Infertility affects one in six couples globally, with advanced maternal age leading to challenges in IVF, prompting a study to improve live birth predictions following single vitrified-warmed blastocyst transfer (SVBT) in these patients.
A retrospective analysis of 1,168 SVBT cycles identified key predictors of live birth, such as the quality of the inner cell mass and trophectoderm, number of oocytes retrieved, and endometrial thickness, using advanced machine-learning models.
The stacking model showed the best performance in predicting live birth outcomes, significantly outperforming traditional methods, suggesting that utilizing these models can enhance clinical decision-making for AMA patients, although more research is needed to confirm findings in larger settings.