Fertility and sterility最新文献

Objective: To externally validate a fully automated embryo classification in in vitro fertilization (IVF) treatments.

Design: Retrospective cohort study SUBJECTS: A total of 6,434 patients undergoing 7,352 IVF treatments contributed 70,456 embryos.

Exposure: Embryos were evaluated by conventional morphology and retrospectively scored using a fully automated deep learning-based algorithm across conventional IVF, oocyte donation, and PGT-A cycles.

Main outcome measures: The primary outcomes were implantation and live birth including odds ratios (ORs) from generalized estimating equation (GEE) models. Secondary outcomes were embryo morphology, euploidy and miscarriage. Exploratory outcomes included comparison between conventional methodology and artificial intelligence (AI) algorithm with areas under the ROC curves (AUCs), agreement degree between AI and embryologists, Cohen's Kappa coefficient and relative risk (RR).

Results: Implantation and live birth rates increased as the automatic embryo score rose. The GEE model, controlling for confounders, showed the automatic score was associated with an OR of 1.31 (95%CI[1.25-1.36]) for implantation in treatments using oocytes from patients, and an OR of 1.17 (95%CI[1.14-1.20]) in the oocyte donation program, with no significant association in PGT-A treatments. For live birth, the ORs were 1.27 (95%CI[1.21-1.33]) for patients, 1.16 (95%CI[1.13-1.19]) for donors, and 1.05 (95%CI[1-1.10]) for PGT-A cycles. The average score was higher in embryos with better morphology, in euploid embryos compared to aneuploid embryos, and in embryos that resulted in a full-term pregnancy compared to those that miscarried. Concordance between the highest-scoring embryo and the embryo with the best conventional morphology was 71.4%(95%CI[67.7%-75.0%]) in treatments with patient oocytes and 61.0%(95%CI[58.6%-63.4%]) in the oocyte donation program. Overall, the Cohen's Kappa coefficient was 0.63. The automatic embryo score showed similar AUCs to conventional morphology, although implantation was higher when the transferred embryo matched the highest-scoring embryo from each cohort (57.36% vs. 49.98%). RR indicated a 1.14-fold increase in implantation likelihood when the top-ranked embryo was transferred.

Conclusion: Fully automated embryo scoring effectively ranked embryos based on their potential for implantation and live birth. The performance of the conventional methodology was comparable to that of the artificial intelligence-based technology; however, better clinical outcomes were observed when the highest-scoring embryo in the cohort was transferred.

Objective: To assess the adequate ovarian follicular development and oocyte recovery between ovarian potential (antral follicle count [AFC]) before the start of ovarian stimulation (OS) and oocyte quantity and quality at oocyte retrieval. A holistic overview of the current key performance indicators (KPIs) was applied to identify the complementary strengths and identify where the current repertoire can be expanded.

Design: Expert opinion.

Subjects: Not applicable.

Intervention: None.

Main outcome measures: To formulate a proposal for a refined and expanded repertoire of KPIs for individualized OS for Assisted Reproductive Technology.

Results: The performance and outcomes of OS on ovarian follicular development can be evaluated through the application of defined KPIs. Current KPIs for OS are the ovarian sensitivity index (OSI), the follicular output rate (FORT), the oocyte retrieval rate (ORR), and the follicle to oocyte index (FOI). Notably, there are no specific KPIs dedicated to the assessment of follicular development (i.e., recruitment, selection, growth and dominance). In light of this, we recommend expanding the current KPIs for OS to include "Early FORT" (accounting for the number of follicles measuring ≥10-11 mm on Day 5/6 of OS relative to AFC) and "Modified FORT" (the ratio between the number of follicles measuring ≥12 mm at the time of oocyte maturation triggering and AFC); the extension of ORR to include two discrete categories at oocyte retrieval: follicles ≥12 mm and follicles ≥16 mm, to ensure all responsive follicles are accounted for; and FOI to be measured at oocyte maturation triggering and oocyte retrieval ("Advanced FOI").

Conclusions: Once validated and adopted in clinical practice, we envisage that the proposed expanded KPIs measuring the effect of OS on follicular development (recruitment, selection, growth and dominance) will increase the understanding of the relationship between ovarian reserve measured by AFC and oocyte quantity and quality at oocyte retrieval. This understanding will enable physicians to better evaluate the direct effect of different gonadotropins and doses on ovarian response, leading to a more personalized approach to OS in the context of ART treatment.