Embryologist agreement when assessing blastocyst implantation probability: is data-driven prediction the solution to embryo assessment subjectivity?

Non-invasively predicting euploidy in human blastocysts via quantitative 3D morphology measurement: a retrospective cohort study

BACKGROUND

Blastocyst morphology has been demonstrated to be associated with ploidy status. Existing artificial intelligence models use manual grading or 2D images as the input for euploidy prediction, which suffer from subjectivity from observers and information loss due to incomplete features from 2D images. Here we aim to predict euploidy in human blastocysts using quantitative morphological parameters obtained by 3D morphology measurement.

METHODS

Multi-view images of 226 blastocysts on Day 6 were captured by manually rotating blastocysts during the preparation stage of trophectoderm biopsy. Quantitative morphological parameters were obtained by 3D morphology measurement. Six machine learning models were trained using 3D morphological parameters as the input and PGT-A results as the ground truth outcome. Model performance, including sensitivity, specificity, precision, accuracy and AUC, was evaluated on an additional test dataset. Model interpretation was conducted on the best-performing model.

RESULTS

All the 3D morphological parameters were significantly different between euploid and non-euploid blastocysts. Multivariate analysis revealed that three of the five parameters including trophectoderm cell number, trophectoderm cell size variance and inner cell mass area maintained statistical significance (P < 0.001, aOR = 1.054, 95% CI 1.034-1.073; P = 0.003, aOR = 0.994, 95% CI 0.991-0.998; P = 0.010, aOR = 1.003, 95% CI 1.001-1.006). The accuracy of euploidy prediction by the six machine learning models ranged from 80 to 95.6%, and the AUCs ranged from 0.881 to 0.984. Particularly, the decision tree model achieved the highest accuracy of 95.6% (95% CI 84.9-99.5%) with the AUC of 0.978 (95% CI 0.882-0.999), and the extreme gradient boosting model achieved the highest AUC of 0.984 (95% CI 0.892-1.000) with the accuracy of 93.3% (95% CI 81.7-98.6%). No significant difference was found between different age groups using either decision tree or extreme gradient boosting to predict euploid blastocysts. The quantitative criteria extracted from the decision tree imply that euploid blastocysts have a higher number of trophectoderm cells, larger inner cell mass area, and smaller trophectoderm cell size variance compared to non-euploid blastocysts.

CONCLUSIONS

Using quantitative morphological parameters obtained by 3D morphology measurement, the decision tree-based machine learning model achieved an accuracy of 95.6% and AUC of 0.978 for predicting euploidy in Day 6 human blastocysts.

TRIAL REGISTRATION

N/A.

Large language models to facilitate pregnancy prediction after in vitro fertilization

We evaluated the efficacy of large language models (LLMs), specifically, generative pre-trained transformer-4 (GPT-4), in predicting pregnancy following in vitro fertilization (IVF) treatment and compared its accuracy with results from an original published study. Our findings revealed that GPT-4 can autonomously develop and refine advanced machine learning models for pregnancy prediction with minimal human intervention. The prediction accuracy was 0.79, and the area under the receiver operating characteristic curve (AUROC) was 0.89, exceeding or being at least equivalent to the metrics reported in the original study, that is, 0.78 for accuracy and 0.87 for AUROC. The results suggest that LLMs can facilitate data processing, optimize machine learning models in predicting IVF success rates, and provide data interpretation methods. This capacity can help bridge the knowledge gap between data scientists and medical personnel to solve the most pressing clinical challenges. However, more experiments on diverse and larger datasets are needed to validate and promote broader applications of LLMs in assisted reproduction.

A review of artificial intelligence applications in in vitro fertilization

The field of reproductive medicine has witnessed rapid advancements in artificial intelligence (AI) methods, which have significantly enhanced the efficiency of diagnosing and treating reproductive disorders. The integration of AI algorithms into the in vitro fertilization (IVF) has the potential to represent the next frontier in advancing personalized reproductive medicine and enhancing fertility outcomes for patients. The potential of AI lies in its ability to bring about a new era characterized by standardization, automation, and an improved success rate in IVF. At present, the utilization of AI in clinical practice is still in its early stages and faces numerous ethical, regulatory, and technical challenges that require attention. In this review, we present an overview of the latest advancements in various applications of AI in IVF, including follicular monitoring, oocyte assessment, embryo selection, and pregnancy outcome prediction. The aim is to reveal the current state of AI applications in the field of IVF, their limitations, and prospects for future development. Further studies, which involve the development of comprehensive models encompassing multiple functions and the conduct of large-scale randomized controlled trials, could potentially indicate the future direction of AI advancements in the field of IVF.

Enhancing predictive models for egg donation: time to blastocyst hatching and machine learning insights

BACKGROUND

Data sciences and artificial intelligence are becoming encouraging tools in assisted reproduction, favored by time-lapse technology incubators. Our objective is to analyze, compare and identify the most predictive machine learning algorithm developed using a known implantation database of embryos transferred in our egg donation program, including morphokinetic and morphological variables, and recognize the most predictive embryo parameters in order to enhance IVF treatments clinical outcomes.

METHODS

Multicenter retrospective cohort study carried out in 378 egg donor recipients who performed a fresh single embryo transfer during 2021. All treatments were performed by Intracytoplasmic Sperm Injection, using fresh or frozen oocytes. The embryos were cultured in Geri® time-lapse incubators until transfer on day 5. The embryonic morphokinetic events of 378 blastocysts with known implantation and live birth were analyzed. Classical statistical analysis (binary logistic regression) and 10 machine learning algorithms were applied including Multi-Layer Perceptron, Support Vector Machines, k-Nearest Neighbor, Cart and C0.5 Classification Trees, Random Forest (RF), AdaBoost Classification Trees, Stochastic Gradient boost, Bagged CART and eXtrem Gradient Boosting. These algorithms were developed and optimized by maximizing the area under the curve.

RESULTS

The Random Forest emerged as the most predictive algorithm for implantation (area under the curve, AUC = 0.725, IC 95% [0.6232-0826]). Overall, implantation and miscarriage rates stood at 56.08% and 18.39%, respectively. Overall live birth rate was 41.26%. Significant disparities were observed regarding time to hatching out of the zona pellucida (p = 0.039). The Random Forest algorithm demonstrated good predictive capabilities for live birth (AUC = 0.689, IC 95% [0.5821-0.7921]), but the AdaBoost classification trees proved to be the most predictive model for live birth (AUC = 0.749, IC 95% [0.6522-0.8452]). Other important variables with substantial predictive weight for implantation and live birth were duration of visible pronuclei (DESAPPN-APPN), synchronization of cleavage patterns (T8-T5), duration of compaction (TM-TiCOM), duration of compaction until first sign of cavitation (TiCAV-TM) and time to early compaction (TiCOM).

CONCLUSIONS

This study highlights Random Forest and AdaBoost as the most effective machine learning models in our Known Implantation and Live Birth Database from our egg donation program. Notably, time to blastocyst hatching out of the zona pellucida emerged as a highly reliable parameter significantly influencing our implantation machine learning predictive models. Processes involving syngamy, genomic imprinting during embryo cleavage, and embryo compaction are also influential and could be crucial for implantation and live birth outcomes.

Development of a Novel Non-invasive Metabolomics Assay to Predict Implantation Potential of Human Embryos

Can a set of metabolites present in embryo culture media correlate with embryo implantation? Case-control study in two phases: discovery phase (101 samples) and validation phase (169 samples), collected between 2018 and 2022, with a total of 218 participants. Culture media samples with known implantation outcomes were collected after blastocyst embryo transfer (including both PGT and non-PGT cycles) and were analyzed using chromatography followed by mass spectrometry. The spectra were processed and analyzed using statistical and machine learning techniques to identify biomarkers associated with embryo implantation, and to develop a predictive model. In the discovery phase, 148 embryo implantation biomarkers were identified using high resolution equipment, and 47 of them were characterized. Our results indicate a significant enrichment of tryptophan metabolism, arginine and proline metabolism, and lysine degradation biochemical pathways. After transferring the method to a lower resolution equipment, a model able to assign a Metabolite Pregnancy Index (MPI) to each embryo culture media was developed, taking the concentration of 36 biomarkers as input. Applying this model to 20% of the validation samples (N=34) used as the test set, an accuracy of 85.29% was achieved, with a PPV (Positive Predictive Value) of 88% and a NPV (Negative Predictive Value) of 77.78%. Additionally, informative results were obtained for all the analyzed samples. Metabolite concentration in the media after in vitro culture shows correlation with embryo implantation potential. Furthermore, the mathematical combination of biomarker concentrations using Artificial Intelligence techniques can be used to predict embryo implantation outcome with an accuracy of around 85%.

Making and Selecting the Best Embryo in In vitro Fertilization

Currently, most assisted reproduction units transfer a single embryo to avoid multiple pregnancies. Embryologists must select the embryo to be transferred from a cohort produced by a couple during a cycle. This selection process should be accurate, non-invasive, inexpensive, reproducible, and available to in vitro fertilization (IVF) laboratories worldwide. Embryo selection has evolved from static and morphological criteria to the use of morphokinetic embryonic characteristics using time-lapse systems and artificial intelligence, as well as the genetic study of embryos, both invasive with preimplantation genetic testing for aneuploidies (PGT-A) and non-invasive (niPGT-A). However, despite these advances in embryo selection methods, the overall success rate of IVF techniques remains between 25 and 30%. This review summarizes the different methods and evolution of embryo selection, their strengths and limitations, as well as future technologies that can improve patient outcomes in the shortest possible time. These methodologies are based on procedures that are applied at different stages of embryo development, from the oocyte to the cleavage and blastocyst stages, and can be used in laboratory routine.

