Dataset Information

Using Unlabeled Information of Embryo Siblings from the Same Cohort Cycle to Enhance In Vitro Fertilization Implantation Prediction.

ABSTRACT: High-content time-lapse embryo imaging assessed by machine learning is revolutionizing the field of in vitro fertilization (IVF). However, the vast majority of IVF embryos are not transferred to the uterus, and these masses of embryos with unknown implantation outcomes are ignored in current efforts that aim to predict implantation. Here, whether, and to what extent the information encoded within "sibling" embryos from the same IVF cohort contributes to the performance of machine learning-based implantation prediction is explored. First, it is shown that the implantation outcome is correlated with attributes derived from the cohort siblings. Second, it is demonstrated that this unlabeled data boosts implantation prediction performance. Third, the cohort properties driving embryo prediction, especially those that rescued erroneous predictions, are characterized. The results suggest that predictive models for embryo implantation can benefit from the overlooked, widely available unlabeled data of sibling embryos by reducing the inherent noise of the individual transferred embryo.

SUBMITTER: Tzukerman N

PROVIDER: S-EPMC10520665 | biostudies-literature | 2023 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Using Unlabeled Information of Embryo Siblings from the Same Cohort Cycle to Enhance In Vitro Fertilization Implantation Prediction.

Tzukerman Noam N Rotem Oded O Shapiro Maya Tsarfati MT Maor Ron R Meseguer Marcos M Gilboa Daniella D Seidman Daniel S DS Zaritsky Assaf A

Advanced science (Weinheim, Baden-Wurttemberg, Germany) 20230728 27

High-content time-lapse embryo imaging assessed by machine learning is revolutionizing the field of in vitro fertilization (IVF). However, the vast majority of IVF embryos are not transferred to the uterus, and these masses of embryos with unknown implantation outcomes are ignored in current efforts that aim to predict implantation. Here, whether, and to what extent the information encoded within "sibling" embryos from the same IVF cohort contributes to the performance of machine learning-based ...[more]

PMID: 37507828

Similar Datasets

Project description:Currently, in vitro fertilization (IVF) is one of the most common approaches towards treating infertility. However, the success of this approach is still relatively low an the outcome of the IVF procedure is challenging to predict. At present, there is no highly successful marker that could reliably predict the pregnancy outcome in the process of assisted reproduction (AR). Currently, multiple embryo transfers are performed to warrant a successful pregnancy outcome, but this commonly results in multiple pregnancies, narrowing the feasibility of this method for a subset of couples affected by infertility. Recently IVF cycles with single-embryo transfers have become an option of interest in AR approaches. Such cycles, however, are significantly less successful and for this reason, there is an incentive to improve the pregnancy chance per IVF cycle by incorporating more criteria for selection of the embryo with the highest implantation potential. Gene expression in follicular cells, including granulosa cells (GC) and cumulus cells (CC) has previously been considered as a tool to predict the quality of the oocytes in several studies in addition to assessing the morphologic criteria of the embryos. Gene expression estimation in these cells, especially of the CC population, carries along several benefits as their harvesting is non-invasive, they are in direct contact with the oocyte and are usually discarded during the process of intracytoplasmatic sperm injection procedure (ICSI), making them any easily accessible surrogate tissue for gene expression analyses. Considering that several studies reporting various rates of success in prediction of AR cycle outcome with expression as a biomarker have been published, we attempted to perform the largest study of global gene expression alterations in finding novel biomarkers to outcome of in- vitro fertilization, which would encompass discovery of new biomarker genes and subsequent confirmational study of the selected biomarker set on an independent validation group. In this experiments 4 samples were hybridized twice, to allow for inspection of technical validity of microarray experiments.

Project description:BackgroundMicroRNAs (miRNAs) are small, non-coding RNAs that are dysregulated in many diseases and can act as biomarkers. Although well-studied in cancer, the role of miRNAs in embryo implantation is poorly understood. Approximately 70% of embryos fail to implant following in-vitro fertilization and embryo transfer, 10% of patients experienced recurrent implantation failure. However, there are no well-established biomarkers that can predict implantation failure. Our purpose is to investigate distinct miRNA profiles in plasma and plasma exosomes during the window of implantation between patients with failed implantation and successful implantation.MethodsWe select a nested case-control population of 12 patients with implantation failure or successfully clinical pregnancy using propensity score matching. RNA was extracted from plasma and plasma exosomes collected during the window of implantation (WOI). MicroRNA expression in all samples was quantified using microRNA sequencing. The intersection of differently expressed miRNAs in plasma and exosomes were further validated in the GEO dataset. Significantly altered microRNAs in both plasma and plasma exosomes were then subjected to target prediction and KEGG pathway enrichment analyses to search for key signaling pathways. WGCNA analysis was performed to identify hub miRNAs associated with implantation.Results13 miRNAs were differentially expressed in both plasma and plasma exosomes in patients with implantation failure. Among them, miR-150-5p, miR-150-3p, miR-149-5p, and miR-146b-3p had consistent direction changes in endometrium of patients with recurrent implantation failure (RIF), miR-342-3p had consistent direction changes in blood samples of patients with RIF. Pathway enrichment analysis showed that the target genes of differentially expressed miRNAs are enriched in pathways related to embryo implantation. WGCNA analysis indicated that miR-150-5p, miR-150-3p, miR-146b-3p, and miR-342-3p are hub miRNAs.ConclusionsImplantation failure is associated with distinct miRNA profiles in plasma and plasma exosomes during WOI.

