Top-quality embryo transfer is associated with lower odds of ectopic pregnancy

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.

ESHRE Guideline Group on the Number of Embryos to Transfer, Alteri A, Arroyo G, Baccino G, Craciunas L, De Geyter C, Ebner T, Koleva M, Kordic K, Mcheik S, Mertes H, Pavicic Baldani D, Rodriguez-Wallberg KA, Rugescu I, Santos-Ribeiro S, Tilleman K, Woodward B, Vermeulen N, Veleva Z. ESHRE guideline: number of embryos to transfer during IVF/ICSI†

STUDY QUESTION

Which clinical and embryological factors should be considered to apply double embryo transfer (DET) instead of elective single embryo transfer (eSET)?

SUMMARY ANSWER

No clinical or embryological factor per se justifies a recommendation of DET instead of eSET in IVF/ICSI.

WHAT IS KNOWN ALREADY

DET is correlated with a higher rate of multiple pregnancy, leading to a subsequent increase in complications for both mother and babies. These complications include preterm birth, low birthweight, and other perinatal adverse outcomes. To mitigate the risks associated with multiple pregnancy, eSET is recommended by international and national professional organizations as the preferred approach in ART.

STUDY DESIGN, SIZE, DURATION

The guideline was developed according to the structured methodology for development and update of ESHRE guidelines. Literature searches were performed in PUBMED/MEDLINE and Cochrane databases, and relevant papers published up to May 2023, written in English, were included. Live birth rate, cumulative live birth rate, and multiple pregnancy rate were considered as critical outcomes.

PARTICIPANTS/MATERIALS, SETTING, METHODS

Based on the collected evidence, recommendations were discussed until a consensus was reached within the Guideline Development Group (GDG). A stakeholder review was organized after the guideline draft was finalized. The final version was approved by the GDG and the ESHRE Executive Committee.

MAIN RESULTS AND THE ROLE OF CHANCE

The guideline provides 35 recommendations on the medical and non-medical risks associated with multiple pregnancies and on the clinical and embryological factors to be considered when deciding on the number of embryos to transfer. These recommendations include 25 evidence-based recommendations, of which 24 were formulated as strong recommendations and one as conditional, and 10 good practice points. Of the evidence-based recommendations, seven (28%) were supported by moderate-quality evidence. The remaining recommendations were supported by low (three recommendations; 12%), or very low-quality evidence (15 recommendations; 60%). Owing to the lack of evidence-based research, the guideline also clearly mentions recommendations for future studies.

LIMITATIONS, REASONS FOR CAUTION

The guideline assessed different factors one by one based on existing evidence. However, in real life, clinicians' decisions are based on several prognostic factors related to each patient's case. Furthermore, the evidence from randomized controlled trials is too scarce to formulate high-quality evidence-based recommendations.

WIDER IMPLICATIONS OF THE FINDINGS

The guideline provides health professionals with clear advice on best practice in the decision-making process during IVF/ICSI, based on the best evidence currently available, and recommendations on relevant information that should be communicated to patients. In addition, a list of research recommendations is provided to stimulate further studies in the field.

STUDY FUNDING/COMPETING INTEREST(S)

