Embryo selection through artificial intelligence versus embryologists: a systematic review

Predictive model for live birth outcomes in single euploid frozen embryo transfers: a comparative analysis of logistic regression and machine learning approaches

PURPOSE

To develop and validate a predictive model for live birth (LB) outcomes in single euploid frozen embryo transfers (seFET) based on patient's characteristics and embryo parameters.

METHODS

A retrospective cohort study was performed including 1979 seFET performed between March 2017 and December 2023. Prediction models were built using logistic regression (LR), random forest classifier (RFC), support vector machines (SVM), and a gradient booster (XGBoost). Considered variables associated with LB outcomes were blastocyst expansion, blastocyst inner cell mass (ICM) and TE quality, day (D) of TE biopsy (D5, D6, and D7), female age and body mass index (BMI), distance from the uterine fundus at embryo transfer, endometrial preparation as natural cycles (NC) or hormonal replacement therapy (HRT), and endometrial thickness. Model performance was evaluated using area under the precision-recall curve and calibration metrics.

RESULTS

Variables that were negatively associated with LB rate were BMI (OR = 0.79 [0.64-0.96], P = 0.020 for overweight and OR = 0.76 [0.60-0.95], P = 0.015 for obese class I/II), ICM grade B (OR = 0.72 [0.57-0.90], P = 0.005) or C (OR = 0.21 [0.15-0.30], P < 0.001), TE grade C (OR = 0.32 [0.24-0.43], P < 0.001), and blastocyst biopsied on D6 (OR = 0.66 [0.55-0.80], P < 0.001 or D7 (OR = 0.19[0.09-0.37], P < 0.001). The LR model was the best in terms of overall classification performance (C-statistics: 0.626 ± 0.018 vs. 0.606 ± 0.018, 0.581 ± 0.018, 0.601 ± 0.017, LR vs. RFC, XGBoost, and SVM, respectively, P < 0.001). A prediction model of LB outcome was developed and is free to access: https://artfertilityclinics.shinyapps.io/ABLE/ .

CONCLUSION

LR demonstrated a stable validation performance and superior LB prediction, aiding as a predictive tool for patient counselling and assessing success in seFET cycles.

Deep learning classification integrating embryo images with associated clinical information from ART cycles

An advanced Artificial Intelligence (AI) model that leverages cutting-edge computer vision techniques to analyse embryo images and clinical data, enabling accurate prediction of clinical pregnancy outcomes in single embryo transfer procedures. Three AI models were developed, trained, and tested using a database comprised of a total of 1503 international treatment cycles (Thailand, Malaysia, and India): 1) A Clinical Multi-Layer Perceptron (MLP) for patient clinical data. 2) An Image Convolutional Neural Network (CNN) AI model using blastocyst images. 3) A fused model using a combination of both models. All three models were evaluated against their ability to predict clinical pregnancy and live birth. Each of the models were further assessed through a visualisation process where the importance of each data point clarified which clinical and embryonic features contributed the most to the prediction. The MLP model achieved a strong performance of 81.76% accuracy, 90% average precision and 0.91 AUC (Area Under the Curve). The CNN model achieved a performance of 66.89% accuracy, 74% average precision and 0.73 AUC. The Fusion model achieved 82.42% accuracy, 91% average precision and 0.91 AUC. From the visualisation process we found that female and male age to be the most clinical factors, whilst Trophectoderm to be the most important blastocyst feature. There is a gap in performance between the Clinical and Images model, which is expected due to the difficulty in predicting clinical pregnancy from just the blastocyst images. However, the Fusion AI model made more informed predictions, achieving better performance than separate models alone. This study demonstrates that AI for IVF application can increase prediction performance by integrating blastocyst images with patient clinical information.

The Role of Artificial Intelligence in Female Infertility Diagnosis: An Update

Female infertility is a multifaceted condition affecting millions of women worldwide, with causes ranging from hormonal imbalances and genetic predispositions to lifestyle and environmental factors. Traditional diagnostic approaches, such as hormonal assays, ultrasound imaging, and genetic testing, often require extensive time, resources, and expert interpretation. In recent years, artificial intelligence (AI) has emerged as a transformative tool in the field of reproductive medicine, offering advanced capabilities for improving the accuracy, efficiency, and personalization of infertility diagnosis and treatment. AI technologies demonstrate significant potential in analyzing vast and complex datasets, identifying hidden patterns, and providing data-driven insights that enhance clinical decision-making processes in assisted reproductive technologies (ART) services. This narrative review explores the current advancements in AI applications in female infertility diagnostics and therapeutics, highlighting key technological innovations, their clinical implications, and existing limitations. It also discusses the future potential of AI in revolutionizing reproductive healthcare. As AI-based technologies continue to evolve, their integration into reproductive medicine is expected to pave the way for more accessible, cost-effective, and personalized fertility care.

Deep learning applications for human embryo assessment using time-lapse imaging: scoping review

Background

The integration of deep learning (DL) and time-lapse imaging technologies offers new possibilities for improving embryo assessment and selection in clinical in vitro Fertilization (IVF).

Objectives

This scoping review aims to explore the range of deep learning model applications in the evaluation and selection of embryos monitored through time-lapse imaging systems.

Methods

A total of 6 electronic databases (Scopus, MEDLINE, EMBASE, ACM Digital Library, IEEE Xplore, and Google Scholar) were searched for peer-reviewed literature published before May 2024. We adhered to the PRISMA guidelines for reporting scoping reviews.

