Seeking arrangements: cell contact as a cleavage-stage biomarker.

RESEARCH QUESTION: What can three-dimensional cell contact networks tell us about the developmental potential of cleavage-stage human embryos? DESIGN: This pilot study was a retrospective analysis of two Embryoscope imaging datasets from two clinics. An artificial intelligence system was used to reconstruct the three-dimensional structure of embryos from 11-plane focal stacks. Networks of cell contacts were extracted from the resulting embryo three-dimensional models and each embryo's mean contacts per cell was computed. Unpaired t-tests and receiver operating characteristic curve analysis were used to statistically analyse mean cell contact outcomes. Cell contact networks from different embryos were compared with identical embryos with similar cell arrangements. RESULTS: At t4, a higher mean number of contacts per cell was associated with greater rates of blastulation and blastocyst quality. No associations were found with biochemical pregnancy, live birth, miscarriage or ploidy. At t8, a higher mean number of contacts was associated with increased blastocyst quality, biochemical pregnancy and live birth. No associations were found with miscarriage or aneuploidy. Mean contacts at t4 weakly correlated with those at t8. Four-cell embryos fell into nine distinct cell arrangements; the five most common accounted for 97% of embryos. Eight-cell embryos, however, displayed a greater degree of variation with 59 distinct cell arrangements. CONCLUSIONS: Evidence is provided for the clinical relevance of cleavage-stage cell arrangement in the human preimplantation embryo beyond the four-cell stage, which may improve selection techniques for day-3 transfers. This pilot study provides a strong case for further investigation into spatial biomarkers and three-dimensional morphokinetics.

Predicting the number of oocytes retrieved from controlled ovarian hyperstimulation with machine learning.

STUDY QUESTION: Can machine learning predict the number of oocytes retrieved from controlled ovarian hyperstimulation (COH)? SUMMARY ANSWER: Three machine-learning models were successfully trained to predict the number of oocytes retrieved from COH. WHAT IS KNOWN ALREADY: A number of previous studies have identified and built predictive models on factors that influence the number of oocytes retrieved during COH. Many of these studies are, however, limited in the fact that they only consider a small number of variables in isolation. STUDY DESIGN, SIZE, DURATION: This study was a retrospective analysis of a dataset of 11,286 cycles performed at a single centre in France between 2009 and 2020 with the aim of building a predictive model for the number of oocytes retrieved from ovarian stimulation. The analysis was carried out by a data analysis team external to the centre using the Substra framework. The Substra framework enabled the data analysis team to send computer code to run securely on the centre's on-premises server. In this way, a high level of data security was achieved as the data analysis team did not have direct access to the data, nor did the data leave the centre at any point during the study. PARTICIPANTS/MATERIALS, SETTING, METHODS: The Light Gradient Boosting Machine algorithm was used to produce three predictive models: one that directly predicted the number of oocytes retrieved and two that predicted which of a set of bins provided by two clinicians the number of oocytes retrieved fell into. The resulting models were evaluated on a held-out test set and compared to linear and logistic regression baselines. In addition, the models themselves were analysed to identify the parameters that had the biggest impact on their predictions. MAIN RESULTS AND THE ROLE OF CHANCE: On average, the model that directly predicted the number of oocytes retrieved deviated from the ground truth by 4.21 oocytes. The model that predicted the first clinician's bins deviated by 0.73 bins whereas the model for the second clinician deviated by 0.62 bins. For all models, performance was best within the first and third quartiles of the target variable, with the model underpredicting extreme values of the target variable (no oocytes and large numbers of oocytes retrieved). Nevertheless, the erroneous predictions made for these extreme cases were still within the vicinity of the true value. Overall, all three models agreed on the importance of each feature which was estimated using Shapley Additive Explanation (SHAP) values. The feature with the highest mean absolute SHAP value (and thus the highest importance) was the antral follicle count, followed by basal AMH and FSH. Of the other hormonal features, basal TSH, LH, and testosterone levels were similarly important and baseline LH was the least important. The treatment characteristic with the highest SHAP value was the initial dose of gonadotropins. LIMITATIONS, REASONS FOR CAUTION: The models produced in this study were trained on a cohort from a single centre. They should thus not be used in clinical practice until trained and evaluated on a larger cohort more representative of the general population. WIDER IMPLICATIONS OF FINDINGS: These predictive models for the number of oocytes retrieved from COH may be useful in clinical practice, assisting clinicians in optimizing COH protocols for individual patients. Our work also demonstrates the promise of using the Substra framework for allowing external researchers to provide clinically relevant insights on sensitive fertility data in a fully secure, trustworthy manner and opens a number of exciting avenues for accelerating future research. STUDY FUNDING/COMPETING INTEREST(S): This study was funded by the French Public Bank of Investment as part of the Healthchain Consortium. T.Fe., C.He., J.C., C.J., C.-A.P., and C.Hi. are employed by Apricity. C.Hi. has received consulting fees and honoraria from Vitrolife, Merck Serono, Ferring, Cooper Surgical, Dibimed, Apricity, and Fairtility and travel support from Fairtility and Vitrolife, participates on an advisory board for Merck Serono, was the founder and organizer of the AI Fertility conference, has stock in Aria Fertility, TMRW, Fairtility, Apricity, and IVF Professionals, and received free equipment from Planar in exchange for first user feedback. C.J. has received a grant from BPI. J.C. has also received a grant from BPI, is a member of the Merck AI advisory board, and is a board member of Labelia Labs. C.He has a contract for medical writing of this manuscript by CHU Nantes and has received travel support from Apricity. A.R. haș received honoraria from Ferring and Organon. T.Fe. has received a grant from BPI. TRIAL REGISTRATION NUMBER: N/A.

