![]() GnRHa stimulation test and hormonal measurement The study was approved by the Ethics Committee of the First Affiliated Hospital, Zhejiang University School of Medicine. Ĭonsidering the extensive application of machine learning classifiers in the medical field, we aimed to construct models based on basal pubertal hormone levels, pituitary dimensions measured by MRI, and pelvic ultrasound parameters using various machine learning classifiers to diagnose girls with ICPP. Nevertheless, the consensus on its use in the case of suspected ICPP has not yet been established. The possibility of replacing the GnRHa stimulation test with basal pubertal hormones, such as luteinizing hormone (LH) and routine imaging tests has been continuously reviewed. Magnetic resonance imaging (MRI) of the brain can be used to determine the presence of brain lesions causing premature pubertal development. Pelvic ultrasound is considered an additional tool in the diagnosis of CPP in a situation when the results of the GnRH stimulation test are opaque. Pelvic ultrasound, as rapid and non-invasive tests, is currently routine examinations utilized in female patients with precocious puberty. However, the GnRHa stimulation tests require multiple invasive blood sampling procedures which is inconvenient in paediatric patients. To date, the gonadotropin-releasing hormone analogue (GnRHa) stimulation test is considered the gold standard to distinguish between the intermediate forms of precocious puberty that are not suitable for treatment with GnRHa and CPP. Thus, it is very important to diagnosis ICPP in subjects with early symptoms of puberty. Idiopathic CPP (ICPP) may mimic other forms of precocious puberty and can lead to short stature in adults due to early epiphyseal fusion, and adverse psychosocial outcomes. About 90% of cases in girls are idiopathic without definite organic disease. CPP results from the premature activation of the hypothalamic-pituitary-gonadal (HPG) axis. Precocious puberty in girls is defined as the onset of secondary sexual characteristics before the age of 8 and can be divided into three types: central precocious puberty (CPP), peripheral precocious puberty and incomplete precocious puberty. The machine learning prediction model we developed has good efficacy for predicting response to GnRHa stimulation tests which could help in the diagnosis of CPP. ![]() Basal pubertal hormone levels (including luteinizing hormone, follicle-stimulating hormone, and estradiol), averaged ovarian volume, and several uterine parameters were predictors in the model. XGBoost had the highest diagnostic efficacy, with sensitivity of 0.81, specificity of 0.72, and F1 score of 0.80. All machine learning classifiers used achieved good performance in distinguishing CPP group and non-CPP group, with the area under the curve (AUC) ranging from 0.72 to 0.81 in validation set. The participates were divided into an idiopathic CPP group (n = 263) and a non-CPP group (n = 192). The accuracy, sensitivity, specificity, positive predictive value, negative predictive value, area under receiver operating characteristic (AUC) and F1 score of the models were measured. Four machine learning classifiers were developed to identify girls with CPP, including logistic regression, random forest, light gradient boosting (LightGBM), and eXtreme gradient boosting (XGBoost). They were randomly assigned to the training or internal validation set in an 8:2 ratio. ![]() This retrospective study included 455 girls diagnosed with precocious puberty who underwent transabdominal pelvic ultrasound, brain MRI examinations and GnRHa stimulation testing were retrospectively reviewed. The aim of this study was to construct machine learning models incorporating basal pubertal hormone levels, pituitary magnetic resonance imaging (MRI), and pelvic ultrasound parameters to predict the response of precocious girls to GnRHa stimulation test. The current diagnosis of central precocious puberty (CPP) relies on the gonadotropin-releasing hormone analogue (GnRHa) stimulation test, which requires multiple invasive blood sampling procedures. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |