Blastocyst quality and reproductive and perinatal outcomes: a multinational multicentre observational study

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.

The Istanbul Consensus update: a revised ESHRE/ALPHA consensus on oocyte and embryo static and dynamic morphological assessment† ‡

This European Society of Human Reproduction and Embryology (ESHRE)/Alpha Scientists in Reproductive Medicine (ALPHA) consensus document provides several novel recommendations to assess oocyte and embryo morphology and rank embryos for transfer. A previous ALPHA/ESHRE consensus on oocyte and embryo morphological assessment was published in 2011. After more than a decade, and the integration of time-lapse technology into embryo culture and assessment, a thorough review and update was needed. A working group consisting of ALPHA members and ESHRE Special interest group of Embryology members formulated recommendations on oocyte and embryo assessment. The working group included 17 internationally recognized experts with extensive experience in clinical embryology. Seven members represented ALPHA and eight members represented ESHRE, along with two methodological experts from the ESHRE central office. Based on a systematic literature search and discussion of existing evidence, the recommendations of the Istanbul Consensus (2011) were reassessed and, where appropriate, updated based on consensus within the working group. A stakeholder review was organized after the updated draft was finalized. The final version was approved by the working group, the ALPHA Executive Committee and the ESHRE Executive Committee. This updated consensus paper provides 20 recommendations focused on the timeline of preimplantation developmental events and morphological criteria for oocyte, zygote and embryo assessment. Based on the duration of embryo culture, recommendations are given on the frequency and timing of assessments to ensure consistency and effectiveness. Several criteria relevant to oocyte and embryo morphology have not been well studied, leading to either a recommendation against their use for grading or for their use in ranking rather than grading. Future updates may require further revision of these recommendations. This document provides embryologists with advice on best practices when assessing oocyte and embryo quality based on the most recent evidence.

The Istanbul consensus update: a revised ESHRE/ALPHA consensus on oocyte and embryo static and dynamic morphological assessment†,‡

STUDY QUESTION

What are the current recommended criteria for morphological assessment of oocytes, zygotes, and embryos?

SUMMARY ANSWER

The present ESHRE/Alpha Scientists in Reproductive Medicine consensus document provides several novel recommendations to assess oocyte and embryo morphology and rank embryos for transfer.

WHAT IS KNOWN ALREADY

A previous Alpha Scientists in Reproductive Medicine/ESHRE consensus on oocyte and embryo morphological assessment was published in 2011. After more than a decade, and the integration of time-lapse technology into embryo culture and assessment, a thorough review and update was needed.

STUDY DESIGN, SIZE, DURATION

A working group consisting of Alpha Scientists in Reproductive Medicine executive committee members and ESHRE Special interest group of Embryology members formulated recommendations on oocyte and embryo assessment.

PARTICIPANTS/MATERIALS, SETTING, METHODS

The working group included 17 internationally recognized experts with extensive experience in clinical embryology. Seven members represented Alpha Scientists in Reproductive Medicine and eight members represented ESHRE, along with to two methodological experts from the ESHRE central office. Based on a systematic literature search and discussion of existing evidence, the recommendations of the Istanbul Consensus (2011) were reassessed and, where appropriate, updated based on consensus within the working group. A stakeholder review was organized after the updated draft was finalized. The final version was approved by the working group, the Alpha executive committee and the ESHRE Executive Committee.

MAIN RESULTS AND THE ROLE OF CHANCE

This updated consensus paper provides 20 recommendations focused on the timeline of preimplantation developmental events and morphological criteria for oocyte, zygote, and embryo assessment. Based on duration of embryo culture, recommendations are given on the frequency and timing of assessments to ensure consistency and effectiveness.

LIMITATIONS, REASONS FOR CAUTION

Several criteria relevant to oocyte and embryo morphology have not been well studied, leading to either a recommendation against their use for grading or for their use in ranking rather than grading. Future updates may require further revision of these recommendations.

