Predictor Of Pregnancy Outcome Research Articles

Prediction of clinical pregnancy outcome after single fresh blastocyst transfer during in vitro fertilization: an ensemble learning perspective

Prediction of clinical pregnancy outcome after single fresh blastocyst transfer during in vitro fertilization: an ensemble learning perspective

Combination of body mass index and body fat percentage in middle and late pregnancy to predict pregnancy outcomes in patients with gestational diabetes in Wenzhou, China: a single-centre retrospective cohort study

ObjectivesThe present study aimed to evaluate whether body mass index (BMI) and body fat percentage (BFP) could be used to predict pregnancy outcomes in patients with gestational diabetes mellitus (GDM).DesignRetrospective...

Maternal mitochondrial DNA copy number and methylation as possible predictors of pregnancy outcomes in a Michigan pregnancy cohort

ABSTRACT Background: Little is understood about the role of mitochondria in pregnancy-related adaptations. Therefore, we evaluated associations of maternal early-to-mid pregnancy mitochondrial DNA copy number (mtDNAcn) and mtDNA methylation with birth size and gestational length. Methods: Michigan women (n=396) provided venous bloodspots at median 11 weeks gestation to quantify mtDNAcn marker NADH-ubiquinone oxidoreductase chain 1 (ND1) using real-time quantitative PCR and mtDNA methylation at several regions within four mitochondria-specific genes using pyrosequencing: MTTF (mitochondrially encoded tRNA phenylalanine), DLOOP (D-loop promoter region, heavy strand), CYTB (cytochrome b), and LDLR (D-loop promoter region, light strand). We abstracted gestational length and birthweight from birth certificates and calculated birthweight z-scores using published references. We used multivariable linear regression to evaluate associations of mtDNAcn and mtDNA methylation with birthweight and birthweight z-scores. Cox Proportional Hazards Models (PHMs) and quantile regression characterized associations of mitochondrial measures with gestational length. We also considered differences by fetal sex. Results: Using linear regression and Cox PHMs, mtDNAcn was not associated with birth outcomes, whereas associations of mtDNA methylation with birth outcomes were inconsistent. However, using quantile regression, mtDNAcn was associated with shorter gestation in female newborns at the upper quantiles of gestational length, but with longer gestational length in males at the lower quantiles of gestational length. Maternal LDLR, DLOOP, and MTTF methylation was associated with longer gestational length in females at the upper quantiles and in males at lower gestational length quantiles. Conclusions: Maternal mtDNAcn and mtDNA methylation were associated with gestational length in babies born comparatively early or late, which could reflect adaptations in mitochondrial processes that regulate the length of gestation.

Dynamic prediction of pregnancy outcome after previous stillbirth or perinatal death: pilot study to establish proof-of-concept and explore method feasibility.

To establish proof-of-concept for the dynamic prediction of adverse pregnancy outcome in women with a history of stillbirth or perinatal death, repeatedly throughout the pregnancy. A retrospective cohort study of women in a subsequent pregnancy following previous perinatal loss, who received antenatal care at a tertiary hospital between January 2014 and December 2017, was used as the basis for exploratory prognostic model development. Models were developed to repeatedly predict a composite adverse outcome (stillbirth or neonatal death, 5-min Apgar score < 7, umbilical artery pH ≤ 7.05, admission to the neonatal intensive care unit for longer than 24 h, preterm birth (< 37 completed weeks) or birth weight < 10th centile) using the findings of sequential ultrasound scans for fetal biometry and umbilical and uterine artery Doppler. In total, 506 participants were eligible, of whom 504 were included in the analysis. An adverse pregnancy outcome was experienced by 110 (22%) participants. The ability to predict the composite outcome using repeated head circumference and estimated fetal weight measurements improved as the pregnancy progressed (e.g. area under the receiver-operating-characteristics curve improved from 0.59 at 24 weeks' gestation to 0.74 at 36 weeks' gestation), supporting proof-of-concept. Predictors to include in dynamic prediction models were identified, including ultrasound measurements of fetal biometry, umbilical and uterine artery Doppler and placental size and shape. The present study supports proof-of-concept for dynamic prediction of adverse outcome in pregnancy following prior stillbirth or perinatal death, which could be used to identify risks earlier in pregnancy, while highlighting methodological challenges and requirements for subsequent large-scale model development studies. © 2024 The Author(s). Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

A review of artificial intelligence applications in in vitro fertilization.