Results

Out of the 773 articles reviewed, 77 met the inclusion criteria. Over the past four years, the use of DL in embryo analysis has increased rapidly. The primary applications of DL in the reviewed studies included predicting embryo development and quality (61%, n = 47) and forecasting clinical outcomes, such as pregnancy and implantation (35%, n = 27). The number of embryos involved in the studies exhibited significant variation, with a mean of 10,485 (SD = 35,593) and a range from 20 to 249,635 embryos. A variety of data types have been used, namely images of blastocyst-stage embryos (47%, n = 36), followed by combined images of cleavage and blastocyst stages (23%, n = 18). Most of the studies did not provide maternal age details (82%, n = 63). Convolutional neural networks (CNNs) were the predominant deep learning architecture used, accounting for 81% (n = 62) of the studies. All studies utilized time-lapse video images (100%) as training data, while some also incorporated demographics, clinical and reproductive histories, and IVF cycle parameters. Most studies utilized accuracy as the discriminative measure (58%, n = 45).

Conclusion

Our results highlight the diverse applications and potential of deep learning in clinical IVF and suggest directions for future advancements in embryo evaluation and selection techniques.

External validation of a fully automated evaluation tool: a retrospective analysis of 68,471 scored embryos

OBJECTIVE

To externally validate a fully automated embryo classification system for in vitro fertilization (IVF) treatments.

DESIGN

Retrospective cohort study.

SUBJECTS

A total of 6,434 patients undergoing 7,352 IVF treatments contributed 70,456 embryos.

EXPOSURE

Embryos were evaluated by conventional morphology and retrospectively scored using a fully automated deep learning-based algorithm across conventional IVF, oocyte donation, and preimplantation genetic testing for aneuploidy (PGT-A) cycles.

MAIN OUTCOME MEASURES

The primary outcomes were implantation and live birth, including odds ratios (ORs) from generalized estimating equation models. Secondary outcomes were embryo morphology, euploidy, and miscarriage. Exploratory outcomes included a comparison between conventional methodology and artificial intelligence algorithm with areas under the receiver operating characteristics curves (AUCs), agreement degree between artificial intelligence and embryologists, Cohen's Kappa coefficient, and relative risk.

RESULTS

Implantation and live birth rates increased as the automatic embryo scores increased. The generalized estimating equation model, controlling for confounders, showed that the automatic score was associated with an OR of 1.31 (95% confidence interval [CI], 1.25-1.36) for implantation in treatments using oocytes from patients and an OR of 1.17 (95% CI, 1.14-1.20) in the oocyte donation program, with no significant association with PGT-A treatments. For live birth, the ORs were 1.27 (95% CI, 1.21-1.33) for patients, 1.16 (95% CI, 1.13-1.19) for donors, and 1.05 (95% CI, 1-1.10) for PGT-A cycles. The average score was higher in embryos with better morphology, in euploid embryos compared with aneuploid embryos, and in embryos that resulted in a full-term pregnancy compared with those that miscarried. Concordance between the highest-scoring embryo and the embryo with the best conventional morphology was 71.4% (95% CI, 67.7%-75.0%) in treatments with patient oocytes and 61.0% (95% CI, 58.6%-63.4%) in the oocyte donation program. Overall, the Cohen's Kappa coefficient was 0.63. The automatic embryo score showed similar AUCs to conventional morphology, although implantation was higher when the transferred embryo matched the highest-scoring embryo from each cohort (57.36% vs. 49.98%). Relative risk indicated a 1.14-fold increase in implantation likelihood when the top-ranked embryo was transferred.

CONCLUSIONS

A fully automated embryo scoring system effectively ranked embryos based on their potential for implantation and live birth. The performance of the conventional methodology was comparable to that of the artificial intelligence-based technology; however, better clinical outcomes were observed when the highest-scoring embryo in the cohort was transferred.

Do we still need embryologists?

IVF has given scientists a unique role, one probably unparalleled in other medical disciplines. This role has become increasingly more impactful due to the introduction of breakthrough laboratory interventions, such as intracytoplasmic sperm injection and cryopreservation. More recently, incessant advances in automation, information technology and artificial intelligence have started to transform diverse biomedical disciplines. In IVF, relevant examples are novel equipment that can automatically perform embryo assessment, patient/sample identification, vitrification and sperm manipulation/selection/analysis. This has questioned the role of the embryologist. However, the introduction of novel technology is not straightforward; it generates numerous challenges. Which manual interventions should be automated and why? Do machines perform better than humans? Does automation involve higher treatment costs? At the same time, certain highly intellectual activities, such as the integration of novel categories of data and their interpretation, formulation of novel key performance indicators, generation of novel educational and training contents and enhancement and collaborative research, remain human prerogatives. Therefore, while it is to be expected that direct human intervention will be partly replaced by automated devices, we can envisage that the embryologist's role will not become extinct, but will evolve in new forms. Ideally, this change should be guided by principles safeguarding the ethics of medicine and human activity.

