A nomogram model to predict the high risk of lower live birth probability in young women undergoing the first IVF-ET cycle: a retrospective study

Objective: To build a prediction nomogram for early prediction of live birth probabilities according to number of oocytes retrieved in women ≤ 35 years of age.

Methods: A prediction model was built including 9265 infertile women ≤ 35 years of age accepting their first ovum pick-up cycle from January 2018 to December 2022. Least absolute shrinkage and selection operator (LASSO) regression was performed to identify independent predictors and establish a nomogram to predict reproductive outcomes. Both discrimination and calibration were assessed by bootstrapping with 1000 resamples.

Results: The critical threshold for the number of retrieved oocytes associated with cumulative live birth was determined as 10.5 (AUC: 0.824). Consequently, a nomogram was constructed to predict the likelihood of obtaining fewer than 10 oocytes at one oocyte retrieval cycle. There were five indicators significantly related to the risk of obtaining less than 10 oocytes at one oocyte retrieval cycle, including age, antral follicle count (AFC), anti-Mullerian hormone (AMH), follicle-stimulating hormone (FSH), and FSH to luteinizing hormone ratio. These factors were subsequently used to develop a nomogram prediction model. The model's performance was evaluated using the area under the curve (AUC), concordance index (C-index), and calibration curves, which indicated fair predictive ability and good calibration.

Conclusion: We developed and validated a nomogram based on five ovarian reserve indicators to predict the risk of retrieving fewer than 10 oocytes at one oocyte retrieval cycle in women ≤ 35 years of age. The model demonstrated good discrimination and calibration, indicating its reliability for clinical application. This nomogram offers a practical and accurate tool for early identification of young women with potentially decreased ovarian reserve, enabling timely intervention and personalized management strategies.