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.

Study on the optimal time limit of frozen embryo transfer and the effect of a long-term frozen embryo on pregnancy outcome.

In this retrospective study conducted at Sichuan Jinxin Xinan Women and Children's Hospital spanning January 2015 to December 2021, our objective was to investigate the impact of embryo cryopreservation duration on outcomes in frozen embryo transfer. Participants, totaling 47,006 cycles, were classified into 3 groups based on cryopreservation duration: ≤1 year (Group 1), 1 to 6 years (Group 2), and ≥6 years (Group 3). Employing various statistical analyses, including 1-way ANOVA, Kruskal-Wallis test, chi-square test, and a generalized estimating equation model, we rigorously adjusted for confounding factors. Primary outcomes encompassed clinical pregnancy rate and Live Birth Rate (LBR), while secondary outcomes included biochemical pregnancy rate, multiple pregnancy rate, ectopic pregnancy rate, early and late miscarriage rates, preterm birth rate, neonatal birth weight, weeks at birth, and newborn sex. Patient distribution across cryopreservation duration groups was as follows: Group 1 (40,461 cycles), Group 2 (6337 cycles), and Group 3 (208 cycles). Postcontrolling for confounding factors, Group 1 exhibited a decreased likelihood of achieving biochemical pregnancy rate, clinical pregnancy rate, and LBR (OR < 1, aOR < 1, P < .05). Furthermore, an elevated incidence of ectopic pregnancy was observed (OR > 1, aOR > 1), notably significant after 6 years of freezing time [aOR = 4.141, 95% confidence intervals (1.013-16.921), P = .05]. Cryopreservation exceeding 1 year was associated with an increased risk of early miscarriage and preterm birth (OR > 1, aOR > 1). No statistically significant differences were observed in birth weight or sex between groups. However, male infant birth rates were consistently higher than those of female infants across all groups. In conclusion, favorable pregnancy outcomes align with embryo cryopreservation durations within 1 year, while freezing for more than 1 year may diminish clinical pregnancy and LBRs, concurrently elevating the risk of ectopic pregnancy and preterm birth.

The association of post-embryo transfer SARS-CoV-2 infection with early pregnancy outcomes in in vitro fertilization: a prospective cohort study.

BACKGROUND: The influence of SARS-CoV-2 infection after embryo transfer on early pregnancy outcomes in in vitro fertilization or intracytoplasmic sperm injection-embryo transfer treatment remains inadequately understood. This knowledge gap endures despite an abundance of studies investigating the repercussions of preceding SARS-CoV-2 infection on early pregnancy outcomes in spontaneous pregnancies. OBJECTIVE: This study aimed to investigate the association between SARS-CoV-2 infection within 10 weeks after embryo transfer and early pregnancy outcomes in patients undergoing in vitro fertilization/intracytoplasmic sperm injection treatment. STUDY DESIGN: This prospective cohort study was conducted at a single public in vitro fertilization center in China. Female patients aged 20 to 39 years, with a body mass index ranging from 18 to 30 kg/m2, undergoing in vitro fertilization/intracytoplasmic sperm injection treatment, were enrolled between September 2022 and December 2022, with follow-up extended until March 2023. The study tracked SARS-CoV-2 infection time (≤14 days, ≤28 days, and ≤10 weeks after embryo transfer), symptoms, vaccination status, the interval between vaccination and embryo transfer, and early pregnancy outcomes, encompassing biochemical pregnancy rate, implantation rate, clinical pregnancy rate, and early miscarriage rate. The study used single-factor analysis and multivariate logistic regression to examine the association between SARS-CoV-2 infection status, along with other relevant factors, and the early pregnancy outcomes. RESULTS: A total of 857 female patients undergoing in vitro fertilization/intracytoplasmic sperm injection treatment were analyzed. In the first stage, SARS-CoV-2 infection within 14 days after embryo transfer did not have a significant negative association with the biochemical pregnancy rate (adjusted odds ratio, 0.74; 95% confidence interval, 0.51-1.09). In the second stage, SARS-CoV-2 infection within 28 days after embryo transfer had no significant association with the implantation rate (36.6% in infected vs 44.0% in uninfected group; P=.181). No statistically significant association was found with the clinical pregnancy rate after adjusting for confounding factors (adjusted odds ratio, 0.69; 95% confidence interval, 0.56-1.09). In the third stage, SARS-CoV-2 infection within 10 weeks after embryo transfer had no significant association with the early miscarriage rate (adjusted odds ratio, 0.77; 95% confidence interval, 0.35-1.71). CONCLUSION: Our study suggests that SARS-CoV-2 infection within 10 weeks after embryo transfer may not be negatively associated with the biochemical pregnancy rate, implantation rate, clinical pregnancy rate, and early miscarriage rate in patients undergoing in vitro fertilization/intracytoplasmic sperm injection treatment. It is important to note that these findings are specific to the target population of in vitro fertilization/intracytoplasmic sperm injection patients aged 20 to 39 years, without previous SARS-CoV-2 infection, and with a body mass index of 18 to 30 kg/m2. This information offers valuable insights, addressing current concerns and providing a clearer understanding of the actual risk associated with SARS-CoV-2 infection after embryo transfer.