Artificial intelligence in assisted reproductive technology: separating the dream from reality

This paper critically reviews the role of artificial intelligence (AI) in assisted reproductive technology (ART), a nascent field that has emerged over the last decade. While AI holds immense promise for enhancing IVF efficiency, standardization, and outcomes, its current trajectory reveals significant challenges. Much of the recent literature presents variations on established methodologies rather than groundbreaking advancements, with many studies lacking clear clinical applications or outcome-driven validations. Moreover, the growing enthusiasm for AI in ART is often accompanied by undue hype that obscures its realistic potential and fosters inflated expectations. Despite these limitations, AI-driven innovations such as advanced image analysis, personalized protocols, and automation of embryology workflows are beginning to show value. Machine learning algorithms and robotics may help address inefficiencies, alleviate staff shortages, and improve decision-making in the IVF laboratory. However, progress is tempered by drawbacks including ethical concerns, limited transparency in AI systems, and regulatory impediments. Data-sharing barriers in our field hinder AI tool development significantly. Energy-intensive computational processes and expanding data centers also raise sustainability concerns, underscoring the need for environmentally responsible development. As the field evolves, it must emphasize rigorous validation, collaborative data frameworks, and alignment with the needs of ART practitioners and patients.

Merging synthetic and real embryo data for advanced AI predictions

Accurate embryo morphology assessment is essential in assisted reproductive technology for selecting the most viable embryo. Artificial intelligence has the potential to enhance this process. However, the limited availability of embryo data presents challenges for training deep learning models. To address this, we trained two generative models using two datasets-one we created and made publicly available, and one existing public dataset-to generate synthetic embryo images at various cell stages, including 2-cell, 4-cell, 8-cell, morula, and blastocyst. These were combined with real images to train classification models for embryo cell stage prediction. Our results demonstrate that incorporating synthetic images alongside real data improved classification performance, with the model achieving 97% accuracy compared to 94.5% when trained solely on real data. This trend remained consistent when tested on an external Blastocyst dataset from a different clinic. Notably, even when trained exclusively on synthetic data and tested on real data, the model achieved a high accuracy of 92%. Furthermore, combining synthetic data from both generative models yielded better classification results than using data from a single generative model. Four embryologists evaluated the fidelity of the synthetic images through a Turing test, during which they annotated inaccuracies and offered feedback. The analysis showed the diffusion model outperformed the generative adversarial network, deceiving embryologists 66.6% versus 25.3% and achieving lower Fréchet inception distance scores.

The perception of artificial intelligence and infertility care among patients undergoing fertility treatment

PURPOSE

To characterize the opinions of patients undergoing infertility treatment on the use of artificial intelligence (AI) in their care.

METHODS

Patients planning or undergoing in vitro fertilization (IVF) or frozen embryo transfers were invited to complete an anonymous electronic survey from April to June 2024. The survey collected demographics, technological affinity, general perception of AI, and its applications to fertility care. Patient-reported trust of AI compared to a physician for fertility care (e.g. gamete selection, gonadotropin doing, and stimulation length) were analyzed. Descriptive statistics were calculated, and subgroup analyses by age, occupation, and parity were performed. Chi-squared tests were used to compare categorical variables.

RESULTS

A total of 200 patients completed the survey and were primarily female (n = 193/200) and of reproductive age (mean 37 years). Patients were well educated with high technological affinity. Respondents were familiar with AI (93%) and generally supported its use in medicine (55%), but fewer trusted AI-informed reproductive care (46%). More patients disagreed (37%) that AI should be used to determine gonadotropin dose or stimulation length compared to embryo selection (26.5%; p = 0.01). In the setting of disagreement between physician and AI recommendation, patients preferred the physician-based recommendation in all treatment-related decisions. However, a larger proportion favored AI recommendations for gamete (22%) and embryo (14.5%) selection, compared to gonadotropin dosing (6.5%) or stimulation length (7.0%). Most would not be willing to pay more for AI-informed fertility care.

CONCLUSIONS

In this highly educated infertile population familiar with AI, patients still prefer physician-based recommendations compared with AI.

FertilitY Predictor-a machine learning-based web tool for the prediction of assisted reproduction outcomes in men with Y chromosome microdeletions

PURPOSE

Y chromosome microdeletions (YCMD) are a common cause of azoospermia and oligozoospermia in men. Herein, we developed a machine learning-based web tool to predict sperm retrieval rates and success rates of assisted reproduction (ART) in men with YCMD.

METHODS

Data on ART outcomes of men with YCMD who underwent ART were extracted from published studies by performing a systematic review. This data was used to develop a web-based predictive algorithm using machine learning.

RESULTS

FertilitY Predictor classifies the type of YCMD into AZFa, AZFb, AZFc, their combinations, and gr/gr deletions based on the genetic markers as input. Further, it predicts the probability of sperm retrieval, fertilization rate, clinical pregnancy rate, and live birth rate based on the type of YCMD. Validation studies demonstrated its high accuracy and predictability for sperm retrieval, clinical pregnancy rates, and live birth rates. The tool predicts that men with deletions have a chance of sperm retrieval that varies with type of deletions, the clinical pregnancy rates and live birth rates are lower in men with AZF deletions. A trial version of the tool is available at http://fertilitypredictor.sbdaresearch.in .

CONCLUSIONS

FertilitY Predictor allows users to classify AZFa, AZFb, AZFc, and gr/gr deletions and also predict the outcomes of ART based on the type of deletions.

TRIAL REGISTRATION

PROSPERO (CRD42022311738).

