Determining predictors of decreased ovarian reserve after bariatric surgery using machine learning methods

Devoted to analysing the effect of bariatric surgery on the ovarian reserve in obese women using machine learning methods. The study covers data from 149 female patients who underwent surgical intervention in order to identify the relationship between weight loss and changes in reproductive function. The work applied random forest and extreme gradient bousting algorithms to identify key factors affecting anti-müllerian hormone (AMH) levels and menstrual cycle disruption (MCI) 12 months after bariatric surgery. The revealed predictive ability of the models (AUC 0.79–0.80) highlights the importance of applying machine learning in analysing the relationships between metabolic changes and reproductive health. This work opens new perspectives for further research in reproductive medicine and endocrinology, and emphasises the need for a better understanding of the impact of bariatric surgery on women's health.

Authors: A. K. Khamitov, A. A. Meldo, Z. V. Shvets, S. V. Dora

Direction: Informatics, Computer Technologies And Control

Keywords: bariatric surgery, machine learning, obesity, fertility prognosis, antimüllerian hormone

---

View full article