Personalized prediction of the secondary oocytes number after ovarian stimulation for in vitro fertilization: a machine learning method

The objective of this study was to develop a predictive algorithm utilizing baseline clinical characteristics, cycle-specific parameters, and sequence variants to accurately predict the number of high-quality oocytes that will be obtained during oocyte retrieval in an IVF procedure. For this purpose, we analyzed the potential predictors that affect females’ clinical outcomes, assessed the effect of genetic factors on the ovarian response to ovarian stimulation, and developed a machine learning model to predict the number of fertilization-ready metaphase II (MII) oocytes at the oocyte retrieval. The performance of our model was also validated on a prospective cohort of ovulation-stimulated patients and oocyte donors.