Correlation of progesterone levels on the day of oocyte retrieval with basal hormonal status and the outcome of ART

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

STUDY QUESTION

Can machine learning predict the number of oocytes retrieved from controlled ovarian hyperstimulation (COH)?

SUMMARY ANSWER

Three machine-learning models were successfully trained to predict the number of oocytes retrieved from COH.

WHAT IS KNOWN ALREADY

A number of previous studies have identified and built predictive models on factors that influence the number of oocytes retrieved during COH. Many of these studies are, however, limited in the fact that they only consider a small number of variables in isolation.

STUDY DESIGN, SIZE, DURATION

This study was a retrospective analysis of a dataset of 11,286 cycles performed at a single centre in France between 2009 and 2020 with the aim of building a predictive model for the number of oocytes retrieved from ovarian stimulation. The analysis was carried out by a data analysis team external to the centre using the Substra framework. The Substra framework enabled the data analysis team to send computer code to run securely on the centre's on-premises server. In this way, a high level of data security was achieved as the data analysis team did not have direct access to the data, nor did the data leave the centre at any point during the study.

PARTICIPANTS/MATERIALS, SETTING, METHODS

The Light Gradient Boosting Machine algorithm was used to produce three predictive models: one that directly predicted the number of oocytes retrieved and two that predicted which of a set of bins provided by two clinicians the number of oocytes retrieved fell into. The resulting models were evaluated on a held-out test set and compared to linear and logistic regression baselines. In addition, the models themselves were analysed to identify the parameters that had the biggest impact on their predictions.

MAIN RESULTS AND THE ROLE OF CHANCE

On average, the model that directly predicted the number of oocytes retrieved deviated from the ground truth by 4.21 oocytes. The model that predicted the first clinician's bins deviated by 0.73 bins whereas the model for the second clinician deviated by 0.62 bins. For all models, performance was best within the first and third quartiles of the target variable, with the model underpredicting extreme values of the target variable (no oocytes and large numbers of oocytes retrieved). Nevertheless, the erroneous predictions made for these extreme cases were still within the vicinity of the true value. Overall, all three models agreed on the importance of each feature which was estimated using Shapley Additive Explanation (SHAP) values. The feature with the highest mean absolute SHAP value (and thus the highest importance) was the antral follicle count, followed by basal AMH and FSH. Of the other hormonal features, basal TSH, LH, and testosterone levels were similarly important and baseline LH was the least important. The treatment characteristic with the highest SHAP value was the initial dose of gonadotropins.

LIMITATIONS, REASONS FOR CAUTION

The models produced in this study were trained on a cohort from a single centre. They should thus not be used in clinical practice until trained and evaluated on a larger cohort more representative of the general population.

WIDER IMPLICATIONS OF FINDINGS

These predictive models for the number of oocytes retrieved from COH may be useful in clinical practice, assisting clinicians in optimizing COH protocols for individual patients. Our work also demonstrates the promise of using the Substra framework for allowing external researchers to provide clinically relevant insights on sensitive fertility data in a fully secure, trustworthy manner and opens a number of exciting avenues for accelerating future research.

STUDY FUNDING/COMPETING INTEREST(S)

This study was funded by the French Public Bank of Investment as part of the Healthchain Consortium. T.Fe., C.He., J.C., C.J., C.-A.P., and C.Hi. are employed by Apricity. C.Hi. has received consulting fees and honoraria from Vitrolife, Merck Serono, Ferring, Cooper Surgical, Dibimed, Apricity, and Fairtility and travel support from Fairtility and Vitrolife, participates on an advisory board for Merck Serono, was the founder and organizer of the AI Fertility conference, has stock in Aria Fertility, TMRW, Fairtility, Apricity, and IVF Professionals, and received free equipment from Planar in exchange for first user feedback. C.J. has received a grant from BPI. J.C. has also received a grant from BPI, is a member of the Merck AI advisory board, and is a board member of Labelia Labs. C.He has a contract for medical writing of this manuscript by CHU Nantes and has received travel support from Apricity. A.R. haș received honoraria from Ferring and Organon. T.Fe. has received a grant from BPI.

TRIAL REGISTRATION NUMBER

N/A.

Addition of intramuscular to vaginal progesterone for luteal phase support in fresh embryo transfer cycles: A cross-sectional study

Background

Luteal phase deficiency is common in assisted reproductive technology and is characterized by inadequate progesterone production. Various studies have shown that administration of progesterone in fresh embryo transfer cycles increases the rate of clinical pregnancy and live birth rate. Progesterone administration has variable types: oral, vaginal, oil-based intramuscular, and subcutaneous.

Objective

This study aims to compare the effect of adding intramuscular progesterone to the vaginal progesterone for luteal phase support in the fresh embryo transfer cycle.

Materials and Methods

This study reviewed the information related to 355 women who had a fresh embryo transfer between March 2020 and February 2021 at the Yazd Reproductive Sciences Institute, Yazd, Iran. The participants population were divided into 2 groups based on the type of luteal phase support regime: group I (n = 173) received 400 mg vaginal progesterone alone twice a day from the day of ovum pick up; and group II (n = 182) received 50 mg IM of progesterone in addition to vaginal progesterone 400 mg twice a day from the day of ovum pick up. Chemical and clinical pregnancy rates were compared between groups.

