RESUMEN
PURPOSE: Ovarian stimulation with gonadotropins is crucial for obtaining mature oocytes for in vitro fertilization (IVF). Determining the optimal gonadotropin dosage is essential for maximizing its effectiveness. Our study aimed to develop a machine learning (ML) model to predict oocyte counts in IVF patients and retrospectively analyze whether higher gonadotropin doses improve ovarian stimulation outcomes. METHODS: We analyzed the data from 9598 ovarian stimulations. An ML model was employed to predict the number of mature metaphase II (MII) oocytes based on clinical parameters. These predictions were compared with the actual counts of retrieved MII oocytes at different gonadotropin dosages. RESULTS: The ML model provided precise predictions of MII counts, with the AMH and AFC being the most important, and the previous stimulation outcome and age, the less important features for the prediction. Our findings revealed that increasing gonadotropin dosage did not result in a higher number of retrieved MII oocytes. Specifically, for patients predicted to produce 4-8 MII oocytes, a decline in oocyte count was observed as gonadotropin dosage increased. Patients with low (1-3) and high (9-12) MII predictions achieved the best results when administered a daily dose of 225 IU; lower and higher doses proved to be less effective. CONCLUSIONS: Our study suggests that high gonadotropin doses do not enhance MII oocyte retrieval. Our ML model can offer clinicians a novel tool for the precise prediction of MII to guide gonadotropin dosing.
RESUMEN
Controlled ovarian stimulation is tailored to the patient based on clinical parameters but estimating the number of retrieved metaphase II (MII) oocytes is a challenge. Here, we have developed a model that takes advantage of the patient's genetic and clinical characteristics simultaneously for predicting the stimulation outcome. Sequence variants in reproduction-related genes identified by next-generation sequencing were matched to groups of various MII oocyte counts using ranking, correspondence analysis, and self-organizing map methods. The gradient boosting machine technique was used to train models on a clinical dataset of 8,574 or a clinical-genetic dataset of 516 ovarian stimulations. The clinical-genetic model predicted the number of MII oocytes better than that based on clinical data. Anti-Müllerian hormone level and antral follicle count were the two most important predictors while a genetic feature consisting of sequence variants in the GDF9, LHCGR, FSHB, ESR1, and ESR2 genes was the third. The combined contribution of genetic features important for the prediction was over one-third of that revealed for anti-Müllerian hormone. Predictions of our clinical-genetic model accurately matched individuals' actual outcomes preventing over- or underestimation. The genetic data upgrades the personalized prediction of ovarian stimulation outcomes, thus improving the in vitro fertilization procedure.