The synergy of morphokinetic parameters and sHLA-G in cleavage embryo enhancing implantation rates

Objective: This study aimed to assess the relationship between implantation and soluble HLA-G (sHLA-G) expression in cleavage embryo culture medium (ECM) in conjunction with early developmental kinetics determined by time-lapse imaging (TLI). Methods: A retrospective, single-center study was conducted involving 238 embryos from 165 patients who underwent Frozen-thawed embryo transfer (FET) using autologous oocytes, with either single or double embryo transfer. TLI morphokinetic parameters (t2, t3, t4, t5, t6, t7, t8, cc2, s2, cc3, s3) of embryos were analyzed, and sHLA-G levels in D3 ECM were measured using an enzyme-linked immunosorbent assay (ELISA). A hierarchical classification model was developed to categorize embryos into five groups (A, B, C, D, E). The correlation between sHLA-G levels, TLI classification of embryos, and embryo implantation was investigated to establish a non-invasive method for evaluating implantation potential. Multivariate logistic regression analysis was performed to identify potential influencing factors, and receiver operating characteristic (ROC) curves were used to evaluate the predictive value for implantation. Results: Multivariate unconditional logistic regression analysis indicated that TLI parameters t5 and s3 and sHLA-G level in ECM were independent risk factors affecting embryo implantation. The implantation rate decreased from TLI classification A to E. The proposed classification model effectively assessed the implantation potential of embryos. The implantation rate was higher in the sHLA-G positive group compared to the sHLA-G negative group (p < 0.001). The expression of sHLA-G in D3 ECM, combined with the TLI classification model, accurately evaluated the implantation potential of embryos with an AUC of 0.876. Conclusion: The integration of cleavage kinetics and embryonic sHLA-G expression could reliably identify embryos with a high likelihood of successful implantation.

Viewing early life without labels: optical approaches for imaging the early embryo†

Embryo quality is an important determinant of successful implantation and a resultant live birth. Current clinical approaches for evaluating embryo quality rely on subjective morphology assessments or an invasive biopsy for genetic testing. However, both approaches can be inherently inaccurate and crucially, fail to improve the live birth rate following the transfer of in vitro produced embryos. Optical imaging offers a potential non-invasive and accurate avenue for assessing embryo viability. Recent advances in various label-free optical imaging approaches have garnered increased interest in the field of reproductive biology due to their ability to rapidly capture images at high resolution, delivering both morphological and molecular information. This burgeoning field holds immense potential for further development, with profound implications for clinical translation. Here, our review aims to: (1) describe the principles of various imaging systems, distinguishing between approaches that capture morphological and molecular information, (2) highlight the recent application of these technologies in the field of reproductive biology, and (3) assess their respective merits and limitations concerning the capacity to evaluate embryo quality. Additionally, the review summarizes challenges in the translation of optical imaging systems into routine clinical practice, providing recommendations for their future development. Finally, we identify suitable imaging approaches for interrogating the mechanisms underpinning successful embryo development.

Generative artificial intelligence to produce high-fidelity blastocyst-stage embryo images

STUDY QUESTION

Can generative artificial intelligence (AI) models produce high-fidelity images of human blastocysts?

SUMMARY ANSWER

Generative AI models exhibit the capability to generate high-fidelity human blastocyst images, thereby providing substantial training datasets crucial for the development of robust AI models.

WHAT IS KNOWN ALREADY

The integration of AI into IVF procedures holds the potential to enhance objectivity and automate embryo selection for transfer. However, the effectiveness of AI is limited by data scarcity and ethical concerns related to patient data privacy. Generative adversarial networks (GAN) have emerged as a promising approach to alleviate data limitations by generating synthetic data that closely approximate real images.

STUDY DESIGN, SIZE, DURATION

Blastocyst images were included as training data from a public dataset of time-lapse microscopy (TLM) videos (n = 136). A style-based GAN was fine-tuned as the generative model.

PARTICIPANTS/MATERIALS, SETTING, METHODS

We curated a total of 972 blastocyst images as training data, where frames were captured within the time window of 110-120 h post-insemination at 1-h intervals from TLM videos. We configured the style-based GAN model with data augmentation (AUG) and pretrained weights (Pretrained-T: with translation equivariance; Pretrained-R: with translation and rotation equivariance) to compare their optimization on image synthesis. We then applied quantitative metrics including Fréchet Inception Distance (FID) and Kernel Inception Distance (KID) to assess the quality and fidelity of the generated images. Subsequently, we evaluated qualitative performance by measuring the intelligence behavior of the model through the visual Turing test. To this end, 60 individuals with diverse backgrounds and expertise in clinical embryology and IVF evaluated the quality of synthetic embryo images.