The field of reproductive medicine has witnessed rapid advancements in artificial intelligence (AI) methods, which have significantly enhanced the efficiency of diagnosing and treating reproductive disorders. The integration of AI algorithms into the in vitro fertilization (IVF) has the potential to represent the next frontier in advancing personalized reproductive medicine and enhancing fertility outcomes for patients. The potential of AI lies in its ability to bring about a new era characterized by standardization, automation, and an improved success rate in IVF. At present, the utilization of AI in clinical practice is still in its early stages and faces numerous ethical, regulatory, and technical challenges that require attention. In this review, we present an overview of the latest advancements in various applications of AI in IVF, including follicular monitoring, oocyte assessment, embryo selection, and pregnancy outcome prediction. The aim is to reveal the current state of AI applications in the field of IVF, their limitations, and prospects for future development. Further studies, which involve the development of comprehensive models encompassing multiple functions and the conduct of large-scale randomized controlled trials, could potentially indicate the future direction of AI advancements in the field of IVF.

Fetal Fraction of Cell-Free DNA in the Prediction of Adverse Pregnancy Outcomes: A Nationwide Retrospective Cohort Study.

To assess the added value of fetal fraction of cell-free DNA in the maternal circulation in the prediction of adverse pregnancy outcomes. Retrospective cohort study. Nationwide implementation study on non-invasive prenatal testing (NIPT; TRIDENT-2 study). Pregnant women in the Netherlands opting for NIPT between June 2018 and June 2019. Two logistic regression prediction models were constructed for each adverse pregnancy outcome. The first model (base model) included prognostic clinical parameters that were selected from existing first-trimester prediction models for adverse pregnancy outcomes. The second model (fetal fraction model) included fetal fraction as a predictor on top of the prognostic clinical parameters included in the base model. The added prognostic value of fetal fraction was assessed by comparing the base and fetal fraction models in terms of goodness of fit and predictive performance. Likelihood ratio test (LRT), area under the curve (AUC) and Integrated Discrimination Improvement (IDI) index. The study cohort consisted of 56 110 pregnancies. The incidence of adverse pregnancy outcomes was 5.7% for hypertensive disorders of pregnancy (HDP; n = 3207), 10.2% for birthweight < p10 (n = 5726), 3.2% for birthweight < p2.3 (n = 1796), 3.4% for spontaneous preterm birth (sPTB; n = 1891), 3.4% for diabetes (n = 1902) and 1.3% for congenital anomalies (n = 741). Adding fetal fraction to the base model improved model fit for HDP, birthweight < p10, birthweight < p2.3, all sPTB, and diabetes, but not for congenital anomalies (LRT p < 0.05). For HDP, the AUC improved from 0.67 to 0.68 by adding fetal fraction to the base model (p = 0.14) with an IDI of 0.0018 (p < 0.0001). For birthweight < p10, the AUC improved from 0.65 to 0.66 (p < 0.0001) with an IDI of 0.0023 (p < 0.0001). For birthweight < p2.3, the AUC improved from 0.67 to 0.69 (p < 0.0001) with an IDI of 0.0011 (p < 0.0001). For all sPTB, the AUC was similar for both models (AUC 0.63, p = 0.021) with an IDI of 0.00028 (p = 0.0023). For diabetes, the AUC was similar (AUC 0.72, p = 0.35) with an IDI of 0.00055 (p = 0.00015). Fetal fraction has statistically significant but limited prognostic value in the prediction of adverse pregnancy outcomes in addition to known prognostic clinical parameters.