Machine learning for prediction of euploidy in human embryos: in search of the best-performing model and predictive features.

OBJECTIVE: To assess the best-performing machine learning (ML) model and features to predict euploidy in human embryos. DESIGN: Retrospective cohort analysis. SETTING: Department for reproductive medicine in a university hospital. PATIENT(S): One hundred twenty-eight infertile couples treated between January 2016 and December 2019. Demographic and clinical data and embryonic developmental and morphokinetic data from 539 embryos (45% euploid, 55% aneuploid) were analyzed. INTERVENTION(S): Random forest classifier (RFC), scikit-learn gradient boosting classifier, support vector machine, multivariate logistic regression, and naïve Bayes ML models were trained and used in 9 databases containing either 26 morphokinetic features (as absolute [A1] or interim [A2] times or combined [A3]) alone or plus 19 standard development features [B1, B2, and B3] with and without 40 demographic and clinical characteristics [C1, C2, and C3]. Feature selection and model retraining were executed for the best-performing combination of model and dataset. MAIN OUTCOME MEASURE(S): The main outcome measures were overall accuracy, precision, recall or sensitivity, F1 score (the weighted average of precision and recall), and area under the receiver operating characteristic curve (AUC) of ML models for each dataset. The secondary outcome measure was ranking of feature importance for the best-performing combination of model and dataset. RESULT(S): The RFC model had the highest accuracy (71%) and AUC (0.75) when trained and used on dataset C1. The precision, recall or sensitivity, F1 score, and AUC were 66%, 86%, 75%, and 0.75, respectively. The accuracy, recall or sensitivity, and F1 score increased to 72%, 88%, and 76%, respectively, after feature selection and retraining. Morphokinetic features had the highest relative predictive weight. CONCLUSION(S): The RFC model can predict euploidy with an acceptable accuracy (>70%) using a dataset including embryos' morphokinetics and standard embryonic development and subjects' demographic and clinical features.

Aneuploidy rates and morphokinetic parameters of embryos cultured in distinct culture media: a sibling oocyte study.