Could metabolic imaging and artificial intelligence provide a novel path to non-invasive aneuploidy assessments? A certain clinical need

Pre-implantation genetic testing for aneuploidy (PGT-A) via embryo biopsy helps in embryo selection by assessing embryo ploidy. However, clinical practice needs to consider the invasive nature of embryo biopsy, potential mosaicism, and inaccurate representation of the entire embryo. This creates a significant clinical need for improved diagnostic practices that do not harm embryos or raise treatment costs. Consequently, there has been an increasing focus on developing non-invasive technologies to enhance embryo selection. Such innovations include non-invasive PGT-A, artificial intelligence (AI) algorithms, and non-invasive metabolic imaging. The latter measures cellular metabolism through autofluorescence of metabolic cofactors. Notably, hyperspectral microscopy and fluorescence lifetime imaging microscopy (FLIM) have revealed unique metabolic activity signatures in aneuploid embryos and human fibroblasts. These methods have demonstrated high accuracy in distinguishing between euploid and aneuploid embryos. Thus, this review discusses the clinical challenges associated with PGT-A and emphasizes the need for novel solutions such as metabolic imaging. Additionally, it explores how aneuploidy affects cell behaviour and metabolism, offering an opinion perspective on future research directions in this field of research.

Novel application of metabolic imaging of early embryos using a light-sheet on-a-chip device: a proof-of-concept study

STUDY QUESTION

Is it feasible to safely determine metabolic imaging signatures of nicotinamide adenine dinucleotide [NAD(P)H] associated auto-fluorescence in early embryos using a light-sheet on-a-chip approach?

SUMMARY ANSWER

We developed an optofluidic device capable of obtaining high-resolution 3D images of the NAD(P)H autofluorescence of live mouse embryos using a light-sheet on-a-chip device as a proof-of-concept.

WHAT IS KNOWN ALREADY

Selecting the most suitable embryos for implantation and subsequent healthy live birth is crucial to the success rate of assisted reproduction and offspring health. Besides morphological evaluation using optical microscopy, a promising alternative is the non-invasive imaging of live embryos to establish metabolic activity performance. Indeed, in recent years, metabolic imaging has been investigated using highly advanced microscopy technologies such as fluorescence-lifetime imaging and hyperspectral microscopy.

STUDY DESIGN, SIZE, DURATION

The potential safety of the system was investigated by assessing the development and viability of live embryos after embryo culture for 67 h post metabolic imaging at the two-cell embryo stage (n = 115), including a control for culture conditions and sham controls (system non-illuminated). Embryo quality of developed blastocysts was assessed by immunocytochemistry to quantify trophectoderm and inner mass cells (n = 75). Furthermore, inhibition of metabolic activity (FK866 inhibitor) during embryo culture was also assessed (n = 18).

PARTICIPANTS/MATERIALS, SETTING, METHODS

The microstructures were fabricated following a standard UV-photolithography process integrating light-sheet fluorescence microscopy into a microfluidic system, including on-chip micro-lenses to generate a light-sheet at the centre of a microchannel. Super-ovulated F1 (CBA/C57Bl6) mice were used to produce two-cell embryos and embryo culture experiments. Blastocyst formation rates and embryo quality (immunocytochemistry) were compared between the study groups. A convolutional neural network (ResNet 34) model using metabolic images was also trained.

MAIN RESULTS AND THE ROLE OF CHANCE

The optofluidic device was capable of obtaining high-resolution 3D images of live mouse embryos that can be linked to their metabolic activity. The system's design allowed continuous tracking of the embryo location, including high control displacement through the light-sheet and fast imaging of the embryos (<2 s), while keeping a low dose of light exposure (16 J · cm-2 and 8 J · cm-2). Optimum settings for keeping sample viability showed that a modest light dosage was capable of obtaining 30 times higher signal-noise-ratio images than images obtained with a confocal system (P < 0.00001; t-test). The results showed no significant differences between the control, illuminated and non-illuminated embryos (sham control) for embryo development as well as embryo quality at the blastocyst stage (P > 0.05; Yate's chi-squared test). Additionally, embryos with inhibited metabolic activity showed a decreased blastocyst formation rate of 22.2% compared to controls, as well as a 47% reduction in metabolic activity measured by metabolic imaging (P < 0.0001; t-test). This indicates that the optofluidic device was capable of producing metabolic images of live embryos by measuring NAD(P)H autofluorescence, allowing a novel and affordable approach. The obtained metabolic images of two-cell embryos predicted blastocyst formation with an AUC of 0.974.

LARGE SCALE DATA

N/A.

LIMITATIONS, REASONS FOR CAUTION

The study was conducted using a mouse model focused on early embryo development assessing illumination at the two-cell stage. Further safety studies are required to assess the safety and use of 405 nm light at the blastocyst stage by investigating any potential negative impact on live birth rates, offspring health, aneuploidy rates, mutational load, changes in gene expression, and/or effects on epigenome stability in newborns.

WIDER IMPLICATIONS OF THE FINDINGS

This light-sheet on-a-chip approach is novel and after rigorous safety studies and a roadmap for technology development, potential future applications could be developed for ART. The overall cost-efficient fabrication of the device will facilitate scalability and integration into future devices if full-safety application is demonstrated.

STUDY FUNDING/COMPETING INTEREST(S)

This work was partially supported by an Ideas Grant (no 2004126) from the National Health and Medical Research Council (NHMRC), by the Education Program in Reproduction and Development (EPRD), Department Obstetrics and Gynaecology, Monash University, and by the Department of Mechanical and Aerospace Engineering, Faculty of Engineering, Monash University. The authors E.V-O, R.N., V.J.C., A.N., and F.H. have applied for a patent on the topic of this technology (PCT/AU2023/051132). The remaining authors have nothing to disclose.

