A hybrid artificial intelligence model leverages multi-centric clinical data to improve fetal heart rate pregnancy prediction across time-lapse systems

STUDY QUESTION

Can artificial intelligence (AI) algorithms developed to assist embryologists in evaluating embryo morphokinetics be enriched with multi-centric clinical data to better predict clinical pregnancy outcome?

SUMMARY ANSWER

Training algorithms on multi-centric clinical data significantly increased AUC compared to algorithms that only analyzed the time-lapse system (TLS) videos.

WHAT IS KNOWN ALREADY

Several AI-based algorithms have been developed to predict pregnancy, most of them based only on analysis of the time-lapse recording of embryo development. It remains unclear, however, whether considering numerous clinical features can improve the predictive performances of time-lapse based embryo evaluation.

STUDY DESIGN, SIZE, DURATION

A dataset of 9986 embryos (95.60% known clinical pregnancy outcome, 32.47% frozen transfers) from 5226 patients from 14 European fertility centers (in two countries) recorded with three different TLS was used to train and validate the algorithms. A total of 31 clinical factors were collected. A separate test set (447 videos) was used to compare performances between embryologists and the algorithm.

PARTICIPANTS/MATERIALS, SETTING, METHODS

Clinical pregnancy (defined as a pregnancy leading to a fetal heartbeat) outcome was first predicted using a 3D convolutional neural network that analyzed videos of the embryonic development up to 2 or 3 days of development (33% of the database) or up to 5 or 6 days of development (67% of the database). The output video score was then fed as input alongside clinical features to a gradient boosting algorithm that generated a second score corresponding to the hybrid model. AUC was computed across 7-fold of the validation dataset for both models. These predictions were compared to those of 13 senior embryologists made on the test dataset.

MAIN RESULTS AND THE ROLE OF CHANCE

The average AUC of the hybrid model across all 7-fold was significantly higher than that of the video model (0.727 versus 0.684, respectively, P = 0.015; Wilcoxon test). A SHapley Additive exPlanations (SHAP) analysis of the hybrid model showed that the six first most important features to predict pregnancy were morphokinetics of the embryo (video score), oocyte age, total gonadotrophin dose intake, number of embryos generated, number of oocytes retrieved, and endometrium thickness. The hybrid model was shown to be superior to embryologists with respect to different metrics, including the balanced accuracy (P ≤ 0.003; Wilcoxon test). The likelihood of pregnancy was linearly linked to the hybrid score, with increasing odds ratio (maximum P-value = 0.001), demonstrating the ranking capacity of the model. Training individual hybrid models did not improve predictive performance. A clinic hold-out experiment was conducted and resulted in AUCs ranging between 0.63 and 0.73. Performance of the hybrid model did not vary between TLS or between subgroups of embryos transferred at different days of embryonic development. The hybrid model did fare better for patients older than 35 years (P < 0.001; Mann-Whitney test), and for fresh transfers (P < 0.001; Mann-Whitney test).

LIMITATIONS, REASONS FOR CAUTION

Participant centers were located in two countries, thus limiting the generalization of our conclusion to wider subpopulations of patients. Not all clinical features were available for all embryos, thus limiting the performances of the hybrid model in some instances.

WIDER IMPLICATIONS OF THE FINDINGS

Our study suggests that considering clinical data improves pregnancy predictive performances and that there is no need to retrain algorithms at the clinic level unless they follow strikingly different practices. This study characterizes a versatile AI algorithm with similar performance on different time-lapse microscopes and on embryos transferred at different development stages. It can also help with patients of different ages and protocols used but with varying performances, presumably because the task of predicting fetal heartbeat becomes more or less hard depending on the clinical context. This AI model can be made widely available and can help embryologists in a wide range of clinical scenarios to standardize their practices.

STUDY FUNDING/COMPETING INTEREST(S)

Funding for the study was provided by ImVitro with grant funding received in part from BPIFrance (Bourse French Tech Emergence (DOS0106572/00), Paris Innovation Amorçage (DOS0132841/00), and Aide au Développement DeepTech (DOS0152872/00)). A.B.-C. is a co-owner of, and holds stocks in, ImVitro SAS. A.B.-C. and F.D.M. hold a patent for 'Devices and processes for machine learning prediction of in vitro fertilization' (EP20305914.2). A.D., N.D., M.M.F., and F.D.M. are or have been employees of ImVitro and have been granted stock options. X.P.-V. has been paid as a consultant to ImVitro and has been granted stocks options of ImVitro. L.C.-D. and C.G.-S. have undertaken paid consultancy for ImVitro SAS. The remaining authors have no conflicts to declare.

