Prediction of pregnancy outcomes of single vitrified-warmed blastocyst transfer using combination of an automatic classification algorithm applied on cleavage stage embryos and blastocyst morphological assessment: a single - centre, retrospective study

Abstract

Abstract Background To investigate a combination of the Early Embryo Viability Assessment (EEVA) system and blastocyst morphological assessment as a predictor of pregnancy outcomes of single vitrified-warmed blastocyst transfer, such as implantation and ongoing pregnancy. Methods The retrospective study was conducted in a single centre from 2020 to 2023 and included 511 single vitrified-warmed blastocyst transfer cycles. Blastocyst were selected for transfer based on conventional morphological assessment. Embryos Day 3 were evaluated using EEVA software. The correlation between the EEVA system alone, or a combination of the EEVA system and blastocyst morphological assessment, and pregnancy outcomes was qualified by generalized estimating equations (GEEs). Results The implantation rate and ongoing pregnancy were higher with lower scores generated by the EEVA software. A GEE model showed a negative association between a higher embryo score and lower odds of implantation and ongoing pregnancy. The OR of Score 3;4;5 vs. 1 were 0.350; 0.288; 0.282 (95%CI 0.201–0.607; 0.151–0.546; 0.125–0.636, p=0.000), respectively, for implantation. The OR of Score 3;4;5 vs. 1 were 0.321; 0256; 0.228 (95%CI 0.184-0.557; 0.129-0.505; 0.092-0.563, p=0.000), respectively, for ongoing pregnancy. The AUC of the model using the EEVA system for implantation and ongoing pregnancy potential is 0.651 and 0.655, respectively. The AUC of the model combining both systems for implantation and ongoing pregnancy potential is 0.730 and 0.726. The differences were statistically significant (p=0.0001). Conclusions The EEVA system can predict the success rates of assisted reproduction cycles, especially when combined with blastocyst morphological assessment in blastocyst selection for transfer.