Search

Abstract The utilization of neural networks in assisted reproductive technology is essential due to their ability to process complex and multidimensional data inherent in IVF procedures, offering opportunities for clinical outcome prediction, personalized treatment implementation, and overall advancement in fertility treatment. The aim of this study was to develop a novel approach to IVF laboratory data analysis, employing deep neural networks to predict the likelihood of clinical pregnancy occurrence within an individual treatment cycle, integrating both key performance indicators and clinical data. We conducted a retrospective analysis spanning 11 years, encompassing 8732 treatment cycles, to extract the most relevant features to our goal and train the model. Internal validation was performed on 1600 preimplantation genetic testing for aneuploidy embryo transfers, while external was conducted across two independent clinics (over 10,000 cases). Leveraging recurrent neural networks, our model demonstrates high accuracy in predicting the likelihood of clinical pregnancy within specific IVF treatment cycles (AUC = 0.68–0.86; test accuracy = 0.78, F1 score = 0.71, sensitivity = 0.62; specificity = 0.86) comparable to time-lapse system but with a simpler approach. Our model facilitates both retrospective analysis of outcomes and prospective evaluation of clinical pregnancy chances, thus presenting a promising avenue for quality management programs and promotes their realization in medical centers.

Abstract Background The 25-hydroxyvitamin D3 (25 (OH) D3) is crucial for follicular development. This study aimed to investigate the relationship between the level of 25 (OH) D3 in endometriosis patients, pregnancy outcomes of in vitro fertilization (IVF), and the underlying mechanism. Methods The 25 (OH) D3 levels in serum and follicular Fluid (FF) samples were detected using enzyme-linked immunosorbent assay (ELISA). Clinical features and pregnancy outcomes of endometriosis patients were also compared between the deficient group (

Background: Infertility treatment methods that are used today have a limited (or little) success rate, and patients bear a lot of financial and emotional burden to get pregnant. Recently, artificial intelligence has been proposed to evaluate gametes better and choose the best embryo for transfer to the uterus. This study investigated the financial benefit of using artificial intelligence for infertility treatment. Materials and Methods: We aim to evaluate the effectiveness of AI in IVF, comparing AI model performance with standard methods and introducing a novel method to measure financial benefits in healthcare resource allocation. Results: Achieving 75% accuracy, AI significantly outperformed standard methods, reducing the likelihood of discarding viable embryos. This technology streamlines the IVF process, leading to shorter treatment cycles and a cost reduction of 1500 dollars per cycle. Conclusion: The integration of AI in IVF represents a paradigm shift, improving success rates, cost-efficiency, and patient experiences. Further research and adoption of AI-driven embryo selection can revolutionize infertility treatments, benefiting both patients and healthcare systems.

Many factors associated with assisted reproductive technologies significantly influence the success of pregnancy after in vitro fertilization (IVF) either directly or indirectly. These factors include sperm processing techniques, egg retrieval, intrauterine artificial insemination, intracytoplasmic sperm injection, and embryo transfer. Among these technologies, sperm quality is one of the most critical factors for a successful IVF pregnancy. The method used for sperm processing plays a crucial role in determining the quality of sperm. Several widely used sorting techniques, such as conventional swim-up, density gradient centrifugation, magnetic activated cell sorting, and hyaluronic acid, have been extensively compared in various studies. Previous studies have shown that each sperm processing method causes varying degrees of sperm damage, particularly in sperm motility, concentration, morphological features, viability, and DNA integrity. However, sperm processing techniques have been developed slowly, and the impact of these methods on pregnancy rates is still unclear. Further exploration is needed. In this review, we aim to compare the results of different sperm processing techniques concerning sperm quality and IVF pregnancy rates. We will also discuss possible clinical approaches, such as microfluidics and integrated approaches, for testing and improving sperm quality.

