Fertility & Reproduction (Dec 2023)

#316 : Improved Time to Pregnancy When Combining an Artificial Intelligence Score and Morphology Grading for Embryo Selection During IVF

  • Ashleigh Storr,
  • Sonya Diakiw,
  • Jonathan Hall,
  • Tuc Nguyen,
  • Jarrod Moreton,
  • Don Perugini,
  • Michelle Perugini

DOI
https://doi.org/10.1142/S2661318223742169
Journal volume & issue
Vol. 05, no. 04
pp. 436 – 437

Abstract

Read online

Background and Aims: Embryo selection is critical in determining IVF success yet continues to be challenging due to the subjectivity of morphology grading methods, especially when grading fair/average quality embryos. Improving embryo selection could optimise implantation rates and minimise financial/emotional burden on patients. Artificial Intelligence (AI) algorithms represent promising, non-invasive methods of standardising embryo grading and potentially increasing IVF success rates. This study assessed whether an AI algorithm (Life Whisperer Viability) for evaluating the likelihood of clinical pregnancy improves time to pregnancy (TTP) when compared to or combined with standard morphology grading. Method: 305 de-identified 2D images of day 5 blastocysts (121 fresh/184 frozen) with matched clinical pregnancy outcomes (fetal heartbeat at first scan) from women who underwent IVF treatment from 2020-2023 were retrospectively assessed. All images were taken prior to transfer/freezing. TTP was assessed using a simulated cohort ranking method, with TTP being defined as the average number of transfers needed to obtain a clinical pregnancy. Results: A positive linear correlation of LWV scores with pregnancy outcomes was observed (p<0.001). ROC-AUC results indicate that LWV is selecting embryos leading to pregnancy at least as well, if not better, than Gardner morphology grading (0.641 vs 0.624), with further improvement observed when LWV and Gardner grading were combined. The TTP analysis showed a 7.3% reduction in TTP when using LWV over Gardner grading. Combined use of LWV+Gardner grading reduced TTP by up to 10.8%, with the largest improvement (5.3%) seen in the frozen group, where there was a higher distribution of average quality embryos. Conclusion: LWV showed improved embryo rankingand reduction in the estimated average number oftransfers needed to achieveclinical pregnancy. Furthermore, evaluation of TTP supports the combined use of LWV+Gardner grading, showing that they work synergistically to further improve ranking performance when selecting average quality embryos.