TRIAL REGISTRATION NUMBER

N/A.

P-286 Can laser assisted hatching help implantation of warmed blastocysts in presence of fragmented cells ?

Study question

Does laser assisted hatching (LAH) following warming of blastocysts containing fragmentated cells improves blastocyst expansion and implantation?

Summary answer

The application of LAH does not improve blastocyst expansion and implantation regardless the presence or absence of fragmented cells.

What is known already

The absence of natural hatching is one of the hypotheses of implantation failure after cryopreservation, a process that could lead to hardening of the zona pellucida. Another theory is the fact that cellular fragments inside the zona pellucida, surrounding the trophectoderm, could impairs the exit of the blastocyst through the zona decreasing its chances of implantation. Available data regarding the effect of LAH on blastocysts after vitrification are inconclusive and limited to small samples. Evaluating the effectiveness of LHA performed at the time of blastocyst warming when cellular fragments are present could elucidate its impact on hatching and implantation

Study design, size, duration

A bicentric prospective randomized study including 344 successive FET cycles from January 2020 until March 2021. Patients were enrolled only once in the study. Patients underwent a natural cycle or hormonal replacement treatment for FET. Blastocysts graded ≥ BL3BB (Gardner scoring) underwent artificial collapse and were vitrified on D5 or D6. Only blastocysts surviving post-warming were considered in the analysis. Primary end point was clinical pregnancy rate.

Participants/materials, setting, methods

Patients ≤42 years with ≤3 previous oocyte retrievals scheduled for the first elective single embryo transfer (eSET) with vitrified/warmed blastocysts. Survived blastocysts were randomized immediately after warming to LAH group (n = 172) or to control group (no-LAH, n = 172). Cellular fragmentation was annotated as a percentage of the total volume of the embryo (0%, ≤25%, ≤50%, &gt;50%) and LHA was performed on the opposite side. Embryo expansion was annotated at time of transfer, at 3 hours post-warming.

Main results and the role of chance

Patients age were similar between LHA (33.1±9.3) and controls (34.8±7.5). Patients in LAH and controls had similar pregnancy rates (hCG &gt;100) (46% versus 52%, respectively), CPR (37% versus 36%, respectively) (NS) and miscarriage rates. No difference was observed in CPR in relation to patients age. A significant increase in implantation was observed when blastocyst expansion took place 3 hours after warming, independently whether allocated in LAH (47% versus 17%, p &lt; 0.01) or no-LAH group (51% versus 33%, p &lt; 0.01). LAH did not influence cell expansion (83% in LAH versus 85% in no-LAH), however more blastocysts underwent hatching in LAH group (27% versus 12% in no-LAH, p &lt; 0.06). Significantly more embryos that had hatched in LAH group led to pregnancy compared to no-LHA (83% versus 67%, respectively) (p = 0.05).

Extra-cellular (EC) fragmentation not did not impact implantation in neither of the groups. LAH group had 46% of embryos implanted when absence of fragmentation, 40% when EC was present at ≤ 25%, 58% when EC was present at &gt; 25% (NS). In no-LAH group, 52% of embryos implanted when absence of fragmentation, 49% when EC was present at ≤ 25%, 65% when EC was present at &gt; 25% (NS).

Limitations, reasons for caution

A sample size of 700 blastocysts was first chosen calculating a 10% difference in clinical pregnancy rate (CPR) between LAH-group and no-LAH group. The study was interrupted following this interim analysis. Live birth outcomes should be considered in a further analysis to conclude on the null impact of LHA post-warming.

Wider implications of the findings

This study adds to the evidence of the existence of a limited potential of the application of LAH on vitrified-warmed blastocysts and its impact in terms of clinical pregnancy rates.

Trial registration number

not applicable

P–756 Predictive factors influencing multiple live births in cumulative IVF cycles: retrospective analysis of over 265000 embryo transfer procedures from the national French registry

Study question

What are the factors that could predict the number of embryos to be transferred in order to diminish risk of multiple pregnancies?

Summary answer

Single embryo transfer (SET) is advisable for &lt;38 year-old women in fresh cycles and for &lt;35 year-old women in FET whatever the IVF number attempts.

What is known already

Multiple pregnancies are associated to increased maternal and perinatal complications. Risks associated to multiple implantations are significantly reduced with SET policy. However, while SET is more assertive with a lesser negative impact in younger patients (&lt;35 years), its feasibility is less evident for the older population, whom oocyte quality is likely compromised. A double embryo transfer (DET) could improve chances of implantation and shorten their time to pregnancy. Identification of risk factors for multiple pregnancies could help in decision making for a double or SET and reduce chances for multiple gestations without reducing the chances to achieve pregnancy.

Study design, size, duration

A retrospective study from the national French data registry provided and approved by the Agence de la Biomédecine was performed. A total of 196530 fresh and 68913 frozen cycles from women aged 18–43 year-old were included (2014–2017). Risk factors assessed included women’s age, number of attempts, number of oocytes, fertilization rate, embryo stage, number of embryos transferred, number of supernumerary embryos frozen. Secondary infertility, oocyte donor, oocyte freezing, PGT, freeze-all and IVM cycles were excluded.

Participants/materials, setting, methods

Cumulative cycles derived from 65% of ICSI, 32% of IVF and 3,2% IVF/ICSI. The distribution of patients age at oocyte retrieval was 60% &lt; 35, 21% &lt; 38, 11% &lt; 40, and 8% ≥ 40 years old. Multivariable logistic regression was conducted to calculate adjusted odds ratios with 95% confidence intervals for live birth chance and multiple live birth risk associated with each risk factor.

Main results and the role of chance

The chances of obtaining a cumulative live birth decreases with increased patients age (OR 0.71 for 35–38 years and 0.47 for 38–40 years, p &lt; 0.00001), with increased number of attempts (from OR 0.87 for attempt = 2 to OR 0.74 for attempt ≥ 4, p &lt; 0.00001), and for frozen embryos transferred (OR 0.14, p &lt; 0.00001). The chances of live birth increases with the increased number of oocytes (from OR 1.33 for 4–12 to OR 1.52 for &gt; 18, p &lt; 0.00001 in all cases), with a fertilisation rate &gt;40% (OR 1.29, p &lt; 0.00001), with blastocyst transfer (OR 1.29, p &lt; 0.00001), with the increase on the number of frozen embryos (OR 7.37 for &gt;1, OR 13.08 for &gt;2, and OR 16.92 for &gt;6, p &lt; 0.00001 in all cases) and number of embryos transferred (OR 1.42 for 2 embryos and OR 1.39 for &gt;2 embryos, p &lt; 0.00001 in all cases).

In case of live birth, the risks of multiple births when two embryos were transferred decreases in patients aged &gt;38 years (OR 0.50, p &lt; 0.00001) and for frozen embryos transferred (OR 0.65, p &lt; 0.00001). The risk increases with a fertilisation rate &gt;60% (OR 1.30, p &lt; 0.00001), with blastocysts transfer (OR 1.34, p &lt; 0.00001) and when at least one supernumerary embryo is frozen (OR &gt; 1.30, p &lt; 0.00001).

Limitations, reasons for caution

This study is limited in only providing a risk-benefit balance for multiples on the choice of transferring one or two embryos. Clinical data such as stimulation protocols and doses of gonadotropins were not considered in this evaluation.

Wider implications of the findings: This study provides help to develop a strategy for the medical staff in the decision making for the number of embryos to be transferred. It may also serve as a patient’s information aid and help to improve their chances of achieving a health singleton if pregnant.

Trial registration number

Not applicable

Movement characteristics and hyperactivation of human sperm on different epithelial cell monolayers

Studies of sperm movement characteristics concern mainly sperm swimming between two glass surfaces (as in the Makler chamber). Using automated videomicrography, (CellSoft, Cryo Resources, New York, USA), we have analysed the movements of human sperm swimming on monolayers of different origins: monkey kidney (Vero) cells, bovine oviduct cells, and human endometrial cells. About 10(5) sperm were deposited upon preparations consisting of monocellular layers adhering to a coverglass, and placed in a deep slide-coverglass system. Experiments were first performed at room temperature then at 37 degrees C. At room temperature, motion characteristics on Vero cell layers (six samples) were not different from those measured in either the conditioned or corresponding non-conditioned media, except for the amplitude of lateral head displacement (ALH) which was significantly lower. Comparison of the three different cell monolayers showed no difference between them for the corresponding motion parameters. The data were dramatically different at 37 degrees C: sperm swimming on cell monolayers of genital origin (oviduct or endometrium) exhibited high rates of hyperactivation (HA: 36.7% and 38.6% respectively), which was significantly more than on either Vero cells (10.9%) or in a control medium (12.6%). Moreover, HA rates were significantly higher on genital cell monolayers than in the corresponding conditioned medium. Hyperactivated sperm exhibited lasting 'star-spin' trajectories rather than 'transitional phases'. It is concluded that passage of sperm on either oviduct or endometrial epithelial cell monolayers can induce sperm hyperactivation and improve their fertilizing capacity.