Effect of a sharp serum oestradiol fall before HCG administration during ovarian stimulation in donors

The construction of machine learning-based predictive models for high-quality embryo formation in poor ovarian response patients with progestin-primed ovarian stimulation

OBJECTIVE

To explore the optimal models for predicting the formation of high-quality embryos in Poor Ovarian Response (POR) Patients with Progestin-Primed Ovarian Stimulation (PPOS) using machine learning algorithms.

METHODS

A retrospective analysis was conducted on the clinical data of 4,216 POR cycles who underwent in vitro fertilization (IVF) / intracytoplasmic sperm injection (ICSI) at Sichuan Jinxin Xinan Women and Children's Hospital from January 2015 to December 2021. Based on the presence of high-quality cleavage embryos 72 h post-fertilization, the samples were divided into the high-quality cleavage embryo group (N = 1950) and the non-high-quality cleavage embryo group (N = 2266). Additionally, based on whether high-quality blastocysts were observed following full blastocyst culture, the samples were categorized into the high-quality blastocyst group (N = 124) and the non-high-quality blastocyst group (N = 1800). The factors influencing the formation of high-quality embryos were analyzed using logistic regression. The predictive models based on machine learning methods were constructed and evaluated accordingly.

RESULTS

Differential analysis revealed that there are statistically significant differences in 14 factors between high-quality and non-high-quality cleavage embryos. Logistic regression analysis identified 14 factors as influential in forming high-quality cleavage embryos. In models excluding three variables (retrieved oocytes, MII oocytes, and 2PN fertilized oocytes), the XGBoost model performed slightly better (AUC = 0.672, 95% CI = 0.636-0.708). Conversely, in models including these three variables, the Random Forest model exhibited the best performance (AUC = 0.788, 95% CI = 0.759-0.818). In the analysis of high-quality blastocysts, significant differences were found in 17 factors. Logistic regression analysis indicated that 13 factors influence the formation of high-quality blastocysts. Including these variables in the predictive model, the XGBoost model showed the highest performance (AUC = 0.813, 95% CI = 0.741-0.884).

CONCLUSION

We developed a predictive model for the formation of high-quality embryos using machine learning methods for patients with POR undergoing treatment with the PPOS protocol. This model can help infertility patients better understand the likelihood of forming high-quality embryos following treatment and help clinicians better understand and predict treatment outcomes, thus facilitating more targeted and effective interventions.

Estradiol (E2) Reduction Adversely Affect the Embryo Quality and Clinical Outcomes of In Vitro Fertilization and Embryo transfer (IVF-ET)

Objective

The purpose of this study was to explore the influence of decreased serum estradiol (E₂) levels during controlled ovarian hyperstimulation (COH) on in vitro fertilization and embryo transfer (IVF).

Methods

The clinical data of 300 IVF-ET cycles with patients were analyzed retrospectively. According to the presence of falling E₂ level during the COH, we divided all subjects into two groups: the E₂ levels fall group (n = 120, group A) and the control group (n = 180, group B). In group A, there were 57 patients with falling E₂ with drug dosage reduction. The other 63 patients experienced the decreased E₂ level spontaneously. The clinical and laboratory variables in the groups were compared. Receiver operator characteristic (ROC) curve analyses were carried out in order to evaluate the predict value of E₂ level on the day of human chorionic gonadotropin (hCG) administration on IVF outcomes.

Results

Duration and total dosage of gonadotropin (Gn) used were statistically more in group A than in group B (P < 0.001). The high-quality embryo rate was significantly lower in group A (P = 0.048). Women in group A had lower clinical pregnancy rate (P = 0.029), live birth rate (P < 0.001), ongoing pregnancy rate (P = 0.001), and higher early abortion rates (P = 0.008) than group B. Women with spontaneously falling E₂ group had a higher BMI index than those in the drug dosage reduction group (P = 0.001). More dosage and longer duration of Gn in spontaneously falling E₂ group than in the drug dosage reduction group (P < 0.01). There were no differences in clinical outcomes between the two types of E₂ decreased groups. Results from ROC showed an E₂ level <1987.5 pg/ml on the hCG day might predict early abortion in this study. The sensitivity was 58.4% and the specificity was 78.9%. In addition, an E₂ level >2020 pg/ml on the hCG day might be an index to predict live birth. The sensitivity was 57.0% and the specificity was 61.7%.

Conclusions

Reduction of E₂ during COH might adversely affect the clinical pregnancy, early abortion, and ongoing pregnancy of IVF-ET.

New options in assisted reproduction technology: the Cryotop method of oocyte vitrification

The Cryotop vitrification method has been shown to be a very useful tool for oocyte cryopreservation, giving excellent results regarding survival and clinical outcome. There are several clinical situations in which oocyte cryopreservation provides solutions that have not been available to date. This report describes three of these situations: (i) a low-responder patient who needed a single gene diagnosis due to the presence of a genetic disease; (ii) a patient undergoing endometrial bleeding on the day of oocyte retrieval who was also affected by a genetic disorder; and (iii) a patient who failed to become pregnant after the donation of vitrified oocytes and subsequently had the re-vitrified surplus embryos transferred. The resolution of these cases provides evidence of the enormous potential of the Cryotop method as a tool within assisted reproduction technology.