Artificial Intelligence in Human Reproduction

The use of artificial intelligence (AI) in human reproduction is a rapidly evolving field with both exciting possibilities and ethical considerations. This technology has the potential to improve success rates and reduce the emotional and financial burden of infertility. However, it also raises ethical and privacy concerns. This paper presents an overview of the current and potential applications of AI in human reproduction. It explores the use of AI in various aspects of reproductive medicine, including fertility tracking, assisted reproductive technologies, management of pregnancy complications, and laboratory automation. In addition, we discuss the need for robust ethical frameworks and regulations to ensure the responsible and equitable use of AI in reproductive medicine.

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.

Artificial Intelligence in IVF Laboratories: Elevating Outcomes Through Precision and Efficiency

Incorporating artificial intelligence (AI) into in vitro fertilization (IVF) laboratories signifies a significant advancement in reproductive medicine. AI technologies, such as neural networks, deep learning, and machine learning, promise to enhance quality control (QC) and quality assurance (QA) through increased accuracy, consistency, and operational efficiency. This comprehensive review examines the effects of AI on IVF laboratories, focusing on its role in automating processes such as embryo and sperm selection, optimizing clinical outcomes, and reducing human error. AI's data analysis and pattern recognition capabilities offer valuable predictive insights, enhancing personalized treatment plans and increasing success rates in fertility treatments. However, integrating AI also brings ethical, regulatory, and societal challenges, including concerns about data security, algorithmic bias, and the human-machine interface in clinical decision-making. Through an in-depth examination of current case studies, advancements, and future directions, this manuscript highlights how AI can revolutionize IVF by standardizing processes, improving patient outcomes, and advancing the precision of reproductive medicine. It underscores the necessity of ongoing research and ethical oversight to ensure fair and transparent applications in this sensitive field, assuring the responsible use of AI in reproductive medicine.

Deep learning versus manual morphology-based embryo selection in IVF: a randomized, double-blind noninferiority trial

To assess the value of deep learning in selecting the optimal embryo for in vitro fertilization, a multicenter, randomized, double-blind, noninferiority parallel-group trial was conducted across 14 in vitro fertilization clinics in Australia and Europe. Women under 42 years of age with at least two early-stage blastocysts on day 5 were randomized to either the control arm, using standard morphological assessment, or the study arm, employing a deep learning algorithm, intelligent Data Analysis Score (iDAScore), for embryo selection. The primary endpoint was a clinical pregnancy rate with a noninferiority margin of 5%. The trial included 1,066 patients (533 in the iDAScore group and 533 in the morphology group). The iDAScore group exhibited a clinical pregnancy rate of 46.5% (248 of 533 patients), compared to 48.2% (257 of 533 patients) in the morphology arm (risk difference -1.7%; 95% confidence interval -7.7, 4.3; P = 0.62). This study was not able to demonstrate noninferiority of deep learning for clinical pregnancy rate when compared to standard morphology and a predefined prioritization scheme. Australian New Zealand Clinical Trials Registry (ANZCTR) registration: 379161 .

Non-invasive prediction of human embryonic ploidy using artificial intelligence: a systematic review and meta-analysis

Background

Embryonic ploidy is critical for the success of embryo transfer. Currently, preimplantation genetic testing for aneuploidy (PGT-A) is the gold standard for detecting ploidy abnormalities. However, PGT-A has several inherent limitations, including invasive biopsy, high economic burden, and ethical constraints. This paper provides the first comprehensive systematic review and meta-analysis of the performance of artificial intelligence (AI) algorithms using embryonic images for non-invasive prediction of embryonic ploidy.

Methods

Comprehensive searches of studies that developed or utilized AI algorithms to predict embryonic ploidy from embryonic imaging, published up until August 10, 2024, across PubMed, MEDLINE, Embase, IEEE, SCOPUS, Web of Science, and the Cochrane Central Register of Controlled Trials were performed. Studies with prospective or retrospective designs were included without language restrictions. The summary receiver operating characteristic curve, along with pooled sensitivity and specificity, was estimated using a bivariate random-effects model. The risk of bias and study quality were evaluated using the QUADAS-AI tool. Heterogeneity was quantified using the inconsistency index (I 2 ), derived from Cochran's Q test. Predefined subgroup analyses and bivariate meta-regression were conducted to explore potential sources of heterogeneity. This study was registered with PROSPERO (CRD42024500409).

Findings

Twenty eligible studies were identified, with twelve studies included in the meta-analysis. The pooled sensitivity, specificity, and area under the curve of AI for predicting embryonic euploidy were 0.71 (95% CI: 0.59-0.81), 0.75 (95% CI: 0.69-0.80), and 0.80 (95% CI: 0.76-0.83), respectively, based on a total of 6879 embryos (3110 euploid and 3769 aneuploid). Meta-regression and subgroup analyses identified the type of AI-driven decision support system, external validation, risk of bias, and year of publication as the primary contributors to the observed heterogeneity. There was no evidence of publication bias.

Interpretation

Our findings indicate that AI algorithms exhibit promising performance in predicting embryonic euploidy based on embryonic imaging. Although the current AI models developed cannot entirely replace invasive methods for determining embryo ploidy, AI demonstrates promise as an auxiliary decision-making tool for embryo selection, particularly for individuals who are unable to undergo PGT-A. To enhance the quality of future research, it is essential to overcome the specific challenges and limitations associated with AI studies in reproductive medicine.

Funding

This work was supported by the National Key R&D Program of China (2022YFC2702905), the Shengjing Freelance Researcher Plan of Shengjing Hospital and the 345 talent project of Shengjing Hospital.