Ultrasound assessment of embryo cardiac function as a predictive criterion of adverse pregnancy outcome

Purpose to evaluate the value of the embryo/fetus heart rate (HR) in early pregnancy assessed by ultrasound for the formation of a group at high risk of adverse pregnancy outcomes.Materials and methods. A retrospective analysis of ultrasound examinations of 1073 pregnant women at 5+0–10+6 weeks was carried out. The embryo/fetus heart rate was compared with the gestational age calculated by the crown rump length (CRL) and the date of the last menstruation period (LMP). Retrospectively, all examined pregnant women were divided into two groups: group 1—with intrauterine embryo death before 14 weeks of pregnancy (n = 107); group 2—with prolongation of pregnancy until the second trimester (n = 966). When analyzing the data array using a decision tree, the embryo heart rate was assessed at various stages of pregnancy by LMP, CRL, and regardless of the exact period of pregnancy.Results. Analysis of heart rate values at different stages of pregnancy by LMP showed significant differences in heart rate between groups, the cases of later embryo loss characterized by lover heart rate values. There were no significant differences in heart rate between the groups at different stages of pregnancy by CRL (significant differences were obtained only at 8+0–9+6 weeks). Cut-off values of embryo heart rate for prediction of adverse pregnancy outcomes have been proposed for different stages of pregnancy, as well as a universal cut-off for the entire embryonic period.Conclusion. The proposed cut-off values of embryo heart rate for different stages of pregnancy, calculated by LMP, may be used for timely prediction of adverse pregnancy outcomes. When the exact gestational age is unknown, a universal heart rate cut-off value of &lt;116 bpm may be used. All proposed HR cut-off values were characterized by high specificity, but none of them by high sensitivity. A sensitivity of HR cut-off values can be increased by the use in combination with other ultrasound and clinical signs of adverse pregnancy outcome.

Longitudinal biomonitoring of mycotoxin exposure during pregnancy in the Yale pregnancy Outcome Prediction study

Mycotoxins are fungal toxins that may trigger adverse health effects in pregnant women and their unborn children. Yet, data is scarce on the dynamic exposure patterns of mycotoxins in pregnant women, especially in the United States. This study assessed mycotoxin exposure profiles (n = 50) from the Yale Pregnancy Outcome Prediction Study (YPOPS) cohort at four distinct time points. Multi-analyte human biomonitoring (HBM) assays based on liquid chromatography tandem mass spectrometry (LC-MS/MS), were developed for human serum and plasma matrices. The serum method was applied, together with an established urine method, to quantify mycotoxin levels in longitudinally collected matched serum (n = 200) and spot urine (n = 200) samples throughout pregnancy. The serum samples were mostly contaminated by the potential carcinogen ochratoxin A (detection rate: 49 %; median: 0.09 ng/mL), the hepato- and nephrotoxic citrinin (detection rate: 32 %; median: 0.02 ng/mL) and two enniatins (EnnB; detection rate: 97 %; median: 0.01 ng/mL and EnnB1; detection rate: 12 %; median: 0.003 ng/mL) which may act as immunotoxins. The most prevalent mycotoxins quantified in urine included deoxynivalenol (detection rate: 99 %; median: 23 ng/mL), alternariol monomethyl ether (detection rate: 69 %; median: 0.04 ng/mL), and zearalenone (detection rate: 63 %; median: 0.16 ng/mL). Seven other biomarkers of exposure including the highly estrogenic α-zearalenol and genotoxic Alternaria toxins, were also determined. Carcinogenic aflatoxins were not detected in any of the samples. Exposure assessment was based on the urinary data and performed by calculating the probable daily intakes (PDIs) and comparing the human biomonitoring guidance value (HBM-GV) for deoxynivalenol. The results showed that the individuals exceeded the tolerable daily intake (TDI) for deoxynivalenol and zearalenone on average at 28 % and 2 % over the different time points. Using the HBM-GV approach, the average exceedances for deoxynivalenol increased to 48 % indicating high exposure. For all the samples in which ochratoxin A was quantified, the estimated margin of exposure for neoplastic effects was below 10,000, indicating possible health concerns. Overall, this study showed that pregnant women were exposed to several regulated and emerging mycotoxins and that exposome-scale assessment should be a future priority in susceptible populations to better characterize xenobiotic exposure.

Effect and Predictive Value of Blood HbA1c, FBG, 2hPBG, and FINS on the Pregnancy Outcome in Patients with Gestational Diabetes Mellitus.