STUDY QUESTION: Do embryos from sibling oocytes assigned to distinct single-step media culture systems demonstrate differences in early embryo development, morphokinectics or aneuploidy rates? SUMMARY ANSWER: Embryo quality, morphokinetic parameters and aneuploidy rates from trophectoderm biopsy were similar between sibling embryos cultured in distinct media systems from the time of gamete isolation. WHAT IS KNOWN ALREADY: Studies on the effect of commercially available embryo culture media systems have demonstrated inconsistent impact on human embryonic development, morphokinetics, aneuploidy rates and clinical outcomes. In addition, these studies have been primarily randomized at the level of the embryo or the patient to culture media. STUDY DESIGN, SIZE, DURATION: Prospective sibling oocyte cohort derived from 200 subjects undergoing IVF at a tertiary academic medical center between February 2018 and November 2019. PARTICIPANTS/MATERIALS, SETTING, METHODS: Sibling oocytes were allocated to Global® or SAGE® media system based upon laterality of ovary from which they were retrieved. All embryos were cultured in a time-lapse incubator. Blastocysts underwent trophectoderm biopsy for preimplantation genetic testing for aneuploidy using next-generation sequencing. MAIN RESULTS AND THE ROLE OF CHANCE: One hundred twenty-seven subjects (n = 127) had paired blastocysts for biopsy in each culture media system. There was no difference in top quality blastocyst formation (47.1 ± 31.0 vs 48.1 ± 27.2%; P = 0.87) nor aneuploidy rate (62.3 ± 34.0 vs 56.1 ± 34.4%; P = 0.07) for sibling embryos cultured in Global versus SAGE media system. Embryo morphokinetic parameters including time to each cell division from two cells (t2) to eight cells (t8), time to morula stage (tM), time to blastocele formation (tSB), time to fully formed blastocyst (tB) and time to expansion of the blastocyst (tEB) were similar between paired blastocysts from each culture media system. LIMITATIONS, REASONS FOR CAUTION: Pregnancy outcomes and offspring health data were not available for analysis. WIDER IMPLICATIONS OF THE FINDINGS: Commercially available culture media may not have a differential impact on embryo development and blastocyst aneuploidy rate when patient and stimulation-related factors are held constant. STUDY FUNDING/COMPETING INTEREST(S): There was no external funding for this study. C.H. is owner of a consultancy company, IVF Professionals, Chief Scientific Officer at Apricity, Executive Director at TMRW and co-owner and shareholder of Aria Fertility. She has received speaker fees, consulting fees and travel support from Cooper Surgical and Vitrolife. J.B. is an employee and shareholder of vitrolife. TRIAL REGISTRATION NUMBER: N/A.

Is there a better evolutionary outcome in a 4-cell tetrahedron embryo?

With the growing understanding of in vitro fertilization and reproductive technology, the magnitude of studies related to embryonic evolution has also increased. The optimization of embryo selection is crucial to minimize the risk of multiple pregnancies and to guarantee successful implantation and pregnancy. On the second day of culture, the four-cell embryo can be shaped into different arrangements, such as tetrahedral and planar. Previous studies have shown that mammalian embryos have a tetrahedral shape and that any deviation from this ideal configuration can negatively affect blastocyst development. A few studies have also found that planar embryos would be linked to negative predictors of success for reaching the blastocyst stage and its good quality. Therefore, it seems that tetrahedral should be preferred over planar-shaped embryos for embryonic transfers, but there is still little understanding and evidence about this subject. Thus, the objective of the present paper was to review the available literature on study tendencies to compare tetrahedral and planar-shaped embryos considering their effect on implantation and pregnancy results.

An artificial intelligence model based on the proteomic profile of euploid embryos and blastocyst morphology: a preliminary study.

RESEARCH QUESTION: The study aimed to develop an artificial intelligence model based on artificial neural networks (ANNs) to predict the likelihood of achieving a live birth using the proteomic profile of spent culture media and blastocyst morphology. DESIGN: This retrospective cohort study included 212 patients who underwent single blastocyst transfer at IVI Valencia. A single image of each of 186 embryos was studied, and the protein profile was analysed in 81 samples of spent embryo culture medium from patients included in the preimplantation genetic testing programme. The information extracted from the analyses was used as input data for the ANN. The multilayer perceptron and the back-propagation learning method were used to train the ANN. Finally, predictive power was measured using the area under the curve (AUC) of the receiver operating characteristic curve. RESULTS: Three ANN architectures classified most of the embryos correctly as leading (LB+) or not leading (LB-) to a live birth: 100.0% for ANN1 (morphological variables and two proteins), 85.7% for ANN2 (morphological variables and seven proteins), and 83.3% for ANN3 (morphological variables and 25 proteins). The artificial intelligence model using information extracted from blastocyst image analysis and concentrations of interleukin-6 and matrix metalloproteinase-1 was able to predict live birth with an AUC of 1.0. CONCLUSIONS: The model proposed in this preliminary report may provide a promising tool to select the embryo most likely to lead to a live birth in a euploid cohort. The accuracy of prediction demonstrated by this software may improve the efficacy of an assisted reproduction treatment by reducing the number of transfers per patient. Prospective studies are, however, needed.

Data sharing: using blockchain and decentralized data technologies to unlock the potential of artificial intelligence: What can assisted reproduction learn from other areas of medicine?