WIDER IMPLICATIONS OF THE FINDINGS

This document provides embryologists with advice on best practices when assessing oocyte and embryo quality based on the most recent evidence.

STUDY FUNDING/COMPETING INTEREST(S)

The consensus meeting and writing of the paper were supported by funds from ESHRE and Alpha Scientists in Reproductive Medicine. The working group members did not receive any payment. G.C. declared payments or honoraria for lectures from Gedeon Richter and Cooper Surgical. A.C. declared text book royalties (Mastering Clinical Embryology, published 2024), consulting fees from Cooper Surgical, Gedeon Richter and TMRW Life Sciences, honoraria for lectures from Merck, Ferring, and Gedeon Richter, and participation in the HFEA Scientific Advances Committee; she also disclosed being treasurer and vice-president of Alpha Scientists in Reproductive Medicine, a shareholder in Care Fertility Limited and Fertile Mind Limited, and having stock options in TMRW Life Sciences and U-Ploid Biotechnology Ltd. L.R. declared consulting fees from Organon, payments or honoraria for lectures from Merck, Organon, IBSA, Finox, Geden Richter, Origio, Organon, Ferring, Fundation IVI; she also disclosed being a member of the Advisory Scientific Board of IVIRMA (Paid) and a member of the Advisory Scientific Board of Nterilizer (unpaid). I.S. declared payments or honoraria for lectures from Vitrolife and Cooper Surgical, and stock options from Alife Health. M.A. declared payments or honoraria for lectures from Vitrolife and support for attending meetings from Vitrolife and Cooper Surgical (both unrelated to this manuscript). The other authors have no conflicts of interest to declare.

DISCLAIMER

This Good Practice Recommendations (GPRs) document represents the consensus views of the members of this working group based on the scientific evidence available at the time of the meeting. 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.

Comparison of pregnancy outcomes for high morphological scoring mosaic vs. low morphological scoring euploid embryos: a retrospective cohort study

BACKGROUND

Mosaic embryos have been proven to be capable of resulting in live births and have become an option for embryo transfer under certain circumstances. Recent guidelines suggested that embryo morphological scoring should be taken into consideration when selecting mosaic embryos for transfer. Therefore, we introduce a hypothesis that a high morphological scoring mosaic embryo is a better choice compared to a low morphological scoring euploid embryo.

MATERIALS AND METHODS

This retrospective cohort study included 1641 embryo transfer cycles following next-generation sequencing (NGS)-based preimplantation genetic testing for aneuploidy (PGT-A). Participants were categorized into a mosaic group (87 cycles) and an euploid group (1554 cycles) based on the PGT-A results of the transferred embryos. Statistical methods including multivariate logistic regression analysis and propensity score matching (PSM) were employed to compare the pregnancy outcomes between mosaic and euploid embryo transfer cycles.

RESULTS

Multivariate logistic regression analysis showed that the transfer of mosaic embryos was a prognosis for the reducing live birth rate (P = 0.043). Furthermore, when comparing the pregnancy outcomes of the high morphological scoring mosaic embryo transfer group with the low morphological scoring euploid embryo transfer group, no significant differences were observed (P > 0.05). Additionally, no significant differences in pregnancy outcomes were found between both the high morphological score low proportion and segmental mosaic group and the low morphological score euploid group (P > 0.05).

CONCLUSION

Our study indicated that morphological scoring has reference value when choosing between euploid and mosaic embryo transfers. Specifically, when the morphological score of euploid embryos is poor, mosaic embryos with high morphological scores could be a viable option after comprehensive prenatal consultation.

Construction and evaluation of machine learning-based prediction model for live birth following fresh embryo transfer in IVF/ICSI patients with polycystic ovary syndrome

OBJECTIVE

To investigate the determinants affecting live birth outcomes in fresh embryo transfer among polycystic ovary syndrome (PCOS) patients using various machine learning (ML) algorithms and to construct predictive models, offering novel insights for enhancing live birth rates in this specific group.