This study aimed to investigate the effects of hemoglobin A1c (HbA1c), fasting blood glucose (FBG), 2-hours postprandial blood glucose (2hPBG), and fasting insulin (FINS) levels on pregnancy outcomes and their predictive value in patients with gestational diabetes mellitus (GDM). A total of 109 pregnant women with GDM (GDM group) were included and assayed for serum FBG, 2hPBG, HbA1c, and FINS levels. The incidence of adverse pregnancy outcomes was recorded. GDM patients were divided into the poor pregnancy outcome group and the favorable pregnancy outcome group and analyzed for HbA1c, FBG, 2hPBG, and FINS. The predictive value of serum index combined detection on GDM pregnancy outcome was assessed, and the effect of serum indices on pregnancy outcome was evaluated in GDM patients with logistic regression. In the GDM group, there were 8 cases of premature membranes breaking (7.34%), 6 cases of premature delivery (5.50%), 3 cases of hyperamniotic fluid (2.75%), 2 cases of neonatal asphyxia (1.83%), 5 cases of fetal growth restriction (4.59%), and 3 cases of low-birth-weight infants (2.75%). The total incidence of adverse preg-nancy outcomes was 24.77% (27/109). HbA1c, FBG, 2hPBG, and FINS in the poor pregnancy outcome group were higher than those in the favorable pregnancy outcome group. The AUC value of blood biochemical indicators combined detection in predicting pregnancy outcome in GDM patients was higher than of HbA1c, FBG, 2hPBG, and FINS alone detection. HbA1c ≥ 6.94%, FBG ≥ 7.18 mmol/L, 2hPBG ≥ 9.36 mmol/L, and FINS ≥ 13.07 U/L were the risk factors affecting pregnancy outcomes in GDM patients. The changes of HbA1c, FBG, 2hPBG, and FINS levels in GDM patients are associated with adverse pregnancy outcomes, and the combined detection of serum indicators has predictive value for pregnancy outcomes in GDM patients.

Hsa_circ_0088196 Predicts Adverse Pregnancy Outcomes in Preeclampsia Patients and Contributes to Endothelial Cell Injury Via Modulating the miR-145-5p/FLT1 Axis.

Preeclampsia (PE) is a specific hypertension-related disease in pregnancies, causing adverse pregnancy outcomes. Endothelial cell dysfunction is a major etiology of PE, of which the regulation could affect disease progression. This study focused on hsa_circ_0088196, evaluating its clinical significance in PE and its effect on endothelial cell injury, aiming to identify a novel biomarker for PE and complete its regulating mechanism in disease development. The study enrolled 165 normal pregnancies and 165 pregnancies with gestational hypertension. The significance of hsa_circ_0088196 in discriminating gestational hypertension, predicting PE, and predicting adverse pregnancy outcomes was evaluated based on its serum expression. The effect and mechanism of hsa_circ_0088196 in HUVEC injury were assessed by CCK8, Transwell, ELISA, and western blotting. Significant downregulation of hsa_circ_0088196 could distinguish gestational hypertension pregnancies and predict the risk of PE. Gestational hypertension pregnancies developed PE showed a lower serum hsa_circ_0088196 level, which also discriminated PE patients, predicted severe conditions and adverse pregnancy outcomes. Overexpressing hsa_circ_0088196 alleviated the enhanced proliferation, migration, inflammation, and angiogenesis by hypoxia/reoxygenation (H/R), which was reversed by miR-145-5p. Silencing miR-145-5p showed similar effects on H/R-induced endothelial cell injury, which was reversed by FLT1. Moreover, FLT1 was positively regulated by hsa_circ_0088196, indicating its involvement in the regulation of HUVEC injury by hsa_circ_0088196. Reduced serum hsa_circ_0088196 served as a biomarker for the diagnosis of gestational hypertension, risk evaluation of PE, and the prediction of adverse pregnancy outcomes. hsa_circ_0088196 suppressed endothelial cell injury induced by H/R through modulating the miR-145-5p/FLT1 axis.

Predicting Unfavorable Pregnancy Outcomes in Polycystic Ovary Syndrome (PCOS) Patients Using Machine Learning Algorithms.