MAIN RESULTS AND THE ROLE OF CHANCE

During the training process, we observed consistent improvement of image quality that was measured by FID and KID scores. Pretrained and AUG + Pretrained initiated with remarkably lower FID and KID values compared to both Baseline and AUG + Baseline models. Following 5000 training iterations, the AUG + Pretrained-R model showed the highest performance of the evaluated five configurations with FID and KID scores of 15.2 and 0.004, respectively. Subsequently, we carried out the visual Turing test, such that IVF embryologists, IVF laboratory technicians, and non-experts evaluated the synthetic blastocyst-stage embryo images and obtained similar performance in specificity with marginal differences in accuracy and sensitivity.

LIMITATIONS, REASONS FOR CAUTION

In this study, we primarily focused the training data on blastocyst images as IVF embryos are primarily assessed in blastocyst stage. However, generation of an array of images in different preimplantation stages offers further insights into the development of preimplantation embryos and IVF success. In addition, we resized training images to a resolution of 256 × 256 pixels to moderate the computational costs of training the style-based GAN models. Further research is needed to involve a more extensive and diverse dataset from the formation of the zygote to the blastocyst stage, e.g. video generation, and the use of improved image resolution to facilitate the development of comprehensive AI algorithms and to produce higher-quality images.

WIDER IMPLICATIONS OF THE FINDINGS

Generative AI models hold promising potential in generating high-fidelity human blastocyst images, which allows the development of robust AI models as it can provide sufficient training datasets while safeguarding patient data privacy. Additionally, this may help to produce sufficient embryo imaging training data with different (rare) abnormal features, such as embryonic arrest, tripolar cell division to avoid class imbalances and reach to even datasets. Thus, generative models may offer a compelling opportunity to transform embryo selection procedures and substantially enhance IVF outcomes.

STUDY FUNDING/COMPETING INTEREST(S)

This study was supported by a Horizon 2020 innovation grant (ERIN, grant no. EU952516) and a Horizon Europe grant (NESTOR, grant no. 101120075) of the European Commission to A.S. and M.Z.E., the Estonian Research Council (grant no. PRG1076) to A.S., and the EVA (Erfelijkheid Voortplanting & Aanleg) specialty program (grant no. KP111513) of Maastricht University Medical Centre (MUMC+) to M.Z.E.

TRIAL REGISTRATION NUMBER

Not applicable.

WISE: whole-scenario embryo identification using self-supervised learning encoder in IVF

PURPOSE

To study the effectiveness of whole-scenario embryo identification using a self-supervised learning encoder (WISE) in in vitro fertilization (IVF) on time-lapse, cross-device, and cryo-thawed scenarios.

METHODS

WISE was based on the vision transformer (ViT) architecture and masked autoencoders (MAE), a self-supervised learning (SSL) method. To train WISE, we prepared three datasets including the SSL pre-training dataset, the time-lapse identification dataset, and the cross-device identification dataset. To identify whether pairs of images were from the same embryos in different scenarios in the downstream identification tasks, embryo images including time-lapse and microscope images were first pre-processed through object detection, cropping, padding, and resizing, and then fed into WISE to get predictions.

RESULTS

WISE could accurately identify embryos in the three scenarios. The accuracy was 99.89% on the time-lapse identification dataset, and 83.55% on the cross-device identification dataset. Besides, we subdivided a cryo-thawed evaluation set from the cross-device test set to have a better estimation of how WISE performs in the real-world, and it reached an accuracy of 82.22%. There were approximately 10% improvements in cross-device and cryo-thawed identification tasks after the SSL method was applied. Besides, WISE demonstrated improvements in the accuracy of 9.5%, 12%, and 18% over embryologists in the three scenarios.

CONCLUSION

SSL methods can improve embryo identification accuracy even when dealing with cross-device and cryo-thawed paired images. The study is the first to apply SSL in embryo identification, and the results show the promise of WISE for future application in embryo witnessing.

A brief history of artificial intelligence embryo selection: from black-box to glass-box

With the exponential growth of computing power and accumulation of embryo image data in recent years, artificial intelligence (AI) is starting to be utilized in embryo selection in IVF. Amongst different AI technologies, machine learning (ML) has the potential to reduce operator-related subjectivity in embryo selection while saving labor time on this task. However, as modern deep learning (DL) techniques, a subcategory of ML, are increasingly used, its integrated black-box attracts growing concern owing to the well-recognized issues regarding lack of interpretability. Currently, there is a lack of randomized controlled trials to confirm the effectiveness of such black-box models. Recently, emerging evidence has shown underperformance of black-box models compared to the more interpretable traditional ML models in embryo selection. Meanwhile, glass-box AI, such as interpretable ML, is being increasingly promoted across a wide range of fields and is supported by its ethical advantages and technical feasibility. In this review, we propose a novel classification system for traditional and AI-driven systems from an embryology standpoint, defining different morphology-based selection approaches with an emphasis on subjectivity, explainability, and interpretability.

Embryo ranking agreement between embryologists and artificial intelligence algorithms

OBJECTIVE

To evaluate the degree of agreement of embryo ranking between embryologists and eight artificial intelligence (AI) algorithms.

