O-096 Effect of Day-3 embryo morphology on blastocyst quality and ploidy: a machine-learning model of 34781 embryos

Abstract

Abstract Study question What is the predictive value of using Day-3 (D3) embryo morphology and clinical factors to identify good quality euploid blastocysts? Summary answer Using a machine-learning model, D3-cell count and fragmentation helps identifying embryos most and least likely to develop into euploid blastocysts. What is known already It is well-known that the pattern of embryo cleavage affects blastocyst ploidy. Less has been elucidated in relation to embryo fragmentation. Published studies often used outdated biopsy techniques (D3-biopsy) and obsolete genetic technologies (FISH). Hence, the association between embryo fragmentation and ploidy status remains controversial. Existing hypothesis is that embryo fragmentation is a regulation event to maintain homeostasis and normalize genetic constitution. Literature is lacking studies investigating this association using newer genetic technologies such as Next Generating Sequencing (NGS). Moreover, a predictive model using D3-embryo characteristics and clinical factors can be useful for triage of laboratory resources. Study design, size, duration Retrospective observational single center study including 34781 embryos from 5701 cycles, between March 2017 and March 2020. Embryos were evaluated for degree of fragmentation and cell number on D3, 68±1hrs post insemination. Female Age, AMH and BMI were annotated as patient characteristics. All blastocysts available on D5 or D6 with a quality ≥ BL3CC (n = 18361) were subjected to trophectoderm (TE) biopsy for Preimplantation-Genetic-Testing for aneuploidies (PGT-A) analysis with Next-Generation-Sequencing and ploidy rates were recorded. Participants/materials, setting, methods Degree of fragmentation was classified as follows: A( < =10%), B(11-25%), C(26-35%), D(>35%). Data on embryo fragmentation was stratified according to cell number category: <6cells, 6-10 cells, >10 cells and compacted stage. Morphology markers (cell-count and fragmentation rate), along with patient characteristics (age, anti-Mullerian hormone and body-mass index) was modeled using a gradient-boosting decision tree algorithm. Performance of the machine learning (ML) model was assessed with AUC values, calibration curves after partitioning the dataset 1:1 for training/validation. Main results and the role of chance Day-3 embryos consisting of < 6 cells (n = 5926), 6-10 cells (n = 23920), and >10 cells (n = 1612) were included, along with 3323 compacted embryos. The rate of good-quality blastocysts decreased with higher fragmentation rates (38.2%, 14.8%, 4.6%, and 1.6%, A, B, C, and D, respectively; P < 0.001). Day of biopsy was earlier for embryos with lower fragmentation rates (Day-5 biopsy: 24.2%, 9.7%, 4.0%, and 0.0%, P < 0.001). Among the biopsied blastocysts, euploidy rates were similar at 44.9%, 43.0%, 42.7%, and 66.7% in groups A vs B, C, and D, respectively (P = 0.075, 0.350 and 0.141). When stratified by cell number, euploidy rates were lowest in blastocysts derived from <6-cells, at 33.5%, 34.3%, 26.9%, and 50.0% in groups A vs B, C, and D, respectively (P = 0.803, 0.185 and 0.394). The best performance ML model was provided by using fragmentation % and cell count along with female age, BMI and AMH. This resulted in a modest predictive accuracy for predicting euploid embryo development (AUC: 0.72, 95% CI: 0.71 to 0.73). The model was well- calibrated and correctly assessed the probability of D3-embryos developing into euploid blastocyst. For instance, embryos with a predicted probability of ≤ 2.5% rarely developed into euploid blastocyst (actual rate: 2.6%) and model had a predictive value of 97.4%.Limitations, reasons for caution: The retrospective nature of the study and inter-observer variability in D3-embryo fragmentation scoring is a limitation. Nevertheless, embryologists performing the embryo scoring followed the same SOPs. Findings need to be validated in external cohorts. Wider implications of the findings The model can utilize clinical factors and D3-embryo morphology markers to estimate the probability of a D3-embryo developing into an euploid blastocyst. This model can be useful for patient information, mainly when a decision on embryo selection for PGT-A needs to take place. Trial registration number not applicable