The guideline was developed and funded by ESHRE, covering expenses associated with the guideline meetings, the literature searches, and the dissemination of the guideline. The guideline group members did not receive payment. DPB declared receiving honoraria for lectures from Merck, Ferring, and Gedeon Richter. She is a member of ESHRE EXCO, and the Mediterranean Society for reproductive medicine and the president of the Croatian Society for Gynaecological Endocrinology and Reproductive Medicine. CDG is the past Chair of the ESHRE EIM Consortium and a paid deputy member of the Editorial board of Human Reproduction. IR declared receiving reimbursement from ESHRE and EDCD for attending meetings. She holds an unpaid leadership role in OBBCSSR, ECDC Sohonet, and AER. KAR-W declared receiving grants for clinical researchers and funding provision to the institution from the Swedish Cancer Society (200170F), the Senior Clinical Investigator Award, Radiumhemmets Forskningsfonder (Dnr: 201313), Stockholm County Council FoU (FoUI-953912) and Karolinska Institutet (Dnr 2020-01963), NovoNordisk, Merck and Ferring Pharmaceuticals. She received consulting fees from the Swedish Ministry of Health and Welfare. She received honoraria from Roche, Pfizer, and Organon for chairmanship and lectures. She received support from Organon for attending meetings. She participated in advisory boards for Merck, Nordic countries, and Ferring. She declared receiving time-lapse equipment and grants with payment to institution for pre-clinical research from Merck pharmaceuticals and from Ferring. SS-R received research funding from Roche Diagnostics, Organon/MSD, Theramex, and Gedeo-Richter. He received consulting fees from Organon/MSD, Ferring Pharmaceuticals, and Merck Serono. He declared receiving honoraria for lectures from Ferring Pharmaceuticals, Besins, Organon/MSD, Theramex, and Gedeon Richter. He received support for attending Gedeon Richter meetings and participated in the Data Safety Monitoring Board of the T-TRANSPORT trial. He is the Deputy of ESHRE SQART special interest group. He holds stock options in IVI Lisboa and received equipment and other services from Roche Diagnostics and Ferring Pharmaceuticals. KT declared receiving payment for honoraria for giving lectures from Merck Serono and Organon. She is member of the safety advisory board of EDQM. She holds a leadership role in the ICCBBA board of directors. ZV received reimbursement from ESHRE for attending meetings. She also received research grants from ESHRE and Juhani Aaltonen Foundation. She is the coordinator of EHSRE SQART special interest group. The other authors have no conflicts of interest to declare.

DISCLAIMER

This guideline represents the views of ESHRE, which were achieved after careful consideration of the scientific evidence available at the time of preparation. In the absence of scientific evidence on certain aspects, a consensus between the relevant ESHRE stakeholders has been obtained. Adherence to these clinical practice guidelines does not guarantee a successful or specific outcome, nor does it establish a standard of care. Clinical practice guidelines do not replace the need for application of clinical judgement to each individual presentation, nor variations based on locality and facility type. ESHRE makes no warranty, express or implied, regarding the clinical practice guidelines and specifically excludes any warranties of merchantability and fitness for a particular use or purpose (full disclaimer available at https://www.eshre.eu/Guidelines-and-Legal).

Body mass index impacts ectopic pregnancy during in vitro fertilization: an analysis of 42,362 clinical pregnancy cycles

PURPOSE

This large, single-center, retrospective cohort study was aimed to explore the effect of female body mass index (BMI) on ectopic pregnancy (EP) following fresh and frozen-thawed embryo transfers (ET).

METHODS

A total of 27,600 pregnancies after fresh ET and 14,762 pregnancies after frozen-thawed ET were included between January 2010 to June 2022. Women were divided into three groups based on BMI according to the Working Group on Obesity in China (WGOC), International Life Sciences Institute (ILSI): underweight (BMI < 18.5 kg/m2), normal weight (BMI, 18.5-23.9 kg/m2), and overweight or obesity (≥ 24 kg/m2). Compare EP rates among BMI categories in fresh and frozen-thawed ET cycles respectively. Multivariate logistic regression analyses were used to investigate the association between female BMI and EP.

RESULTS

The overall EP rates in fresh, and frozen thawed transfer cycles were 2.43% (672/27,600) and 2.82% (417/14,762), respectively. In fresh ET cycles, underweight women yielded a significantly higher EP rate than those with normal and excess weight (3.29% vs. 2.29% vs. 2.54%, P = 0.029). But EP rates did not differ among the three BMI groups (2.72% vs. 2.76% vs. 2.96%, P = 0.782) in frozen-thawed ET cycles. In fresh ET cycles, after adjusting for potential confounding factors, no significant association was found between female BMI and EP occurrence (adjusted OR: 0.98, 95% CI 0.70-1.37, P = 0.894, for BMI 18.5-23.9 kg/m2; adjusted OR: 0.89, 95% CI 0.75-1.06, P = 0.205, for BMI ≥ 24 kg/m2. Reference = BMI < 18.5 kg/m2).

CONCLUSION(S)

Female BMI did not affect the occurrence of ectopic pregnancy in either fresh or frozen-thawed embryo transfer cycles.