Background and Objectives: Polycystic ovary syndrome (PCOS) is a complex disorder that can negatively impact the obstetrical outcomes. The aim of this study was to determine the predictive performance of four machine learning (ML)-based algorithms for the prediction of adverse pregnancy outcomes in pregnant patients diagnosed with PCOS. Materials and Methods: A total of 174 patients equally divided into 2 groups depending on the PCOS diagnosis were included in this prospective study. We used the Mantel-Haenszel test to evaluate the risk of adverse pregnancy outcomes for the PCOS patients and reported the results as a crude and adjusted odds ratio (OR) with a 95% confidence interval (CI). A generalized linear model was used to identify the predictors of adverse pregnancy outcomes in PCOS patients, quantifying their impact as risk ratios (RR) with 95% CIs. Significant predictors were included in four machine learning-based algorithms and a sensitivity analysis was employed to quantify their performance. Results: Our crude estimates suggested that PCOS patients had a higher risk of developing gestational diabetes and had a higher chance of giving birth prematurely or through cesarean section in comparison to patients without PCOS. When adjusting for confounders, only the odds of delivery via cesarean section remained significantly higher for PCOS patients. Obesity was outlined as a significant predictor for gestational diabetes and fetal macrosomia, while a personal history of diabetes demonstrated a significant impact on the occurrence of all evaluated outcomes. Random forest (RF) performed the best when used to predict the occurrence of gestational diabetes (area under the curve, AUC value: 0.782), fetal macrosomia (AUC value: 0.897), and preterm birth (AUC value: 0.901) in PCOS patients. Conclusions: Complex ML algorithms could be used to predict adverse obstetrical outcomes in PCOS patients, but larger datasets should be analyzed for their validation.

Perspectives of pregnant women on broadening the scope of noninvasive prenatal testing from screening for foetal aneuploidies to prediction of adverse pregnancy outcomes: Aqualitative study.

To explore the perspectives of pregnant women on broadening the scope of noninvasive prenatal testing (NIPT) from screening for foetal aneuploidies to prediction of adverse pregnancy outcomes. Four online focus groups (n=23 participants) and 14 individual semi-structured interviews were conducted. Participants included pregnant women with and without a history of adverse pregnancy outcomes. Both women at low and high risk of adverse pregnancy outcomes had a positive attitude towards using NIPT to predict adverse pregnancy outcomes. Perceived benefits included the possibility to potentially improve maternal and foetal outcomes by taking risk-reducing measures and/or intensified monitoring during pregnancy and the ability to mentally prepare for the potential adverse outcome. Perceived concerns included anxiety and stress caused by a high-risk test result, a false sense of control over pregnancy, and potential false reassurance. Additionally, women reasoned that broadening the scope of NIPT could increase the complexity of prenatal screening and raised concerns on the combined screening aims in one test (prediction of adverse pregnancy outcomes to improve foetal and maternal health vs. screening for foetal aneuploidies to increase reproductive autonomy). On a societal level, considerations on the risk of medicalising pregnancy and overall pressure to opt for NIPT were mentioned. In general, pregnant women have a positive attitude towards broadening the scope of NIPT to the prediction of pregnancy outcomes, although some concerns are acknowledged.

Impact of obesity on the perinatal vaginal environment and bacterial microbiome: effects on birth outcomes.

Introduction. Lactobacillus species predominate the human vagina and are associated with positive vaginal health, including an acidic pH (<4.5). The prevalence of vaginal Lactobacilli increases with increased oestrogen due to increased glycogen production within the vagina. Lactobacilli produce lactic acid, thereby lowering vaginal pH, preventing growth of other bacteria, and lowering microbial diversity. Lower placental oestrogen levels in obese pregnant women could dampen the mechanism to initiate this process, which may be associated with vaginal dysbiosis and unfavourable pregnancy outcomes.Hypothesis. We hypothesize that oestrogen and glycogen levels will be lower, vaginal pH will be higher, and vaginal microbiome diversity will be greater during pregnancy in obese and overweight women compared to healthy weight women.Aim. Pregnancy complications (e.g. preterm birth) are more common in overweight and obese women. If vaginal dysbiosis plays a role, and quantifiable predictors of this increased risk can be determined, these measures could be used to prospectively identify women at risk for pregnancy complications early in pregnancy.Methodology. Vaginal samples were collected at 10-14, 18-24, 26-30, and 34-37 weeks gestation and at delivery from 67 pregnant participants (23 healthy weight, 22 overweight, 22 obese). A blood sample to quantify serum oestrogen was collected at 10-14 weeks. Vaginal samples were collected to test vaginal pH using pH paper, glycogen abundance using fluorometry, and the vaginal microbiome using 16S rRNA amplicon sequencing.Results. Vaginal pH was higher in obese participants compared to healthy weight participants (P=<0.001). Vaginal glycogen levels increased over time in obese participants (P=0.033). The vaginal bacterial alpha diversity was higher in obese participants compared to healthy weight participants (P=0.033). The relative abundances of Peptoniphilus and Anaerococcus were increased in overweight and obese participants, as well as in complicated pregnancies, at 10-14 weeks gestation.Conclusion. The relative abundance of specific vaginal bacteria, like Peptoniphilus and Anaerococcus, in early pregnancy could predict pregnancy outcomes. Our goal is to use the information gathered in this pilot study to further determine the feasibility of assessing the vaginal environment during pregnancy to identify women at risk for negative pregnancy and birth outcomes in the context of a larger study.