Optimizing single blastocyst selection: the role of day 3 embryo morphology in vitrified-warmed blastocyst transfer cycles

RESEARCH QUESTION

Can day 3 embryo morphology serve as an independent criterion for optimal single blastocyst selection?

DESIGN

This retrospective, single-centre cohort study included 1517 single vitrified-warmed blastocyst transfer (SVBT) cycles conducted between October 2019 and July 2022. The live birth rate (LBR) and other clinical outcomes of SVBT cycles were evaluated, considering both good-quality and non-good-quality day 3 embryos. The associations of day 3 morphological characteristics, encompassing number of blastomeres and embryo grade, were assessed. Multivariable analyses were undertaken using multiple models adjusted for day of blastocyst development and blastocyst grade.

RESULTS

Blastocysts from good-quality day 3 embryos had significantly higher LBR compared with those from non-good-quality embryos for both day 5 (51.5% versus 42.9%; P = 0.013) and day 6 (25.1% versus 17.6%; P = 0.018) blastocysts. LBR did not differ significantly with number of blastomeres on day 3, regardless of day of blastocyst development (day 5/6) or blastocyst grade. LBR varied significantly by day 3 embryo grade for both day 5 (48.0%, 51.5%, 46.6% and 32.7% for grades I, II, III and IV-V; P = 0.005) and day 6 (41.5%, 23.6%, 15.9% and 16.1% for grades I, II, III and IV-V; P = 0.001) blastocysts. Multivariable logistic regression revealed that non-good-quality embryos and lower morphological grade (IV-V) on day 3 were significantly and negatively correlated with LBR, while the number of blastomeres on day 3 was not an independent factor.

CONCLUSIONS

When selecting blastocysts of equal quality for SVBT cycles, those with higher day 3 morphological scores are preferred. Day 3 morphological evaluation is a valuable supplement to conventional selection methods.

Quantitative Standardized Expansion Assay: An Artificial Intelligence-Powered Morphometric Description of Blastocyst Expansion and Zona Thinning Dynamics

Artificial intelligence applied to time-lapse microscopy may revolutionize embryo selection in IVF by automating data collection and standardizing the assessments. In this context, blastocyst expansion dynamics, although being associated with reproductive fitness, have been poorly studied. This retrospective study (N = 2184 blastocysts from 786 cycles) exploited both technologies to picture the association between embryo and inner-cell-mass (ICM) area in µm2, the ICM/Trophectoderm ratio, and the zona pellucida thickness in µm (zp-T) at sequential blastocyst expansion stages, with (i) euploidy and (ii) live-birth per transfer (N = 548 transfers). A quantitative-standardized-expansion-assay (qSEA) was also set-up; a novel approach involving automatic annotations of all expansion metrics every 30 min across 5 h following blastulation. Multivariate regressions and ROC curve analyses were conducted. Aneuploid blastocysts were slower, expanded less and showed thicker zp. The qSEA outlined faster and more consistent zp thinning processes among euploid blastocysts, being more or as effective as the embryologists in ranking euploid embryo as top-quality of their cohorts in 69% of the cases. The qSEA also outlined faster and more consistent blastocyst expansion and zp thinning dynamics among euploid implanted versus not implanted blastocysts, disagreeing with embryologists' priority choice in about 50% of the cases. In conclusion, qSEA is a promising objective, quantitative, and user-friendly strategy to predict embryo competence that now deserves prospective validations.

Comparative outcomes of AI-assisted ChatGPT and face-to-face consultations in infertility patients: a cross-sectional study

BACKGROUND

With the advent of artificial intelligence (AI) in healthcare, digital platforms like ChatGPT offer innovative alternatives to traditional medical consultations. This study seeks to understand the comparative outcomes of AI-assisted ChatGPT consultations and conventional face-to-face interactions among infertility patients.

METHODS

A cross-sectional study was conducted involving 120 infertility patients, split evenly between those consulting via ChatGPT and traditional face-to-face methods. The primary outcomes assessed were patient satisfaction, understanding, and consultation duration. Secondary outcomes included demographic information, clinical history, and subsequent actions post-consultation.

RESULTS

While both consultation methods had a median age of 34 years, patients using ChatGPT reported significantly higher satisfaction levels (median 4 out of 5) compared to face-to-face consultations (median 3 out of 5; p < 0.001). The ChatGPT group also experienced shorter consultation durations, with a median difference of 12.5 minutes (p < 0.001). However, understanding, demographic distributions, and subsequent actions post-consultation were comparable between the two groups.

CONCLUSIONS

AI-assisted ChatGPT consultations offer a promising alternative to traditional face-to-face consultations in assisted reproductive medicine. While patient satisfaction was higher and consultation durations were shorter with ChatGPT, further studies are required to understand the long-term implications and clinical outcomes associated with AI-driven medical consultations. Key Messages What is already known on this topic:  Artificial intelligence (AI) applications, such as ChatGPT, have shown potential in various healthcare settings, including primary care and mental health support. Infertility is a significant global health issue that requires extensive consultations, often facing challenges such as long waiting times and varied patient satisfaction. Previous studies suggest that AI can offer personalized care and immediate feedback, but its efficacy compared with traditional consultations in reproductive medicine was not well-studied. What this study adds:  This study demonstrates that AI-assisted ChatGPT consultations result in significantly higher patient satisfaction and shorter consultation durations compared with traditional face-to-face consultations among infertility patients. Both consultation methods were comparable in terms of patient understanding, demographic distributions, and subsequent actions postconsultation. How this study might affect research, practice, or policy:  The findings suggest that AI-driven consultations could serve as an effective and efficient alternative to traditional methods, potentially reducing consultation times and improving patient satisfaction in reproductive medicine. Further research could explore the long-term impacts and broader applications of AI in clinical settings, influencing future healthcare practices and policies toward integrating AI technologies.

