Abstract Study question Does ERICA’s prognosis ranking based on ploidy, predict early miscarriage following positive biochemical pregnancy test? Summary answer The lower ERICA grades embryos, the higher the likelihood of early miscarriage, irrespective of age group. What is known already The vast majority of early miscarriages are due to aneuploidy, but preimplantation genetic testing for aneuploidy (PGTA) is potentially invasive, expensive, time-consuming and usually necessitates cryopreservation. Current methods for embryo selection based on morphology and morphokinetics are poorly correlated with ploidy. ERICA is a deep-learning non-invasive tool for embryo ranking, trained to identify ploidy, and has previously been shown to be similar or better than experienced embryologists in assessing implantation potential. AI-based tools capable of embryo ranking and assessment could help save laboratory time and costs, avoiding risk to embryos from invasive techniques. Study design, size, duration Retrospective analysis of 599 blastocysts transferred over 12 months in which ERICA was used to assist embryologists during the embryo selection process. ERICA’s prognosis based on ploidy potential is presented as groups labelled as “optimal”, “good”, “fair”, or “poor”. Embryo transfers (ET) reaching biochemical pregnancy (beta-hCG ≥ 20iu) were considered for the study. Early pregnancy loss (EPL) was defined as a biochemical pregnancy failing to develop a gestational sac and/or failure to show heartbeat (FHR). Participants/materials, setting, methods ETs resulting in biochemical pregnancies at two IVF clinics were followed-up to FHR till 8 weeks gestation. EPLs were divided into groups according to the presence or absence of a pregnancy sac. ERICA’s suggested prognosis during the embryo selection process was tested against pregnancy outcomes. Further analysis of pregnancy outcomes and their relation to ERICA’s labels was also performed based on age groups. Z-test for two proportions was used to assess statistical significance. Main results and the role of chance 506 ETs were performed for 599 embryos (mean 1.2 embryos), from which 285 resulted in positive pregnancy tests (56.3%). Thirty-one (10.9%) EPLs happened before the identification of a gestational sac (GS). Ten pregnancies failed to develop FHR after initial GS identification (3.9%), for an overall EPL of 14.4%. The average age in this group was 35.4 years. When evaluated using ERICA’s labels “optimal”, “good”, “fair, and “poor”, chances of miscarriage before GS were 8.9% (8/89); 14.1% (11/78); 18.5% (5/27); and 18.7% (9/48) respectively, where denominator represents total number within a label (i.e. EPL/n). When including all EPLs, chances of miscarriage according to the same labels were 11.2%; 17.9%; 22.2%; and 22.9% respectively. ERICA’s performance to anticipate the risk of EPL showed statistical significance when the optimal label was compared against all other labels (Z -1.786, p < 0.05), and against the poor prognosis label (Z=-1.653, p < 0.05). After stratifying the dataset according to age groups, increasing miscarriage rates were maintained as ERICA’s prognosis for an embryo worsened, regardless of age groups. The most notable performance was for ≤35-year-olds, where embryos ranked as optimal had an EPL rate of 14.3% in contrast to lowest ranked embryos having a 33.3% EPL rate. Limitations, reasons for caution The retrospective nature of this study along with its sample-size might limit the reach of our conclusions, in particular for older patients. The results we present must still be confirmed prospectively, and on a larger dataset. Wider implications of the findings Most EPLs are attributed to genetic factors, hence ERICA’s training for embryo ranking was based on ploidy. We conclude that ERICA’s AI is able to identify embryos at a higher risk of EPL non-invasively. Cytogenetic studies from products of miscarriage would help to confirm the hypothesis. Trial registration number Not applicable
Read full abstract