Kidney transplantation (KT), the optimal treatment for stage 5 chronic kidney disease (CKD), restores impaired fertility in most women of reproductive age. However, infertility occurs in some patients after successful KT. We present our own experience of overcoming secondary tubal infertility by in vitro fertilization (IVF). The patient was a 36-year-old with a transplanted kidney, who had lost two pregnancies in the past due to severe preeclampsia (PE). After the second attempt on cryo-thawed embryo transfer against the background of hormone replacement therapy, one embryo was transferred into the uterus, resulting in pregnancy. Gestational diabetes mellitus (GDM) was diagnosed in the first trimester, and a diet was prescribed. Immunosuppression with tacrolimus, azathioprine and methylprednisolone, prophylaxis of PE with low molecular weight heparin and antiplatelet drugs were administered during pregnancy. Elective cesarean section was performed at 37–38 weeks and a healthy boy was born, weighing 2760 g (25th percentile), 48 cm tall (36th percentile). A stay in the neonatal intensive care unit was not required. The baby is growing and developing normally, the mother’s renal graft function is satisfactory. So, IVF can be successfully used in post-KT patients with infertility issues, provided that the IVF program is carefully controlled, and the pregnancy is managed in a multidisciplinary manner.

Abstract The factors that cause a preterm birth (PTB) are not completely understood up to date. Moreover, PTB is more common in pregnancies achieved by in-vitro fertilization (IVF) than in spontaneous pregnancies. Our aim was to compare the composition of vaginal microbiome at 12 weeks of gestation between women who conceived naturally or through IVF in order to study whether IVF PTB-risk could be related to vaginal microbiome composition. We performed an observational, prospective and multicentre study among two public hospitals and a fertility private clinic in Spain. Vaginal swabs from 64 pregnant women at 12 weeks of gestation were collected to analyse the microbiome composition by sequencing the V3–V4 region of the 16S rRNA. Our results showed that the vaginal microbiome signature at 12 weeks of pregnancy was different from women who conceived naturally or through IVF. The beta diversity and the genus composition were different between both cohorts. Gardnerella, Neisseria, Prevotella, and Staphylococcus genus were enriched genus in the vaginal microbiome from the IVF group, allowing us to create a balance model to predict both cohorts. Moreover, at species level the L. iners abundance was higher and L. gasseri was lower in the IVF group. As a conclusion, our findings were consistent with a proposed framework in which IVF pregnancy are related to risk for preterm birth (PTB) suggesting vaginal microbiome could be the reason to the relation between IVF pregnancy and risk for PTB.

Abstract Objective To investigate whether seasonal variations and meteorological factors influence pregnancy outcomes in women undergoing in vitro fertilization-embryo transfer (IVF-ET) treatment. Design Retrospective cohort study. Setting University-affiliated reproductive medical center. Subjects Women aged 0.050). Multivariate logistic regression analysis showed significant seasonal variation in clinical pregnancy (OR = 1.643, 95% CI = 1.203–2.243; P = 0.002), and that a higher daily average temperature at the time of ovulation induction increased the clinical pregnancy rate (OR = 1.012, 95% CI = 1.001–1.022; P = 0.031). Conclusions In women younger than 35 years who undergo IVF treatment, the season and ambient temperature on the date of the beginning of ovulation induction may have an impact on embryo development and clinical pregnancy.

Background: Infertility treatment methods that are used today have a limited (or little) success rate, and patients bear a lot of financial and emotional burden to get pregnant. Recently, artificial intelligence has been proposed to evaluate gametes better and choose the best embryo for transfer to the uterus. This study investigated the financial benefit of using artificial intelligence for infertility treatment. Materials and Methods: We aim to evaluate the effectiveness of AI in IVF, comparing AI model performance with standard methods and introducing a novel method to measure financial benefits in healthcare resource allocation. Results: Achieving 75% accuracy, AI significantly outperformed standard methods, reducing the likelihood of discarding viable embryos. This technology streamlines the IVF process, leading to shorter treatment cycles and a cost reduction of 1500 dollars per cycle. Conclusion: The integration of AI in IVF represents a paradigm shift, improving success rates, cost-efficiency, and patient experiences. Further research and adoption of AI-driven embryo selection can revolutionize infertility treatments, benefiting both patients and healthcare systems. [ABSTRACT FROM AUTHOR]

Many factors associated with assisted reproductive technologies significantly influence the success of pregnancy after in vitro fertilization (IVF) either directly or indirectly. These factors include sperm processing techniques, egg retrieval, intrauterine artificial insemination, intracytoplasmic sperm injection, and embryo transfer. Among these technologies, sperm quality is one of the most critical factors for a successful IVF pregnancy. The method used for sperm processing plays a crucial role in determining the quality of sperm. Several widely used sorting techniques, such as conventional swim-up, density gradient centrifugation, magnetic activated cell sorting, and hyaluronic acid, have been extensively compared in various studies. Previous studies have shown that each sperm processing method causes varying degrees of sperm damage, particularly in sperm motility, concentration, morphological features, viability, and DNA integrity. However, sperm processing techniques have been developed slowly, and the impact of these methods on pregnancy rates is still unclear. Further exploration is needed. In this review, we aim to compare the results of different sperm processing techniques concerning sperm quality and IVF pregnancy rates. We will also discuss possible clinical approaches, such as microfluidics and integrated approaches, for testing and improving sperm quality. [ABSTRACT FROM AUTHOR]

An amendment to this paper has been published and can be accessed via the original article.