METHODS

A sum of 1,062 fresh embryo transfer cycles involving PCOS patients were analyzed, with 466 resulting in live births. The dataset was split randomly into training and testing subsets at a 7:3 ratio. Least absolute shrinkage and selection operator and recursive feature elimination methods were utilized for feature selection within the training data. A grid search strategy identified the optimal parameters for seven ML models: decision tree (DT), K-nearest neighbors (KNN), light gradient boosting machine (LightGBM), naive Bayes model(NBM), random forest (RF), support vector machine (SVM) and extreme gradient boosting (XGBoost). The evaluation of model effectiveness incorporated diverse metrics, encompassing area under the curve (AUC), accuracy, positive predictive value, negative predictive value, F1 score, and Brier score. Calibration curves and decision curve analysis were employed to ascertain the optimal model. Furthermore, Shapley additive explanations were applied to elucidate the importance of predictor variables in the top-performing model.

RESULTS

The AUC values of DT, KNN, LightGBM, NBM, RF, SVM and XGBoost models in the training set were 0.813, 1.000, 0.724, 0.791, 1.000, 0.819 and 0.853, respectively. Corresponding values in the testing set were 0.773, 0.719, 0.705, 0.764, 0.794, 0.806 and 0.822. XGBoost emerged as the most effective ML model. SHAP analysis revealed that variables encompassing embryo transfer count, embryo type, maternal age, infertility duration, body mass index, serum testosterone (T) levels, and progesterone (P) levels on the day of human chorionic gonadotropin administration were pivotal predictors of live birth outcomes in individuals with PCOS receiving fresh embryo transfer.

CONCLUSION

This study developed a live birth prediction model tailored for PCOS fresh embryo transfer cycles, leveraging ML algorithms to compare the efficacy of multiple models. The XGBoost model demonstrated superior predictive capacity, enabling prompt and precise identification of critical risk factors influencing live birth outcomes in PCOS patients. These findings offer actionable insights for clinical intervention, guiding strategies to improve pregnancy outcomes in this population.

CLINICAL TRIAL NUMBER

Not applicable.

Effect of Bovine Follicular Fluid Small Extracellular Vesicles Isolated by Ultracentrifugation and Chromatography on In Vitro Oocyte Maturation and Embryo Development

Small extracellular vesicles (sEVs) play a crucial role in intercellular communication and have demonstrated significant relevance in reproductive biotechnology, particularly in in vitro maturation (IVM) and bovine embryo production. This study evaluates the effects of bovine follicular fluid-derived extracellular vesicles (ffsEVs) isolated using two methods: ultracentrifugation (UC) and size-exclusion chromatography (SEC) on oocyte maturation and preimplantational embryonic development. Significant differences in the size of ffsEVs obtained by both isolation methods were noted, with UC-derived ffsEVs (UC ffsEVs) being smaller than those isolated by SEC (SEC ffsEVs). UC ffsEVs were more effective in upregulating critical oocyte quality genes, such as HSF1 and CPT1B. However, no significant differences were observed in embryonic developmental rates. Furthermore, the expression of genes associated with preimplantational embryonic quality revealed that only the SEC ffsEVs group exhibited a significant increase in IFNT1 and SOX2 levels, indicating an enhancement in embryonic quality. Notably, blastocysts derived from SEC ffsEVs also showed a higher total cell count compared to those from UC ffsEVs. No differences were found in other critical genes like GLUT1 and CDX2. These results suggest that the use of SEC ffsEVs could improve the in vitro embryo production process, highlighting the importance of the isolation method in determining the functional efficacy of ffsEVs according to research objectives.

[Increasing the cumulative live birth rate: Low-grade blastocysts, potential overlook]

It is now widely recognized that, following prolonged culture, the transfer of a high-quality morphologically graded blastocyst is the preferred strategy in embryo transfer. Low-grade blastocysts are often considered to have a low implantation potential, and their use remains highly limited. We conducted a general review of the literature, including publications from August 2017 to October 2023, to assess the current state of knowledge regarding these embryos, which are generally excluded in routine practice. Our primary outcome measure was the "live birth rate" following the frozen transfer of a low-grade morphologically classified blastocyst according to the Gardner classification. The "miscarriage rates" were also evaluated. The bibliographic research led to the selection of 9 articles. Low-grade blastocysts can result in live births, with rates ranging from 5.97 to 40%, and in the birth of healthy children, which remains the primary goal of assisted reproductive technology. It would therefore be relevant to reconsider the routine use of these embryos.