The extension of blockchain use for nonfinancial domains has revealed opportunities to the health care sector that answer the need for efficient and effective data and information exchanges in a secure and transparent manner. Blockchain is relatively novel in health care and particularly for data analytics, although there are examples of improvements achieved. We provide a systematic review of blockchain uses within the health care industry, with a particular focus on the in vitro fertilization (IVF) field. Blockchain technology in the fertility sector, including data sharing collaborations compliant with ethical data handling within confines of international law, allows for large-scale prospective cohort studies to proceed at an international scale. Other opportunities include gamete donation and matching, consent sharing, and shared resources between different clinics.

Predictive modeling in reproductive medicine: Where will the future of artificial intelligence research take us?

Artificial intelligence (AI) systems have been proposed for reproductive medicine since 1997. Although AI is the main driver of emergent technologies in reproduction, such as robotics, Big Data, and internet of things, it will continue to be the engine for technological innovation for the foreseeable future. What does the future of AI research look like?

Managing the IVF laboratory during a pandemic: international perspectives from laboratory managers.

Fertility societies worldwide responded to the COVID-19 pandemic by recommending that fertility clinics close, or sharply reduce, the clinical operation, leading to a shift in the management of IVF laboratories in three phases: shutdown preparation; maintenance during shutdown; and restart. Each of these phases carries distinct risks that need identification and mitigation, forcing laboratory managers to rethink and adapt their procedures in response to the pandemic. The sudden and unprecedented nature of the pandemic forced laboratory managers from around the world to base decisions on opinion and experience when evidence-based response options were unavailable. These perspectives on pandemic response were presented during a virtual international symposium on COVID-19, held on 3 April 2020, and organized by the London Laboratory Managers' Group. Laboratory managers from seven different countries at different stages of the pandemic (China, Italy, Spain, France, UK, Brazil and Australia) presented their personal experiences to a select audience of experienced laboratory managers from 19 different countries. The intention of this paper is to collect the learnings and considerations from this group of laboratory managers who collaborated to share personal experiences to contribute to the debate surrounding what constitutes good IVF laboratory practice in extraordinary circumstances, such as the COVID-19 pandemic.

Cytoplasmic halo characteristics during fertilization and their implications for human preimplantation embryo development and pregnancy outcome.

RESEARCH QUESTION: Is the spatiotemporal phenomenology of the cytoplasmic halo during fertilization related to embryonic competence? DESIGN: Time-lapse images from 1009 zygotes were retrospectively analysed from 560 patients who underwent IVF with minimal stimulation and single vitrified-warmed blastocyst transfer between April 2017 and March 2018. Halo presence and morphokinetics were monitored and compared relative to embryo quality, blastocyst expansion and ongoing pregnancy. RESULTS: Halo was observed in 88% of fertilized oocytes. Embryos derived from zygotes without halo had significantly higher rates of rapid cleavage (P = 0.0004), cell fusion (P = 0.0028) and asymmetrical division (P = 0.0002) compared with those derived from zygotes with halo. Multivariate logistic regression analysis had significantly higher developmental rates compared with the expanded blastocyst stage in embryos displaying a halo, regardless of its distribution (adjusted odds ratio 0.435; P = 0.0004). Prolonged halo time intervals were significantly correlated with increased asymmetrical division at first cell division (P = 0.0412, P = 0.0088, respectively) and decreased developmental rates to expanded blastocyst stage (P = 0.0062, P = 0.0020, respectively). Additionally, prolonged presence of the cytoplasmic halo was associated with a decreased ongoing pregnancy rate (adjusted odds ratio 0.871; P = 0.006). Poor sperm quality and decreased oocyte diameter were correlated with absence of the cytoplasmic halo (P = 0.0477, P < 0.0001, respectively) or prolonged halo presence (P = 0.0139, P = 0.0002, respectively). CONCLUSIONS: Halo presence and morphokinetics are associated with cleavage patterns, development to blastocyst stage and ongoing pregnancy rate after single blastocyst transfer. Halo morphokinetics seems to reflect sperm and oocyte quality. Cytoplasmic halo might be valuable predictor for refining selection of more developmentally competent blastocysts.

Deep learning enables robust assessment and selection of human blastocysts after in vitro fertilization.

