Pathogenesis and epidemiology of precocious puberty. Effects of exogenous oestrogens

Precocious Puberty: Types, Pathogenesis and Updated Management

Precocious puberty (PP) means the appearance of secondary sexual characters before the age of eight years in girls and nine years in boys. Puberty is indicated in girls by the enlargement of the breasts (thelarche) in girls and in boys by the enlargement of the testes in either volume or length (testicular volume = 4 mL, testicular length = 25 mm, or both). Two types of PP are recognized - namely central PP (CPP) and peripheral PP (PPP). This paper aims to describe the clinical findings and laboratory workup of PP and to illustrate the new trends in the management of precocious sexual maturation. Gonadotropin-releasing hormone (GnRH)-independent type (PPP) refers to the development of early pubertal maturation not related to the central activation of the hypothalamic-pituitary-gonadal (HPG) axis. It is classified into genetic or acquired disorders. The most common forms of congenital or genetic causes involve McCune-Albright syndrome (MAS), familial male-limited PP, and congenital adrenal hyperplasia. The acquired causes include exogenous exposure to androgens, functioning tumors or cysts, and the pseudo-PP of profound primary hypothyroidism. On the other hand, CPP is the most common and it is a gonadotropin-dependent form. It is due to premature maturation of the HPG axis. CPP may occur as genetic alterations, such as MKRN3, DLK1, or KISS1;as a part of mutations in the epigenetic factors that regulate the HPG axis, such as Lin28b and let-7; or as a part of syndromes, central lesions such as hypothalamic hamartoma, and others. A full, detailed history and physical examination should be taken. Furthermore, several investigations should be conducted for both types of PP, including the estimation of serum gonadotropins such as luteinizing and follicle-stimulating hormones and sex steroids, in addition to a radiographic workup and thyroid function tests. Treatment depends on the type of PP: Long-acting GnRHa, either intramuscularly or implanted, is the norm of care for CPP management, while in PPP, especially in congenital adrenal hyperplasia, the goal of management is to suppress adrenal androgen secretion by glucocorticoids. In addition, anastrozole and letrozole - third-generation aromatase inhibitors - are more potent for MAS.

Explainable Dynamic Multimodal Variational Autoencoder for the Prediction of Patients with Suspected Central Precocious Puberty

Central precocious puberty (CPP) is the most common type of precocious puberty and has a significant effect on children. A gonadotropin-releasing hormone (GnRH)-stimulation test is the gold standard for confirming CPP. This test, however, is costly and unpleasant for patients. Therefore, it is critical to developing alternative methods for CPP diagnosis in order to alleviate patient suffering. This study aims to develop an artificial intelligence (AI) diagnostic system for predicting response to the GnRH-stimulation test using data from laboratory tests, electronic health records (EHRs), and pelvic ultrasonography and left-hand radiography reports. The challenges are in integrating these mul-timodal features into a comprehensive deep learning model in order to achieve an accurate diagnosis while also accounting for the missing or incomplete modalities. To begin, we developed a dynamic multimodal variational autoencoder (DMVAE) that can exploit intrinsic correlations between different modalities to im-pute features for missing modalities. Next, we combined features from all modalities to predict the outcome of a CPP diagnosis. The experimental results (AUROC 0.9086) demonstrate that our DMVAE model is superior to standard methods. Additionally, we showed that by setting appropriate operating thresholds, clinicians could diagnose about two-thirds of patients with confidence (1.0 specificity). Only about one-third of patients require confirmation of their diagnoses using GnRH (or GnRH analog)-stimulation tests. To interpret the results, we implemented an explainer Shapley additive explanation (SHAP) to analyze the local and global feature attributions.