Application of a methodological framework for the development and multicenter validation of reliable artificial intelligence in embryo evaluation

BACKGROUND

Artificial intelligence (AI) models analyzing embryo time-lapse images have been developed to predict the likelihood of pregnancy following in vitro fertilization (IVF). However, limited research exists on methods ensuring AI consistency and reliability in clinical settings during its development and validation process. We present a methodology for developing and validating an AI model across multiple datasets to demonstrate reliable performance in evaluating blastocyst-stage embryos.

METHODS

This multicenter analysis utilizes time-lapse images, pregnancy outcomes, and morphologic annotations from embryos collected at 10 IVF clinics across 9 countries between 2018 and 2022. The four-step methodology for developing and evaluating the AI model include: (I) curating annotated datasets that represent the intended clinical use case; (II) developing and optimizing the AI model; (III) evaluating the AI's performance by assessing its discriminative power and associations with pregnancy probability across variable data; and (IV) ensuring interpretability and explainability by correlating AI scores with relevant morphologic features of embryo quality. Three datasets were used: the training and validation dataset (n = 16,935 embryos), the blind test dataset (n = 1,708 embryos; 3 clinics), and the independent dataset (n = 7,445 embryos; 7 clinics) derived from previously unseen clinic cohorts.

RESULTS

The AI was designed as a deep learning classifier ranking embryos by score according to their likelihood of clinical pregnancy. Higher AI score brackets were associated with increased fetal heartbeat (FH) likelihood across all evaluated datasets, showing a trend of increasing odds ratios (OR). The highest OR was observed in the top G4 bracket (test dataset G4 score ≥ 7.5: OR 3.84; independent dataset G4 score ≥ 7.5: OR 4.01), while the lowest was in the G1 bracket (test dataset G1 score < 4.0: OR 0.40; independent dataset G1 score < 4.0: OR 0.45). AI score brackets G2, G3, and G4 displayed OR values above 1.0 (P < 0.05), indicating linear associations with FH likelihood. Average AI scores were consistently higher for FH-positive than for FH-negative embryos within each age subgroup. Positive correlations were also observed between AI scores and key morphologic parameters used to predict embryo quality.

CONCLUSIONS

Strong AI performance across multiple datasets demonstrates the value of our four-step methodology in developing and validating the AI as a reliable adjunct to embryo evaluation.

The 'golden fleece of embryology' eludes us once again: a recent RCT using artificial intelligence reveals again that blastocyst morphology remains the standard to beat

Grading of blastocyst morphology is used routinely for embryo selection with good outcomes. A lot of effort has been placed in IVF to search for the prize of selecting the most viable embryo to transfer ('the golden fleece of embryology'). To improve on morphology alone, artificial intelligence (AI) has also become a tool of interest, with many retrospective studies being published with impressive prediction capabilities. Subsequently, AI has again raised expectations that this 'golden fleece of embryology' was once again within reach. A recent RCT however was not able to demonstrate non-inferiority using a deep learning algorithm 'iDAScore version 1' for clinical pregnancy rate when compared to standard morphology. Good blastocyst morphology has again proven itself as a high bar in predicting live birth. We should however not give up on the development of further approaches which may allow us to identify extra features of viable embryos that are not captured by morphology.

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.