Visual morphology assessment is routinely used for evaluating of embryo quality and selecting human blastocysts for transfer after in vitro fertilization (IVF). However, the assessment produces different results between embryologists and as a result, the success rate of IVF remains low. To overcome uncertainties in embryo quality, multiple embryos are often implanted resulting in undesired multiple pregnancies and complications. Unlike in other imaging fields, human embryology and IVF have not yet leveraged artificial intelligence (AI) for unbiased, automated embryo assessment. We postulated that an AI approach trained on thousands of embryos can reliably predict embryo quality without human intervention. We implemented an AI approach based on deep neural networks (DNNs) to select highest quality embryos using a large collection of human embryo time-lapse images (about 50,000 images) from a high-volume fertility center in the United States. We developed a framework (STORK) based on Google's Inception model. STORK predicts blastocyst quality with an AUC of >0.98 and generalizes well to images from other clinics outside the US and outperforms individual embryologists. Using clinical data for 2182 embryos, we created a decision tree to integrate embryo quality and patient age to identify scenarios associated with pregnancy likelihood. Our analysis shows that the chance of pregnancy based on individual embryos varies from 13.8% (age ≥41 and poor-quality) to 66.3% (age <37 and good-quality) depending on automated blastocyst quality assessment and patient age. In conclusion, our AI-driven approach provides a reproducible way to assess embryo quality and uncovers new, potentially personalized strategies to select embryos.

Perivitelline threads associated with fragments in human cleavage stage embryos observed through time-lapse microscopy.

Perivitelline threads (PVT) are defined as thin filaments that extend across the perivitelline space connecting the zona pellucida with the oolemma or, in some cases, blastomere membrane. This is the first report of PVT in human embryos. Time-lapse imagery from 525 blastocysts with either tested ploidy, known implantation status, or both, were reviewed for the presence of PVT, the cell stage when PVT were first observed, association with fragmentation, ploidy or implantation potential; PVT were observed in most embryos (404/525 [77%]). The euploidy rate was similar in embryos with PVT (61/152 [40%]) and without PVT (17/35 [49%]). Implantation rates were also similar in embryos with PVT (64/259 [25%]) and without PVT (25/90 [28%]). In the embryos in which PVT were observed, 98% (396/404) developed at the two-cell stage. In most embryos (384/404 [95%]), PVT were observed to directly pull fragments from the embryo. Fragmentation occurred significantly less frequently in embryos without PVT compared with PVT (81/121 [67%] versus 388/404 [96%]; P < 0.001). These data suggest an association between PVT and fragmentation. This study is limited in that PVT were not characterized so their nature and origin remain unknown and to be determined in future studies.

Heat shock induces interferon-TAU gene expression by in vitro-produced bovine blastocysts.

PROBLEM: The type I interferon (IFN), IFN-tau (τ), is the primary embryonic signal for pregnancy maintenance in ruminants. This study determined the effects of heat shock upon IFN-τ (IFNT) gene expression by bovine blastocysts in vitro. METHOD OF STUDY: In vitro-produced blastocyst-stage embryos were exposed to 42°C for 4 hr, and mRNA for heat-shock protein 70 (HSP70) and IFNT quantified. RESULTS: Heat shock increased both HSP70 and IFNT expression. There was a significant correlation between HSP70 and IFNT transcript levels irrespective of whether a blastocyst had been exposed to heat shock or not. CONCLUSION: The increase in IFNT as a result of heat shock suggests that a proportion of the variation in IFNT expression observed in blastocyst-stage embryos is a response to stress.

Modelling a risk classification of aneuploidy in human embryos using non-invasive morphokinetics.

This study determined whether morphokinetic variables between aneuploid and euploid embryos differ as a potential aid to select euploid embryos for transfer. Following insemination, EmbryoScope time-lapse images from 98 blastocysts were collected and analysed blinded to ploidy. The morphokinetic variables were retrospectively compared with ploidy, which was determined following trophectoderm biopsy and analysis by array comparative genomic hybridization or single-nucleotide polymorphic array. Multiple aneuploid embryos were delayed at the initiation of compaction (tSC; median 85.1 hours post insemination (hpi); P=0.02) and the time to reach full blastocyst stage (tB; median 110.9hpi, P=0.01) compared with euploid embryos (tSC median 79.7 hpi, tB median 105.9 hpi). Embryos having single or multiple aneuploidy (median 103.4 hpi, P=0.004 and 101.9 hpi, P=0.006, respectively) had delayed initiation of blastulation compared with euploid embryos (median 95.1hpi). No significant differences were observed in first or second cell-cycle length, synchrony of the second or third cell cycles, duration of blastulation, multinucleation at the 2-cell stage and irregular division patterns between euploid and aneuploid embryos. This non-invasive model for ploidy classification may be used to avoid selecting embryos with high risk of aneuploidy while selecting those with reduced risk.