DESIGN

Retrospective study.

PATIENT(S)

A total of 100 cycles with at least eight embryos were selected from the Weill Cornell Medicine database. For each embryo, the full-length time-lapse (TL) videos, as well as a single embryo image at 120 hours, were given to five embryologists and eight AI algorithms for ranking.

INTERVENTION(S)

None.

MAIN OUTCOME MEASURE(S)

Kendall rank correlation coefficient (Kendall's τ).

RESULT(S)

Embryologists had a high degree of agreement in the overall ranking of 100 cycles with an average Kendall's tau (K-τ) of 0.70, slightly lower than the interembryologist agreement when using a single image or video (average K-τ = 0.78). Overall agreement between embryologists and the AI algorithms was significantly lower (average K-τ = 0.53) and similar to the observed low inter-AI algorithm agreement (average K-τ = 0.47). Notably, two of the eight algorithms had a very low agreement with other ranking methodologies (average K-τ = 0.05) and between each other (K-τ = 0.01). The average agreement in selecting the best-quality embryo (1/8 in 100 cycles with an expected agreement by random chance of 12.5%; confidence interval [CI]95: 6%-19%) was 59.5% among embryologists and 40.3% for six AI algorithms. The incidence of the agreement for the two algorithms with the low overall agreement was 11.7%. Agreement on selecting the same top two embryos/cycle (expected agreement by random chance corresponds to 25.0%; CI95: 17%-32%) was 73.5% among embryologists and 56.0% among AI methods excluding two discordant algorithms, which had an average agreement of 24.4%, the expected range of agreement by random chance. Intraembryologist ranking agreement (single image vs. video) was 71.7% and 77.8% for single and top two embryos, respectively. Analysis of average raw scores indicated that cycles with low diversity of embryo quality generally resulted in a lower overall agreement between the methods (embryologists and AI models).

CONCLUSION(S)

To our knowledge, this is the first study that evaluates the level of agreement in ranking embryo quality between different AI algorithms and embryologists. The different concordance methods were consistent and indicated that the highest agreement was intraembryologist agreement, followed by interembryologist agreement. In contrast, the agreement between some of the AI algorithms and embryologists was similar to the inter-AI algorithm agreement, which also showed a wide range of pairwise concordance. Specifically, two AI models showed intra- and interagreement at the level expected from random selection.

Does cleavage stage morphology increase the discriminatory power of prediction in blastocyst transfer outcome?

PURPOSE

To evaluate the contribution of the cleavage stage morphological parameters to the prediction of blastocyst transfer outcomes.

METHODS

A retrospective study was conducted on 8383 single-blastocyst transfer cycles including 2246 fresh and 6137 vitrified-warmed cycles. XGboost, LASSO, and GLM algorithms were employed to establish models for assessing the predictive value of the cleavage stage morphological parameters in transfer outcomes. Four models were developed using each algorithm: all-in model with or without day 3 morphology and embryo quality-only model with or without day 3 morphology.

RESULTS

The live birth rate was 48.04% in the overall cohort. The AUCs of the models with the algorithm of XGboost were 0.83, 0.82, 0.63, and 0.60; with LASSO were 0.66, 0.66, 0.61, and 0.60; and with GLM were 0.66, 0.66, 0.61, and 0.60 respectively. In models 1 and 2, female age, basal FSH, peak E2, endometrial thickness, and female BMI were the top five critical features for predicting live birth; In models 3 and 4, the most crucial factor was blastocyst formation on D5 rather than D6. In model 3, incorporating cleavage stage morphology, including early cleavage, D3 cell number, and fragmentation, was significantly associated with successful live birth. Additionally, the live birth rates for blastocysts derived from on-time, slow, and fast D3 embryos were 49.7%, 39.5%, and 52%, respectively.

CONCLUSIONS

The value of cleavage stage morphological parameters in predicting the live birth outcome of single blastocyst transfer is limited.

The Role of Artificial Intelligence and Machine Learning in Assisted Reproductive Technologies

Artificial intelligence (AI) and machine learning, the form most commonly used in medicine, offer powerful tools utilizing the strengths of large data sets and intelligent algorithms. These systems can help to revolutionize delivery of treatments, access to medical care, and improvement of outcomes, particularly in the realm of reproductive medicine. Whether that is more robust oocyte and embryo grading or more accurate follicular measurement, AI will be able to aid clinicians, and most importantly patients, in providing the best possible and individualized care. However, despite all of the potential strengths of AI, algorithms are not immune to bias and are vulnerable to the many socioeconomic and demographic biases that current healthcare systems suffer from. Wrong diagnoses as well is furthering of healthcare discrimination are real possibilities if both the capabilities and limitations of AI are not well understood. Armed with appropriate knowledge of how AI can most appropriately operate within medicine, and specifically reproductive medicine, will enable clinicians to both create and utilize machine learning-based innovations for the furthering of reproductive medicine and ultimately achieving the goal of building of healthy families.

