Reproductive Medicine

Background/Objectives: Precocious puberty (PP), defined as the onset of secondary sexual characteristics before 8 years in girls and 9 years in boys, is associated with psychosocial distress, compromised adult height, and long-term metabolic risk. Early identification remains challenging, as current diagnostic approaches are largely reactive and rely on invasive or resource-intensive testing. This narrative review examines how artificial intelligence (AI) can support earlier risk prediction and detection of PP through integration of clinical, hormonal, imaging, lifestyle, and environmental data. Methods: A narrative literature review was conducted using PubMed, Scopus, Embase, Web of Science, and Google Scholar to identify relevant studies published between 2005 and 2025. Eligible studies included original research and high-quality reviews that examined AI-based approaches, such as machine learning and deep learning, in pediatric endocrinology, particularly for the prediction or diagnosis of central or peripheral precocious puberty. Studies incorporating clinical, hormonal, radiological, lifestyle, environmental, or multi-omics data relevant to AI modeling were included. Results: AI models, including XGBoost, random forest, convolutional neural networks, and regression-based approaches, have demonstrated potential utility in predicting central precocious puberty using hormonal, imaging, and growth data. Reported applications include automated bone age assessment, lifestyle and dietary risk stratification, and exploratory use of wearable-derived behavioral data. However, progress is limited by small pediatric datasets, population bias, limited interpretability, and unresolved ethical challenges related to privacy, consent, and equity. Conclusions: Artificial intelligence represents a promising decision-support approach for earlier, non-invasive, and individualized risk assessment in precocious puberty. Future progress will depend on the integration of longitudinal, multimodal data, the development of ethical models, and interdisciplinary collaboration among pediatric endocrinologists, data scientists, and public health stakeholders.

Background/Objectives: Infertility is a major public health concern, affecting one in six individuals worldwide and nearly one-quarter of couples in France. While a male, female, or combined factor can be identified in approximately 75% of cases, infertility remains unexplained in 10–25%. Genital tract infections account for roughly 15% of male infertility cases and are often asymptomatic, being detected incidentally during routine evaluation prior to assisted reproductive technology (ART). Emerging evidence suggests that the seminal microbiota may contribute to sperm quality and male reproductive health. This systematic review aims to evaluate whether specific microbial profiles are associated with alterations in semen parameters. Methods: A comprehensive literature search was conducted in PubMed and ScienceDirect, yielding 165 and 1418 records, respectively. In the end, 20 articles were included in this systematic review. Results: Men with normal semen parameters commonly exhibited a higher abundance of Lactobacillus and Bifidobacterium, whereas Prevotella was more frequently observed in individuals with impaired semen quality. Several taxa—such as Gardnerella, Corynebacterium, and Staphylococcus spp.—were detected in both normal and altered semen profiles, suggesting that their impact on sperm quality may depend on reaching a pathogenic threshold. Conclusions: Current evidence supports an association between seminal microbiota composition and sperm quality. However, the heterogeneity of available studies and the lack of standardized methodologies limit the ability to draw firm conclusions. Further well-designed studies are required to clarify causal relationships and to determine the clinical relevance of seminal microbiota assessment in male infertility.

Background/Objectives: Dynein axonemal heavy chain (DNAH) genes, including DNAH6, are implicated in male infertility, particularly multiple morphological abnormalities of the spermatozoa flagellum (MMAF). However, an underlying mechanism is unclear. Methods: This in silico study analyzed 19 previously reported DNAH6 mutations to elucidate their effects on the structural, mechanical, and microstructural aspects and axonemal assembly of flagellum and how these changes impact reproductive health, correlating with pathogenicity scores, ATP binding capacity, and protein interactions. Results: DNAH mutations were associated with CDGP (52.63%), male infertility (36.84%), and primary ovarian insufficiency (10.53%). MMAF-linked mutations exhibited higher SNAP2 scores (57.25 ± 5.68 vs. −32.58 ± 44.85, p = 0.002), reduced ATP binding affinity (−6.27 ± 4.20 vs. −8.92 ± 0.23 kcal/mol, p = 0.05), and smaller catalytic cavity size (17,646 ± 13,005 vs. 27190 ± 3485 ų, p = 0.04). These mutations showed reduced DNAH6-CLIP4 binding affinity (−303.90 ± 5.23 vs. −313.60 ± 4.28 kcal/mol, p = 0.002). Literature-based semen analysis revealed correlations between Phred scores and absent flagella (r = 0.952, p = 0.012) and inverse correlations between ATP binding capacity and absent flagella (r = −0.902, p = 0.036) or irregular width (r = −0.949, p = 0.014). A mathematical model of ATP binding kinetics predicted reduced flagellar motility in MMAF mutants due to impaired dynein function. Ultrastructural analyses indicated that high pathogenicity scores and reduced ATP binding correlate with absent inner dynein arms and radial spokes, while impaired DNAH6-CLIP4 interactions disrupt axonemal assembly. Conclusions: In silico analyses, integrated with microstructural, axonemal, and mathematical modeling data, demonstrate that DNAH6 mutations cause MMAF by impairing ATP binding, protein interactions, and axonemal assembly, leading to severe flagellar dysfunction and thereby negatively affecting reproductive health.