A deep learning model for predicting blastocyst formation from cleavage-stage human embryos using time-lapse images

Efficient prediction of blastocyst formation from early-stage human embryos is imperative for improving the success rates of assisted reproductive technology (ART). Clinics transfer embryos at the blastocyst stage on Day-5 but Day-3 embryo transfer offers the advantage of a shorter culture duration, which reduces exposure to laboratory conditions, potentially enhancing embryonic development within a more conducive uterine environment and improving the likelihood of successful pregnancies. In this paper, we present a novel ResNet-GRU deep-learning model to predict blastocyst formation at 72 HPI. The model considers the time-lapse images from the incubator from Day 0 to Day 3. The model predicts blastocyst formation with a validation accuracy of 93% from the cleavage stage. The sensitivity and specificity are 0.97 and 0.77 respectively. The deep learning model presented in this paper will assist the embryologist in identifying the best embryo to transfer at Day 3, leading to improved patient outcomes and pregnancy rates in ART.

Quality of IVM ovarian tissue oocytes: impact of clinical, demographic, and laboratory factors

PURPOSE

To determine how clinical, demographic, and laboratory characteristics influence ovarian tissue oocyte quality.

METHODS

Immature cumulus-oocyte complexes were isolated from removed ovaries and cultured for 48-52 h in either monophasic standard or biphasic CAPA media for fertility preservation. A total of 355 MII oocytes from 53 patients were described for intracytoplasmic and extracytoplasmic anomalies. Multiple clinical, laboratory, and demographic characteristics were analyzed. Statistically significant differences between independent groups in qualitative variables were identified using Pearson's χ2 and Fisher's exact tests. The diagnostic value of quantitative variables was assessed using the ROC curve analysis. Factors associated with the development of dysmorphism, taking patient age into account, were identified using the binary logistic regression analysis.

RESULTS

Dysmorphisms were observed in 245 oocytes (69.0%), with a median number of dysmorphisms of 2. Oocyte dysmorphisms were found to be 2.211 times more likely to be detected in patients with ovarian cancer, while the presence of dark-colored cytoplasm was associated with gynecologic surgery in the anamnesis (p = 0.002; OR 16.652; 95% CI, 1.977-140.237; Cramer's V 0.187). Small polar bodies developed 2.717 times more often (95% CI, 1.195-6.18) in patients older than 35. In the case of ovarian transportation on ice at 4 ℃, the chances of development of cytoplasmic granularity increased 2.569 times (95% CI, 1.301-5.179). The use of biphasic CAPA IVM media contributed to a decrease in the probability of large polar body formation (p = 0.034) compared to the standard monophasic IVM media.

CONCLUSIONS

Both patients' characteristics and laboratory parameters have an impact on the quality of IVM ovarian tissue oocytes.

Trophectoderm, Inner Cell Mass, and Expansion Status for Live Birth Prediction After Frozen Blastocyst Transfer: The Winner Is Trophectoderm

Despite advancements in technologies such as time-lapse microscopy and artificial intelligence, the gold standard for embryo selection still relies on standard morphological assessment. Several studies have investigated the correlation between blastocyst characteristics (expansion status, inner cell mass, and trophectoderm) and clinical outcomes, reaching contradictory results. In consideration of these ambiguities in the literature, we performed a retrospective study of 1546 untested first-vitrified-warmed single day 5/6 blastocyst transfers. The purpose of our study is to evaluate three scenarios: (i) independent association between each morphological characteristic (expansion status, inner cell mass, and trophectoderm) and live birth; (ii) comparison between blastocysts with inner cell mass grade A and trophectoderm grade B and blastocysts with inner cell mass grade B and trophectoderm grade A; and (iii) comparison between poor-quality day 5 and top-quality day 6 blastocysts. After adjusting for principal confounders, we report that trophectoderm is more predictive of live births than inner cell mass and expansion status. We observed a trend in favor of top-quality day 6 blastocysts over poor-quality day 5 blastocysts. Moreover, on the same day of development and expansion status, blastocyst BA should be preferable to blastocyst AB.