Predicting the likelihood of live birth: an objective and user-friendly blastocyst grading system

RESEARCH QUESTION

Can day-5 blastocysts be ranked according to their likelihood of live birth using an objective and user-friendly grading system?

DESIGN

A retrospective multicentre study conducted between 2017 and 2019, including 1044 day-5 blastocysts. Blastocyst expansion degree, trophectoderm and inner cell mass quality were assessed morphologically and morphometrically. Several analyses were conducted: the association between the qualitative and quantitative assessment for the blastocyst expansion degree and the number of trophectoderm cells; the effect of the embryo quality on day 3 and the contribution of the three blastocyst parameters to live birth, with logistic regression; and a decision tree with the most significant variables to create the new scoring system.

RESULTS

Cut-off points were found to discriminate between expanding and expanded blastocysts (165 µm for blastocyst diameter) and between trophectoderm grades (A: ≥14 cells; B: 11-13 cells; C: ≤10 cells). When the embryos reached the blastocyst stage, their quality on day 3 did not add predictive value for implantation and live birth. In the logistic regression analysis, the only parameter capable of significantly predicting the live birth likelihood was the trophectoderm grade: A versus C (OR 1.95, 95% CI 1.26 to 3.0); B versus C (OR 1.71, 95% CI 1.22 to 2.4). The decision tree supported the finding that the trophectoderm grade had the highest predictive value for a live birth, followed by the blastocyst expansion degree in a second step.

CONCLUSIONS

This new method makes objective blastocyst assessment feasible, allowing for standardization and exportation to other laboratories worldwide.

Embryo selection through artificial intelligence versus embryologists: a systematic review

STUDY QUESTION

What is the present performance of artificial intelligence (AI) decision support during embryo selection compared to the standard embryo selection by embryologists?

SUMMARY ANSWER

AI consistently outperformed the clinical teams in all the studies focused on embryo morphology and clinical outcome prediction during embryo selection assessment.

WHAT IS KNOWN ALREADY

The ART success rate is ∼30%, with a worrying trend of increasing female age correlating with considerably worse results. As such, there have been ongoing efforts to address this low success rate through the development of new technologies. With the advent of AI, there is potential for machine learning to be applied in such a manner that areas limited by human subjectivity, such as embryo selection, can be enhanced through increased objectivity. Given the potential of AI to improve IVF success rates, it remains crucial to review the performance between AI and embryologists during embryo selection.

STUDY DESIGN SIZE DURATION

The search was done across PubMed, EMBASE, Ovid Medline, and IEEE Xplore from 1 June 2005 up to and including 7 January 2022. Included articles were also restricted to those written in English. Search terms utilized across all databases for the study were: ('Artificial intelligence' OR 'Machine Learning' OR 'Deep learning' OR 'Neural network') AND ('IVF' OR 'in vitro fertili*' OR 'assisted reproductive techn*' OR 'embryo'), where the character '*' refers the search engine to include any auto completion of the search term.

PARTICIPANTS/MATERIALS SETTING METHODS

A literature search was conducted for literature relating to AI applications to IVF. Primary outcomes of interest were accuracy, sensitivity, and specificity of the embryo morphology grade assessments and the likelihood of clinical outcomes, such as clinical pregnancy after IVF treatments. Risk of bias was assessed using the Modified Down and Black Checklist.

MAIN RESULTS AND THE ROLE OF CHANCE

Twenty articles were included in this review. There was no specific embryo assessment day across the studies-Day 1 until Day 5/6 of embryo development was investigated. The types of input for training AI algorithms were images and time-lapse (10/20), clinical information (6/20), and both images and clinical information (4/20). Each AI model demonstrated promise when compared to an embryologist's visual assessment. On average, the models predicted the likelihood of successful clinical pregnancy with greater accuracy than clinical embryologists, signifying greater reliability when compared to human prediction. The AI models performed at a median accuracy of 75.5% (range 59-94%) on predicting embryo morphology grade. The correct prediction (Ground Truth) was defined through the use of embryo images according to post embryologists' assessment following local respective guidelines. Using blind test datasets, the embryologists' accuracy prediction was 65.4% (range 47-75%) with the same ground truth provided by the original local respective assessment. Similarly, AI models had a median accuracy of 77.8% (range 68-90%) in predicting clinical pregnancy through the use of patient clinical treatment information compared to 64% (range 58-76%) when performed by embryologists. When both images/time-lapse and clinical information inputs were combined, the median accuracy by the AI models was higher at 81.5% (range 67-98%), while clinical embryologists had a median accuracy of 51% (range 43-59%).

LIMITATIONS REASONS FOR CAUTION

The findings of this review are based on studies that have not been prospectively evaluated in a clinical setting. Additionally, a fair comparison of all the studies were deemed unfeasible owing to the heterogeneity of the studies, development of the AI models, database employed and the study design and quality.

