ABSTRACT
First trimester pregnancy losses are commonly attributed to chromosomal abnormalities. The causes of pregnancy loss following transfer of a euploid embryo are not fully elucidated. The aim of this study was to evaluate clinical and embryological parameters for pregnancy failure following the transfer of a single euploid embryo. Pregnancy outcomes of single euploid embryo transfers from a single centre between January 2017 and March 2020 were retrospectively evaluated. Several clinical and embryological parameters were evaluated in consideration to pregnancy outcomes; total pregnancy loss and live birth. Endometrial preparation type, number of previous frozen embryo transfer cycles, history of recurrent pregnancy loss, higher body mass index, presence of endometriosis and/or adenomyosis and embryo quality were found to be significantly different between two groups. Morphokinetic parameter analysis of 523 euploid embryos using time-lapse imaging did not show any statistical differences between the two groups, however a significantly higher rate of uneven blastomeres in the cleavage stage was observed in the total preganncy loss group. Evaluation of clinical and embryological data can reveal possible factors associated with pregnancy loss that can facilitate improved patient consultation. Feasible interventions can potentially increase the chance of achieving a live birth.
Subject(s)
Infertility , Humans , Female , Infertility/therapy , Infertility/diagnosis , Male , Reproductive Techniques, AssistedABSTRACT
RESEARCH QUESTION: Can artificial intelligence identify predictors of an increased Day 5 blastocyst utilization rate (D5BUR), which is one of the most informative key performance indicators in an IVF laboratory? DESIGN: This retrospective, multicentre study evaluated six variables for predicting D5BUR using an artificial neural network (ANN): number of metaphase II (MII) oocytes injected (intracytoplasmic sperm injection); use of autologous/donated gametes; maternal age at oocyte retrieval; sperm concentration; progressive sperm motility rate; and fertilization rate. Cycles were divided into training and testing sets through stratified random sampling. D5BUR on Day 5 was grouped into <60% and ≥60% as per the Vienna consensus benchmark values. RESULTS: The area under the receiver operating characteristic curve (AUC) to predict the D5BUR groups was 80.2%. From the ANN model, all six independent variables were found to be of significant value for the prediction of D5BUR (P<0.0001), with the most important variable being the number of MII oocytes injected. Investigation of the effect of MII oocytes injected on D5BUR indicated an inverse correlation, with injection of an increasing number of MII oocytes resulting in a decreasing D5BUR (r=-0.344, P<0.001) and injection of up to six oocytes resulting in D5BUR ≥60%. CONCLUSION: The number of MII oocytes injected is the most important predictor of D5BUR. Exploration of additional variables and further validation of models that can predict D5BUR can guide the way towards personalized treatment and increased safety.