Perinatal complications and neonatal outcomes in in vitro fertilization/intracytoplasmic sperm injection: a propensity score matching cohort study

Background

The utilization of in vitro fertilization/intracytoplasmic sperm injection (IVF/ICSI) has witnessed a significant increase in recent years. However, the comparative perinatal and neonatal outcomes compared to natural pregnancies are unclear. This study aims to compare the outcomes of pregnancies from IVF and ICSI with natural pregnancies.

Methods

This retrospective, propensity score-matched cohort study was conducted at the First People's Hospital of Shangqiu and The First Affiliated Hospital of Xinjiang Medical University, involving 5,628 patients from February 2019 to December 2022. It compared pregnancies achieved through IVF/ICSI with those conceived naturally. The primary outcomes assessed were perinatal complications and neonatal health parameters. Propensity score matching and multivariate logistic regression analysis were employed to adjust for potential confounders and identify independent associations.

Results

After propensity score matching, the IVF/ICSI group demonstrated significantly higher rates of placental adherence (12.1% vs. 7.4%, p < 0.001) and postpartum hemorrhage (11.1% vs. 7.6%, p = 0.002) compared to the NP group. Neonates in the IVF/ICSI group had a lower gestational age (38.21 ± 2.12 weeks vs. 38.63 ± 2.29 weeks, p < 0.001), reduced birth weight (3159.42 ± 722.75 g vs. 3211.31 ± 624.42 g, p = 0.032), and an increased preterm delivery rate (11.2% vs. 8.9%, p = 0.017). Multivariate analysis further confirmed these findings, highlighting the independent associations between IVF/ICSI and these adverse outcomes.

Conclusion

This study suggests a potential correlation between the use of IVF/ICSI and unfavorable perinatal and neonatal outcomes. These findings underscore the critical need for ongoing monitoring and research efforts to enhance the safety and effectiveness of these reproductive technologies.

The construction of machine learning-based predictive models for high-quality embryo formation in poor ovarian response patients with progestin-primed ovarian stimulation

OBJECTIVE

To explore the optimal models for predicting the formation of high-quality embryos in Poor Ovarian Response (POR) Patients with Progestin-Primed Ovarian Stimulation (PPOS) using machine learning algorithms.

METHODS

A retrospective analysis was conducted on the clinical data of 4,216 POR cycles who underwent in vitro fertilization (IVF) / intracytoplasmic sperm injection (ICSI) at Sichuan Jinxin Xinan Women and Children's Hospital from January 2015 to December 2021. Based on the presence of high-quality cleavage embryos 72 h post-fertilization, the samples were divided into the high-quality cleavage embryo group (N = 1950) and the non-high-quality cleavage embryo group (N = 2266). Additionally, based on whether high-quality blastocysts were observed following full blastocyst culture, the samples were categorized into the high-quality blastocyst group (N = 124) and the non-high-quality blastocyst group (N = 1800). The factors influencing the formation of high-quality embryos were analyzed using logistic regression. The predictive models based on machine learning methods were constructed and evaluated accordingly.

RESULTS

Differential analysis revealed that there are statistically significant differences in 14 factors between high-quality and non-high-quality cleavage embryos. Logistic regression analysis identified 14 factors as influential in forming high-quality cleavage embryos. In models excluding three variables (retrieved oocytes, MII oocytes, and 2PN fertilized oocytes), the XGBoost model performed slightly better (AUC = 0.672, 95% CI = 0.636-0.708). Conversely, in models including these three variables, the Random Forest model exhibited the best performance (AUC = 0.788, 95% CI = 0.759-0.818). In the analysis of high-quality blastocysts, significant differences were found in 17 factors. Logistic regression analysis indicated that 13 factors influence the formation of high-quality blastocysts. Including these variables in the predictive model, the XGBoost model showed the highest performance (AUC = 0.813, 95% CI = 0.741-0.884).

CONCLUSION

We developed a predictive model for the formation of high-quality embryos using machine learning methods for patients with POR undergoing treatment with the PPOS protocol. This model can help infertility patients better understand the likelihood of forming high-quality embryos following treatment and help clinicians better understand and predict treatment outcomes, thus facilitating more targeted and effective interventions.

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.