Project description:BackgroundIn assisted reproduction technology embryo competence is routinely evaluated on morphological criteria but efficacy remains relatively low. Additional information could be obtained by evaluating pronuclear (PN) morphology. Up to now controversial results have been reported about the prognostic value of PN score. One of the main limitations of literature data is the use of different PN classification methods. In this regard, in 2011 the ESHRE and Alpha Scientists in Reproductive Medicine defined three PN categories to standardize zygote assessment. In this study we evaluated whether the consensus ESHRE-Alpha system for the pronuclear scoring could be an useful additional criterion to improve prediction of embryo implantation potential.MethodsThis is a retrospective, longitudinal, observational, cohort study. We included 3004 zygotes from 555 women who underwent ICSI treatment at our Center between January 2014 and June 2019. The PN were categorized as score 1: symmetrical, 2: non-symmetrical, 3: abnormal. A subset of 110 zygotes did not cleaved. On day 2-3 1163 embryos were transferred, 232 arrested, and 9 were cryopreserved. Among the 1490 embryos cultured up to day 5-7, 516 became blastocysts: 123 were transferred on day 5 and 393 were cryopreserved. Comparisons of age, cleavage and blastocyst rate, quality of embryos, implantation success among PN score groups were evaluated by chi-square test or Kruskal-Wallis test as appropriate. Potential predictors of embryo implantation were first tested in univariable analysis using generalized estimating equations taking into account correlation between embryos originated from the same patient. Then, variables potentially associated with implantation success (P<0.05) were included in a multivariable analysis for calculating the adjusted odds ratio (OR) and 95% confidence interval (CI).ResultsThere was no significant difference in patients'age, cleavage and blastulation rates, and embryo morphology among the three PNscore groups. The PN score 1-embryos had a greater implantation success respect to score 2-3-ones (OR 1.83; 95% CI 1.34-2.50, P=0.0001). Consistently, the pronuclear score remained predictive of implantation in top quality embryos (OR 1.68; 95%CI 1.17-2.42, P= 0.005).ConclusionsThe consensus pronuclear score may be routinely included among criteria for embryo evaluation to increase patients' chance of becoming pregnant.

Project description:Congenital adrenal hyperplasia (CAH) is one of the most frequent autosomal recessive diseases in Europe. Treatment is a challenge for pediatric endocrinologists. Important parameters to judge the outcome are adult height and menstrual cycle. We report the follow-up from birth to adulthood of two Caucasian sisters with salt-wasting CAH due to the same mutation, homozygosity c.290-13A>G (I2 splice), in the 21-hydroxylase gene. Their adherence to treatment was excellent. Our objective was to distinguish the effects of treatment with hydrocortisone (HC) and fludrocortisone (FC) on final height (FH) from constitutional factors. The older girl (patient 1), who showed virilized genitalia Prader scale III-IV at birth, reached FH within familial target height at 18 years of age. Menarche occurred at the age of 15. Her menstrual cycles were always irregular. Total pubertal growth was normal (29 cm). She showed a growth pattern consistent with constitutional delay. The younger sister (patient 2) was born without masculinization of the genitalia after her mother was treated with dexamethasone starting in the fourth week of pregnancy. She reached FH at 16 years of age. Her adult height is slightly below familial target height. Menarche occurred at the age of 12.5, followed by regular menses. Total pubertal growth was normal (21 cm). The average dose of HC from birth to FH was 16.7 mg/m2 in patient 1 and 16.8 mg/m2 in patient 2. They received FC once a day in doses from 0.05 to 0.1 mg. Under such therapy, growth velocity was normal starting from the age of 2.5 years with an overall average of +0.2 SD in patient 1 and -0.1 SD in patient 2, androstenedione levels were always within normal age range. Similarly, BMI and blood pressure were always normal, no acne and no hirsutism ever appeared. In conclusion, two siblings with the same genetic form of 21-hydroxylase deficiency and excellent adherence to medication showed different growth and menstrual cycle patterns, rather related to constitutional factors than to underlying CAH. In addition, the second patient represents an example of successful in utero glucocorticoid treatment to prevent virilization of the external genitalia.

Dataset Information

Using Unlabeled Information of Embryo Siblings from the Same Cohort Cycle to Enhance In Vitro Fertilization Implantation Prediction.

Publications

Using Unlabeled Information of Embryo Siblings from the Same Cohort Cycle to Enhance In Vitro Fertilization Implantation Prediction.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets