A novel machine learning-based proposal for early prediction of endometriosis disease

Pyrethroids, which are widely utilized in agriculture, household products, and public health for their potent insecticidal properties, elicit significant concerns regarding their potential endocrine-disrupting effects. However, previous studies have yielded inconsistent data, largely due to the absence of a standardized screening system. To address this limitation, the present study introduces an Integrated Approach to Testing and Assessment (IATA) to evaluate the endocrine-disrupting potential of pyrethroids, aligned with the Adverse Outcome Pathway (AOP) framework. Employing this IATA-based methodology, the endocrine-disrupting effects of five pyrethroids, allethrin, phenothrin, deltamethrin, cypermethrin, and lambda-cyhalothrin-were investigated, with a focus on hormone levels of 17(3-estradiol (E2) and testosterone (T). Enzyme-linked immunosorbent assays (ELISA) and receptor transactivation assays were utilized to assess the direct receptor interactions and alternative disruption mechanisms. The results demonstrated that lambda-cyhalothrin and phenothrin significantly elevated E2 levels, while all tested compounds substantially reduced T levels. Notably, transactivation assays indicatedBackground: Endometriosis is one of the causes of female infertility, with some studies estimating its prevalence at around 10 % of reproductive-age women worldwide and between 30 and 50 % in symptomatic women. However, its diagnosis is complex and often delayed, highlighting the need for more accessible and accurate diagnostic methods. The difficulty lies in its diverse etiology and the variability of symptoms among those affected. Methods: This study proposes a predictive model based on supervised machine learning for the early identification of endometriosis, providing support for decision-making by healthcare professionals. For this purpose, an anonymised dataset of 5,143 female patients diagnosed with endometriosis at the private fertility clinic Inebir was used. The model integrates clinical records and genetic analysis through supervised machine learning algorithms, focusing on clinical variables and pathogenic and potentially pathogenic genetic variants. Results: The developed predictive model achieves high accuracy in identifying the presence of endometriosis, highlighting the importance of combining clinical and genetic data in diagnosis. The integration of this data into the DELFOS platform, a clinical decision support system, demonstrates the utility of machine learning in improving the diagnosis of endometriosis. Conclusions: The findings underscore the potential of clinical and genetic factors in the early diagnosis of endometriosis using supervised machine learning algorithms. This study contributes to the classification of clinical variables that influence endometriosis, offering a valuable tool for clinicians in making therapeutic and management decisions for their female patients.