WIDER IMPLICATIONS OF THE FINDINGS

AI provides considerable promise to the IVF field and embryo selection. However, there needs to be a shift in developers' perception of the clinical outcome from successful implantation towards ongoing pregnancy or live birth. Additionally, existing models focus on locally generated databases and many lack external validation.

STUDY FUNDING/COMPETING INTERESTS

This study was funded by Monash Data Future Institute. All authors have no conflicts of interest to declare.

REGISTRATION NUMBER

CRD42021256333.

ESHRE good practice recommendations on recurrent implantation failure

STUDY QUESTION

How should recurrent implantation failure (RIF) in patients undergoing ART be defined and managed?

SUMMARY ANSWER

This is the first ESHRE good practice recommendations paper providing a definition for RIF together with recommendations on how to investigate causes and contributing factors, and how to improve the chances of a pregnancy.

WHAT IS KNOWN ALREADY

RIF is a challenge in the ART clinic, with a multitude of investigations and interventions offered and applied in clinical practice, often without biological rationale or with unequivocal evidence of benefit.

STUDY DESIGN SIZE DURATION

This document was developed according to a predefined methodology for ESHRE good practice recommendations. Recommendations are supported by data from the literature, if available, and the results of a previously published survey on clinical practice in RIF and the expertise of the working group. A literature search was performed in PubMed and Cochrane focussing on 'recurrent reproductive failure', 'recurrent implantation failure', and 'repeated implantation failure'.

PARTICIPANTS/MATERIALS SETTING METHODS

The ESHRE Working Group on Recurrent Implantation Failure included eight members representing the ESHRE Special Interest Groups for Implantation and Early Pregnancy, Reproductive Endocrinology, and Embryology, with an independent chair and an expert in statistics. The recommendations for clinical practice were formulated based on the expert opinion of the working group, while taking into consideration the published data and results of the survey on uptake in clinical practice. The draft document was then open to ESHRE members for online peer review and was revised in light of the comments received.

MAIN RESULTS AND THE ROLE OF CHANCE

The working group recommends considering RIF as a secondary phenomenon of ART, as it can only be observed in patients undergoing IVF, and that the following description of RIF be adopted: 'RIF describes the scenario in which the transfer of embryos considered to be viable has failed to result in a positive pregnancy test sufficiently often in a specific patient to warrant consideration of further investigations and/or interventions'. It was agreed that the recommended threshold for the cumulative predicted chance of implantation to identify RIF for the purposes of initiating further investigation is 60%. When a couple have not had a successful implantation by a certain number of embryo transfers and the cumulative predicted chance of implantation associated with that number is greater than 60%, then they should be counselled on further investigation and/or treatment options. This term defines clinical RIF for which further actions should be considered. Nineteen recommendations were formulated on investigations when RIF is suspected, and 13 on interventions. Recommendations were colour-coded based on whether the investigations/interventions were recommended (green), to be considered (orange), or not recommended, i.e. not to be offered routinely (red).

LIMITATIONS REASONS FOR CAUTION

While awaiting the results of further studies and trials, the ESHRE Working Group on Recurrent Implantation Failure recommends identifying RIF based on the chance of successful implantation for the individual patient or couple and to restrict investigations and treatments to those supported by a clear rationale and data indicating their likely benefit.

WIDER IMPLICATIONS OF THE FINDINGS

This article provides not only good practice advice but also highlights the investigations and interventions that need further research. This research, when well-conducted, will be key to making progress in the clinical management of RIF.

STUDY FUNDING/COMPETING INTERESTS

The meetings and technical support for this project were funded by ESHRE. N.M. declared consulting fees from ArtPRED (The Netherlands) and Freya Biosciences (Denmark); Honoraria for lectures from Gedeon Richter, Merck, Abbott, and IBSA; being co-founder of Verso Biosense. He is Co-Chief Editor of Reproductive Biomedicine Online (RBMO). D.C. declared being an Associate Editor of Human Reproduction Update, and declared honoraria for lectures from Merck, Organon, IBSA, and Fairtility; support for attending meetings from Cooper Surgical, Fujifilm Irvine Scientific. G.G. declared that he or his institution received financial or non-financial support for research, lectures, workshops, advisory roles, or travelling from Ferring, Merck, Gedeon-Richter, PregLem, Abbott, Vifor, Organon, MSD, Coopersurgical, ObsEVA, and ReprodWissen. He is an Editor of the journals Archives of Obstetrics and Gynecology and Reproductive Biomedicine Online, and Editor in Chief of Journal Gynäkologische Endokrinologie. He is involved in guideline developments and quality control on national and international level. G.L. declared he or his institution received honoraria for lectures from Merck, Ferring, Vianex/Organon, and MSD. He is an Associate Editor of Human Reproduction Update, immediate past Coordinator of Special Interest Group for Reproductive Endocrinology of ESHRE and has been involved in Guideline Development Groups of ESHRE and national fertility authorities. D.J.M. declared being an Associate Editor for Human Reproduction Open and statistical Advisor for Reproductive Biomedicine Online. B.T. declared being shareholder of Reprognostics and she or her institution received financial or non-financial support for research, clinical trials, lectures, workshops, advisory roles or travelling from support for attending meetings from Ferring, MSD, Exeltis, Merck Serono, Bayer, Teva, Theramex and Novartis, Astropharm, Ferring. The other authors had nothing to disclose.