Artificial intelligence and porcine breeding

Livestock management is evolving into a new era, characterized by the analysis of vast quantities of data (Big Data) collected from both traditional breeding methods and new technologies such as sensors, automated monitoring system, and advanced analytics. Artificial intelligence (A-In), which refers to the capability of machines to mimic human intelligence, including subfields like machine learning and deep learning, is playing a pivotal role in this transformation. A wide array of A-In techniques, successfully employed in various industrial and scientific contexts, are now being integrated into mainstream livestock management practices. In the case of swine breeding, while traditional methods have yielded considerable success, the increasing amount of information requires the adoption of new technologies such as A-In to drive productivity, enhance animal welfare, and reduce environmental impact. Current findings suggest that these techniques have the potential to match or exceed the performance of traditional methods, often being more scalable in terms of efficiency and sustainability within the breeding industry. This review provides insights into the application of A-In in porcine breeding, from the perspectives of both sows (including welfare and reproductive management) and boars (including semen quality and health), and explores new approaches which are already being applied in other species.

Bovine embryo production in vitro: evolution of culture media and commercial perspectives

In vitro produced embryos exhibit lower viability compared to their in vivo counterparts. Mammalian preimplantation embryos have the ability to reach the blastocyst stage in diverse culture media, showcasing considerable metabolic adaptability, which complicates the identification of optimal developmental conditions. Despite embryos successfully progressing to the blastocyst stage, adaptation to suboptimal culture environments may jeopardize blastocyst viability, cryotolerance, and implantation potential. Enhancing our capacity to support preimplantation embryonic development in vitro requires a deeper understanding of fundamental embryo physiology, including preferred metabolic substrates and pathways utilized by high-quality embryos. Armed with this knowledge, it becomes achievable to optimize culture conditions to support normal, in vivo-like embryo physiology, mitigate adaptive stress, and enhance viability. The objective of this review is to summarize the evolution of culture media for bovine embryos, highlighting significant milestones and remaining challenges.

Can time-lapse culture combined with artificial intelligence improve ongoing pregnancy rates in fresh transfer cycles of single cleavage stage embryos?

Purpose

With the rapid advancement of time-lapse culture and artificial intelligence (AI) technologies for embryo screening, pregnancy rates in assisted reproductive technology (ART) have significantly improved. However, clinical pregnancy rates in fresh cycles remain dependent on the number and type of embryos transferred. The selection of embryos with the highest implantation potential is critical for embryologists and influences transfer strategies in fertility centers. The superiority of AI over traditional morphological scoring for ranking cleavage-stage embryos based on their implantation potential remains controversial.

Methods

This retrospective study analyzed 105 fresh embryo transfer cycles at the Centre for Reproductive Medicine from August 2023 to March 2024, following IVF/ICSI treatment at the cleavage stage. All embryos were cultured using time-lapse technology and scored using an automated AI model (iDAScore V2.0). Embryos were categorized into three groups based on the iDAScore V2.0: Group A (8 cells, iDA: 1.0-5.7); Group B (8 cells, iDA: 5.8-8.0); and Group C (>8 cells, iDA: 5.8-8.0). Clinical treatment outcomes, embryonic development, and pregnancy outcomes were analyzed and compared across the groups.

Results

Baseline characteristics such as patient age, AMH levels, AFC, and basal sex hormones showed no significant differences among the three groups (p > 0.05). The iDAscores were significantly higher in Group C (7.3 ± 0.5) compared to Group B (6.7 ± 0.5) and the iDAscores were significantly higher in Group B (6.7 ± 0.5) compared to Group A (4.8 ± 1.0) (p < 0.001).The mean number of high-quality embryos was highest in Group C (4.7 ± 3.0), followed by Group B (3.6 ± 1.7) and Group A (2.1 ± 1.2) (p < 0.001). There was no statistical difference (p = 0.392) in the ongoing pregnancy rate for single cleavage-stage transfers between Group B (54.5%, 30/55) and Group A (38.1%, 8/21), although there was a tendency for Group B to be higher.

Conclusion

Combining time-lapse culture with AI scoring may enhance ongoing pregnancy rates in single cleavage-stage fresh transfer cycles.

The potential of self- supervised learning in embryo selection for IVF success

How to select the "best" embryo for transfer is a long-standing question in clinical in vitro fertilization (IVF). Wang et al. proposed a multi-modal self-supervised learning framework for human embryo selection with a high accuracy and generalization ability.

FERTILTY CARE IN LOW AND MIDDLE INCOME COUNTRIES: Fertility care in low- and middle-income countries

Infertility affects millions worldwide, with significant medical, financial, and emotional challenges, particularly in low- and middle-income countries (LMICs). Cultural, religious, financial, and gender-related barriers hinder access to treatment, exacerbating social and economic consequences, especially for women. Despite its prevalence, infertility often remains overlooked due to competing health priorities. However, global initiatives recognise infertility as a reproductive health concern, advocating for universal access to high-quality fertility care. In LMICs, limited resources and infrastructure impede access to treatment, prompting people to turn to alternative, often ineffective, non-biomedical solutions. Addressing these challenges requires implementing affordable fertility care services tailored to local contexts, supported by political commitment and community engagement. Emerging technologies offer promising solutions, but comprehensive education and training programs are essential for their effective implementation. By integrating fertility care into broader health policies and fostering partnerships, we can ensure equitable access to infertility treatment and support reproductive health worldwide.