ObjectiveThe purpose of this study was to clarify the influence of the vanishing twin (VT) on the perinatal outcomes in the surviving singleton and further identify the susceptible window.Study designRetrospective cohort study.MethodsA total of 636 survivors of a vanished co-twin and 11,148 singleton controls were enrolled. The exposed group was further divided into early VT (EVT, VT ≤13 weeks, N = 593) and late VT subgroups (LVT, VT >13 weeks, N = 43) according to the gestational age of the twin vanishing. All participants were conceived through in vitro fertilization (IVF). Perinatal outcomes including gestational age, birthweight, and the incidence of preterm birth (PTB), low birthweight (LBW), small for gestational age (SGA), neonatal intensive care unit (NICU) admission, umbilical cord abnormality, jaundice of the newborn, and oligohydramnios were compared among the groups.ResultsIn our birth cohort, about 5.4% of all singleton deliveries originated from vanishing twin pregnancies. Compared with the singletons, both early and late VT pregnancy had a significantly lower birth weight (3337.57±532.24 g and 2916.05±526.07 g vs. 3446.15±526.07 g; p < 0.001 and p < 0.001), more frequent neonatal jaundice (47.0% and 60.5% vs. 40.6%; p = 0.002 and p = 0.008), and decreased incidence of umbilical cord abnormality (15.5% and 7.0% vs. 19.9%; p = 0.009 and p = 0.034). Newborns in the early VT group were more likely to manifest as SGA (5.4% vs. 3.6%, p = 0.002) and suffered oligohydramnios (5.4% vs. 3.4%; p = 0.008) than the primary singletons. In addition, the gestational age of late VT survivors was shorter than that of the controls (37.25 ± 3.25 vs. 39.04 ± 1.63, p = 0.001) and had a significantly higher risk of PTB (30.2% vs. 6.6%; p < 0.001) and NICU admission (27.9% vs. 9.4%, p < 0.001). All differences except for SGA maintain significance after adjusting for maternal age, BMI, and parity.ConclusionsSingletons with a vanished co-twin had worse perinatal outcomes compared with the original singletons, with LVT burden even much on the survival one. Therefore, close monitoring during the perinatal period was suggested in this type of neonates. Moreover, elective single embryo transfer should also be fully considered which could tackle the problem at its root.

Abstract Background There is much value in identifying non-invasive ways of measuring endometrial receptivity, as it has the potential to improve outcomes following in vitro fertilization (IVF). It has been suggested that endometrial echogenicity on the day of hCG administration was a good marker of endometrial receptivity. In the daily practice, we notice that patients with non-homogeneous hyperechoic endometrium on the embryo transfer day usually have lower pregnancy rates. We therefore extended the research onward transformation of echo pattern after hCG trigger to analyze the relationship between endometrial echogenicity transformation and IVF outcomes. Methods A total of 146 infertile women undergoing their first IVF cycle were recruited in the prospective cohort study from August 2017 through August 2018. A series of endometrial echo pattern monitoring was carried out in these patients after hCG trigger: hCG day, from 1 through 3 days after ovum pick-up (OPU + 1, OPU + 2, OPU + 3). Results The endometrial echogenicity value was calculated as the ratio of the hyperechogenic endometrial area over the whole endometrial area. Clinical pregnancy rate and embryo implantation rate had positive relationship with echogenicity value. The ROC curve analysis of endometrial echogenicity showed the area under curve was greatest on the second day after oocyte retrieval (OPU + 1, 2, 3 were 0.738, 0.765, 0.714 respectively) versus pregnancy. Endometrial echogenicity value on OPU + 2 had a higher predictive efficiency, and the cutoff value was 76.5%. The sensitivity was 61.3% and specificity was 82.0%. When putting the cut-off at

Competing Interests: None.