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

O-124 A new artificial intelligence (AI) system in the block: impact of clinical data on embryo selection using four different time-lapse incubators

Study question

Can AI algorithms assist embryologists in evaluating embryos from any time-lapse system (TLS) along with clinical data to better predict pregnancy outcomes and reduce time-to-pregnancy?

Summary answer

Our algorithm (Embryoly) significantly increases accuracy in predicting clinical pregnancy by 26.9% amongst embryos deemed of fair and good quality when clinical data is included.

What is known already

Embryologists routinely use defined morpho-kinetic criteria to decide which embryo to transfer, and yet, many embryos deemed of good quality fail to lead to a pregnancy. Thus, AI algorithms to assist embryologists in objectively selecting the most promising embryos are in demand. To date, several reports indicate that AI algorithms are capable of predicting pregnancy clinical outcomes but to the best of our knowledge they only consider visual data (or together with a small set of clinical features) from individual TLI systems to generate their predictions. 

Study design, size, duration

A dataset of 6790 embryos (97.82% known clinical pregnancy outcome, 31.47% frozen transfers) from 2519 patients from 11 European fertility centers recorded with 4 different TLS (GERI-Merck, Embryoscope & EmbryoscopePlus-Vitrolife and MIRI-Esco) was used to train and validate Embryoly. Nine out of 93 clinical factors were identified as being the most predictive, including woman age, woman and man BMI and AMH levels. Performances were evaluated on a separate test dataset (393 videos).

Participants/materials, setting, methods

Clinical pregnancy outcome was predicted using a 3D convolutional neural network that analyzed up to 5 days of embryo development. The output score was further analyzed considering the clinical features to generate a second clinical score. Both predictions were compared to those of 10 senior embryologists made on the same test dataset (with and without clinical features). Embryo quality was assessed as: poor, fair, good. Unless specified otherwise, McNemar test was used for statistical tests.

Main results and the role of chance

Overall accuracy of embryologists in predicting clinical pregnancy  based on videos alone was 57.25% (CI 95% : 52.34% - 62.16%) compared to 60.56% (CI 95% : 55.71% - 65.41%) for Embryoly (p = 0.35).

When videos were analyzed together with the clinical factors, overall accuracy of embryologists was significantly lower than Embryoly (60.05% [CI 95% : 55.19% - 64.91%] vs 68.19% [CI 95% : 63.57% - 72.82%], p-value=0.015, respectively). Clinical factors significantly increased our accuracy by 7.63% (p-value=0.030). More specifically, Embryoly algorithms fared better in terms of detecting false positives (31.30% vs 19.34%) compared to embryologists, with a specificity of 74.4% vs. 58.6%, respectively.

If we consider only embryos of fair and good quality (71.50% of our test dataset) Embryoly’s accuracy was 13.52% higher than that of embryologists. This translates into AI having an even better ability to detect false positives for embryos that could be seen as good candidates for transfer (20.28% false positives against 42.70% for the embryologists). Embryoly performs differently across selected TLS when analyzing videos alone, but not when clinical data was also considered (chi2 test, p &lt; 0.001 and 0.5, respectively). Further work will investigate these discrepancies across TLS.

Limitations, reasons for caution

As of today, Embryoly’s accuracy in predicting the outcome of poor-quality embryos is not different to that of embryologists (79.46% vs 84.96%; p-value=0.19). We are improving this by exposing Embryoly to more “poor quality” embryos, so as to also identify poor quality embryos with unexpected potential for implantation.

Wider implications of the findings

Our pioneering findings support the use of AI for a standardized and couple-centered care in clinical embryology, integrating male and female factors with embryo development analyses from multiple TLS. Our approach has the potential to cost-effectively reduce time to pregnancy and is another step toward a personalized embryo transfer strategy.

Trial registration number

Not applicable

[Professional Practice Evaluation: How to improve quality management in procreation centers?]

OBJECTIVES

The Professional Practice Evaluation (PPE) is at the heart of quality management in procreation centers. Hereby, we report 3 years of EPP in Cytogenetics and Reproduction laboratory in Amiens University Hospital.

PATIENTS AND METHODS

This PPE is based upon prospective analysis of in vitro fertilization techniques regarding two major parameters: clinically in improving embryo transfer and biologically by determining fecundation levels. Clinical pregnancies in "Top Quality" trial is chosen as a major indicator of our results.

RESULTS

Per transfer, there is an increase of 8% for clinical pregnancies and 31% in "Top quality" trials.

DISCUSSION AND CONCLUSION

The improvement in our results allowed us to propose, in favourable conditions, single embryo transfer.

[Premature ovarian failure: which protocols?]

This review shows the results of the various studies concerning the protocols applied to the women presenting a premature ovarian failure. Will be thus analyzed the natural cycles (or semi-natural), the increase in the dose of gonadotrophins, the clomiphene citrate and the anti-aromatases, the protocols with GnRH agonists long, short, stop or microdoses, the protocols with GnRH antagonists and the adjuvant treatments: aspirin, nitric oxyde, recombinant LH recombining, growth hormone and androgens. The interest of several protocols is to collect a sufficient number of oocytes (and thus of embryos to be transferred), making it possible to obtain reasonable rates of pregnancy. However, it arises that the rates of pregnancy observed among these women depend not only on their ovarian reserve and their age, but are also function of the type of infertility, of the cycle number and the uterus.

[Management of an ovarian stimulation in case of a Kallmann-De Morsier syndrome. The role of LH]

We report a case of ovarian stimulation in a woman with a Kallmann-De Morsier syndrome, which resulted in a triple pregnancy and childbirth by caesarean section at 36 weeks of amenorrhea of three girls weighing from 1,950 to 2,300 g. Starting from a literature review of Kallmann-De Morsier syndrome, we discuss the role of LH during the follicular phase and the monitoring of ovarian stimulation.