Results

The basic characteristics of groups were statistically similar. The rates of chemical and clinical pregnancy were higher in the vaginal plus IM progesterone group than in the vaginal progesterone group. Moreover, chemical pregnancy showed a significant difference between the groups (p = 0.011).

Conclusion

Our findings demonstrated that the addition of IM progesterone to the vaginal progesterone improves the chemical pregnancy rate in fresh embryo transfer.

Impact of Various Parameters as Predictors of The Success Rate of In Vitro Fertilization

Infertility is one of the major problems faced in medicine. There are numerous factors that play a role in infertility. For example, numerous studies mention the impact of the quantity and quality of mitochondria in sexual gametes. This is a narrative review of the effects of the mitochondrial genome on fertility. We searched the PubMed, Science Direct, SID, Google Scholar, and Scopus databases for articles related to “Fertility, Infertility, Miscarriage, Mitochondria, Sperm, mtDNA, Oocytes” and other synonymous keywords from 2000 to 2020. The mitochondrial genome affects infertility in both male and female gametes; in sperm, it mainly releases free radicals. In the oocyte, a mutation in this genome can affect the amount of energy required after fertilisation, leading to gestation failure. In both cases, infertile cells have substantially less mitochondrial DNA (mtDNA) copies. The effects of mtDNA on gamete fertility occur via changes in oxidative phosphorylation and cellular energy production. Also, a reduction in the number of mtDNA copies is directly associated with sex cell infertility. Therefore, evaluation of the mitochondrial genome can be an excellent diagnostic option for couples who have children with neonatal disorders, infertile couples who seek assisted reproductive treatment, and those in whom assisted reproductive techniques have failed.

Regulatory Role and Potential Importance of GDF-8 in Ovarian Reproductive Activity

Growth differentiation factor-8 (GDF-8) is a member of the transforming growth factor-beta superfamily. Studies in vitro and in vivo have shown GDF-8 to be involved in the physiology and pathology of ovarian reproductive functions. In vitro experiments using a granulosa-cell model have demonstrated steroidogenesis, gonadotrophin responsiveness, glucose metabolism, cell proliferation as well as expression of lysyl oxidase and pentraxin 3 to be regulated by GDF-8 via the mothers against decapentaplegic homolog signaling pathway. Clinical data have shown that GDF-8 is expressed widely in the human ovary and has high expression in serum of obese women with polycystic ovary syndrome. GDF-8 expression in serum changes dynamically in patients undergoing controlled ovarian hyperstimulation. GDF-8 expression in serum and follicular fluid is correlated with the ovarian response and pregnancy outcome during in vitro fertilization. Blocking the GDF-8 signaling pathway is a potential therapeutic for ovarian hyperstimulation syndrome and ovulation disorders in polycystic ovary syndrome. GDF-8 has a regulatory role and potential importance in ovarian reproductive activity and may be involved in folliculogenesis, ovulation, and early embryo implantation.

17β-Estradiol Increases APE1/Ref-1 Secretion in Vascular Endothelial Cells and Ovariectomized Mice: Involvement of Calcium-Dependent Exosome Pathway

Apurinic/apyrimidinic endonuclease-1/redox factor-1 (APE1/Ref-1) is a multifunctional protein that can be secreted, and recently suggested as new biomarker for vascular inflammation. However, the endogenous hormones for APE1/Ref-1 secretion and its underlying mechanisms are not defined. Here, the effect of twelve endogenous hormones on APE1/Ref-1 secretion was screened in cultured vascular endothelial cells. The endogenous hormones that significantly increased APE1/Ref-1 secretion was 17β-estradiol (E2), 5𝛼-dihydrotestosterone, progesterone, insulin, and insulin-like growth factor. The most potent hormone inducing APE1/Ref-1 secretion was E2, which in cultured endothelial cells, E2 for 24 h increased APE1/Ref-1 secretion level of 4.56 ± 1.16 ng/mL, compared to a basal secretion level of 0.09 ± 0.02 ng/mL. Among the estrogens, only E2 increased APE1/Ref-1 secretion, not estrone and estriol. Blood APE1/Ref-1 concentrations decreased in ovariectomized (OVX) mice but were significantly increased by the replacement of E2 (0.39 ± 0.09 ng/mL for OVX vs. 4.67 ± 0.53 ng/mL for OVX + E2). E2-induced APE1/Ref-1secretion was remarkably suppressed by the estrogen receptor (ER) blocker fulvestrant and intracellular Ca²⁺ chelator 1,2-Bis(2-aminophenoxy)ethane-N,N,N′,N′-tetraacetic acid tetrakis (acetoxymethyl ester) (BAPTA-AM), suggesting E2-induced APE1/Ref-1 secretion was dependent on ER and intracellular calcium. E2-induced APE1/Ref-1 secretion was significantly inhibited by exosome inhibitor GW4869. Furthermore, APE1/Ref-1 level in CD63-positive exosome were increased by E2. Finally, fluorescence imaging data showed that APE1/Ref-1 co-localized with CD63-labled exosome in the cytoplasm of cells upon E2 treatment. Taken together, E2 was the most potent hormone for APE1/Ref-1 secretion, which appeared to occur through exosomes that were dependent on ER and intracellular Ca²⁺. Furthermore, hormonal effects should be considered when analyzing biomarkers for vascular inflammation.