DISCLAIMER

This Good Practice Recommendations (GPR) document represents the views of ESHRE, which are the result of consensus between the relevant ESHRE stakeholders and are based on the scientific evidence available at the time of preparation. ESHRE GPRs should be used for information and educational purposes. They should not be interpreted as setting a standard of care or be deemed inclusive of all proper methods of care, or be exclusive of other methods of care reasonably directed to obtaining the same results. They do not replace the need for application of clinical judgement to each individual presentation, or variations based on locality and facility type. Furthermore, ESHRE GPRs do not constitute or imply the endorsement, or favouring, of any of the included technologies by ESHRE.

Non-Coding RNAs as Biomarkers for Embryo Quality and Pregnancy Outcomes: A Systematic Review and Meta-Analysis

Despite advances in in vitro fertilization (IVF), there is still a lack of non-invasive and reliable biomarkers for selecting embryos with the highest developmental and implantation potential. Recently, small non-coding RNAs (sncRNAs) have been identified in biological fluids, and extracellular sncRNAs are explored as diagnostic biomarkers in the prediction of IVF outcomes. To determine the predictive role of sncRNAs in embryo quality and IVF outcomes, a systematic review and meta-analysis was performed. Articles were retrieved from PubMed, EMBASE, and Web of Science from 1990 to 31 July 2022. Eighteen studies that met the selection criteria were analyzed. In total, 22 and 47 different sncRNAs were found to be dysregulated in follicular fluid (FF) and embryo spent culture medium (SCM), respectively. MiR-663b, miR-454 and miR-320a in FF and miR-20a in SCM showed consistent dysregulation in two different studies. The meta-analysis indicated the potential predictive performance of sncRNAs as non-invasive biomarkers, with a pooled area under curve (AUC) value of 0.81 (95% CI 0.78, 0.844), a sensitivity of 0.79 (95% CI 0.72, 0.85), a specificity of 0.67 (95% CI 0.52, 0.79) and a diagnostic odds ratio (DOR) of 8 (95% CI 5, 12). Significant heterogeneity was identified among studies in sensitivity (I2  =  46.11%) and specificity (I2  =  89.73%). This study demonstrates that sncRNAs may distinguish embryos with higher developmental and implantation potentials. They can be promising non-invasive biomarkers for embryo selection in ART. However, the significant heterogeneity among studies highlights the demand for prospective multicenter studies with optimized methods and adequate sample sizes in the future.

Medical microrobots in reproductive medicine from the bench to the clinic

Medical microrobotics is an emerging field that aims at non-invasive diagnosis and therapy inside the human body through miniaturized sensors and actuators. Such microrobots can be tethered (e.g., smart microcatheters, microendoscopes) or untethered (e.g., cell-based drug delivery systems). Active motion and multiple functionalities, distinguishing microrobots from mere passive carriers and conventional nanomedicines, can be achieved through external control with physical fields such as magnetism or ultrasound. Here we give an overview of the key challenges in the field of assisted reproduction and how these new technologies could, in the future, enable assisted fertilization in vivo and enhance embryo implantation. As a case study, we describe a potential intervention in the case of recurrent embryo implantation failure, which involves the non-invasive delivery of an early embryo back to the fertilization site using magnetically-controlled microrobots. As the embryo will be in contact with the secretory oviduct fluid, it can develop under natural conditions and in synchrony with the endometrium preparation. We discuss the potential microrobot designs, including a proper selection of materials and processes, envisioning their translation from bench to animal studies and human medicine. Finally, we highlight regulatory and ethical considerations for bringing this technology to the clinic.

Translational Bioinformatics for Human Reproductive Biology Research: Examples, Opportunities and Challenges for a Future Reproductive Medicine

Since 1978, with the first IVF (in vitro fertilization) baby birth in Manchester (England), more than eight million IVF babies have been born throughout the world, and many new techniques and discoveries have emerged in reproductive medicine. To summarize the modern technology and progress in reproductive medicine, all scientific papers related to reproductive medicine, especially papers related to reproductive translational medicine, were fully searched, manually curated and reviewed. Results indicated whether male reproductive medicine or female reproductive medicine all have made significant progress, and their markers have experienced the progress from karyotype analysis to single-cell omics. However, due to the lack of comprehensive databases, especially databases collecting risk exposures, disease markers and models, prevention drugs and effective treatment methods, the application of the latest precision medicine technologies and methods in reproductive medicine is limited.