Preimplantation genetic testing: A narrative review

Preimplantation genetic testing (PGT) is a diagnostic procedure that has become a powerful complement to assisted reproduction techniques. PGT has numerous indications, and there is a wide range of techniques that can be used, each with advantages and limitations that should be considered before choosing the more adequate one. In this article, it is reviewed the indications for PGT, biopsy and diagnostic technologies, along with their evolution, while also broaching new emerging methods.

The Role of One-Carbon Metabolism and Methyl Donors in Medically Assisted Reproduction: A Narrative Review of the Literature

One-carbon (1-C) metabolic deficiency impairs homeostasis, driving disease development, including infertility. It is of importance to summarize the current evidence regarding the clinical utility of 1-C metabolism-related biomolecules and methyl donors, namely, folate, betaine, choline, vitamin B12, homocysteine (Hcy), and zinc, as potential biomarkers, dietary supplements, and culture media supplements in the context of medically assisted reproduction (MAR). A narrative review of the literature was conducted in the PubMed/Medline database. Diet, ageing, and the endocrine milieu of individuals affect both 1-C metabolism and fertility status. In vitro fertilization (IVF) techniques, and culture conditions in particular, have a direct impact on 1-C metabolic activity in gametes and embryos. Critical analysis indicated that zinc supplementation in cryopreservation media may be a promising approach to reducing oxidative damage, while female serum homocysteine levels may be employed as a possible biomarker for predicting IVF outcomes. Nonetheless, the level of evidence is low, and future studies are needed to verify these data. One-carbon metabolism-related processes, including redox defense and epigenetic regulation, may be compromised in IVF-derived embryos. The study of 1-C metabolism may lead the way towards improving MAR efficiency and safety and ensuring the lifelong health of MAR infants.

Diagnostic or prognostic? Decoding the role of embryo selection on in vitro fertilization treatment outcomes

In this review, we take a fresh look at embryo assessment and selection methods from the perspective of diagnosis and prognosis. On the basis of a systematic search in the literature, we examined the evidence on the prognostic value of different embryo assessment methods, including morphological assessment, blastocyst culture, time-lapse imaging, artificial intelligence, and preimplantation genetic testing for aneuploidy.

Predicting implantation by using dual AI system incorporating three-dimensional blastocyst image and conventional embryo evaluation parameters-A pilot study

Purpose

To investigate the usefulness of an original dual artificial intelligence (AI) system, in which the first AI system eliminates the background of sliced tomographic blastocyst images, then the second AI system predicts implantation success using three-dimensional (3D) reconstructed images of the sequential images and conventional embryo evaluation parameters (CEE) such as maternal age.

Methods

Patients (from June 2022 to July 2023) could opt out and there was additional information on the Web site of the clinic. Implantation and non-implantation cases numbered 458 and 519, respectively. A total of 10 747 tomographic images of the blastocyst in a time-lapse incubator system with the CEE were obtained.

Results

The statistic values by the dual AI system were 0.774 ± 0.033 (mean ± standard error) for area under the characteristic curve, 0.727 for sensitivity, 0.719 for specificity, 0.727 for predictive value of positive test, 0.719 predictive value of negative test, and 0.723 for accuracy, respectively.

Conclusions

The usefulness of the dual AI system in predicting implantation of blastocyst in handling 3D data with conventional embryo evaluation information was demonstrated. This system may be a feasible option in clinical practice.

Preimplantation genetic testing: A remarkable history of pioneering, technical challenges, innovations, and ethical considerations

Preimplantation genetic testing (PGT) has emerged as a powerful companion to assisted reproduction technologies. The origins and history of PGT are reviewed here, along with descriptions of advances in molecular assays and sampling methods, their capabilities, and their applications in preventing genetic diseases and enhancing pregnancy outcomes. Additionally, the potential for increasing accuracy and genome coverage is considered, as well as some of the emerging ethical and legislative considerations related to the expanding capabilities of PGT.

Heterogeneity of nucleolar morphology in four-cell mouse embryos after IVF: association with developmental potential

In mammals, around fertilization, the nucleolus of embryos transforms into the nucleolus precursor bodies (NPBs), which continue to mature until the blastocyst stage, leading to distinct morphological changes. In our study, we observed two types of nucleolar morphology in mouse in vitro fertilized embryos at the four-cell stage, which we refer to single nucleolus (SN) and multiple nucleoli (MN). To visualize nucleolar morphology, four-cell embryos were immunostained with anti-NOPP140 antibody. These embryos were categorized into five types based on the number of blastomeres carrying SN: SN4/MN0, SN3/MN1, SN2/MN2, SN1/MN3, and SN0/MN4, with percentages of 13, 27, 21, 23 and 9, respectively. Next, using a light microscope, we divided the four-cell in vitro fertilized embryos without fixation into two groups: those with at least two blastomeres displaying SN (SN embryos) and those without (MN embryos). Notably, significantly more SN embryos developed into blastocysts and offspring at 18.5 dpc compared with MN embryos. Furthermore, SN embryos displayed a higher NANOG-positive cell number at the blastocyst stage, significantly lower body and placental weights, resulting in a higher fetal/placental ratio. These findings suggest a close association between nucleolar state at the four-cell stage and subsequent developmental potential.