Biochemical Markers in the Prediction of Pregnancy Outcome in Gestational Diabetes Mellitus.

Background and Objectives: Gestational diabetes mellitus (GDM) may impact both maternal and fetal/neonatal health. The identification of prognostic indicators for GDM may improve risk assessment and selection of patient for intensive monitoring. The aim of this study was to find potential predictors of adverse pregnancy outcome in GDM and normoglycemic patients by comparing the levels of different biochemical parameters and the values of blood cell count (BCC) between GDM and normoglycemic patients and between patients with adverse and good outcome. Materials and Methods: Prospective clinical study included 49 patients with GDM (study group) and 44 healthy pregnant women (control group) who underwent oral glucose tolerance test (OGTT) at gestational age of 24-28 weeks. At the time of OGTT peripheral blood was taken for the determination of glucose levels, insulin, glycated hemoglobin, lipid status, homeostatic model assessment, BCC, iron and zinc metabolism, liver function, kidney function and inflammatory status. Each group was divided into two subgroups-normal and poor pregnancy outcome. Results: Higher RBC, hemoglobin concentration, hematocrit value, fasting glucose, uric acid and fibrinogen were found in GDM patients compared to control group. In GDM patients with poor pregnancy outcome values of fibrinogen, ALT, sedimentation rate, granulocyte and total leukocyte counts were elevated, while the serum level of zinc was significantly lower. Higher level of fibrinogen was found in normoglycemic patients with adverse pregnancy outcomes. ROC curve was constructed in order to assess fibrinogen's biomarker potential. The established AUC value for diagnostic ROC was 0.816 (p < 0.001, 95% CI 0.691-0.941), while the AUC value for assessing fibrinogen's potential to predict poor pregnancy outcome in GDM was 0.751 (p = 0.0096, 95% CI 0.561-0.941). Conclusions: The results of our study demonstrated that the best prognostic potential in GDM showed inflammation related parameters, identifying fibrinogen as a parameter with both diagnostic and prognostic ability.

Role of umbilical artery and fetal middle cerebral artery doppler study in prediction of pregnancy outcome in high-risk pregnancies

Role of umbilical artery and fetal middle cerebral artery doppler study in prediction of pregnancy outcome in high-risk pregnancies

Clinical Significance of miR-339-5p in Early Diagnosis and Predicting Pregnancy Outcome of Chinese Patients with Liver Injury in Pregnancy

Clinical Significance of miR-339-5p in Early Diagnosis and Predicting Pregnancy Outcome of Chinese Patients with Liver Injury in Pregnancy

Prediction of Pregnancy Outcomes in Women with Threatened Abortion Using Ultrasound Parameters, Uterine Artery Doppler, and Serum Progesterone Levels: A Prospective Cohort Study

Prediction of Pregnancy Outcomes in Women with Threatened Abortion Using Ultrasound Parameters, Uterine Artery Doppler, and Serum Progesterone Levels: A Prospective Cohort Study

Preliminary application of real-time shear wave elastography to evaluate endometrial receptivity and predict pregnancy outcome.

Endometrial receptivity is crucial for the establishment of a healthy pregnancy outcome. Previous research on endometrial receptivity primarily examined endometrial thickness, endometrial echo types, and endometrial blood supply. To explore the differences in the elastic modulus of the endometrium in women with various pregnancy outcomes by real-time shear wave elastography (SWE) and to investigate its application value in evaluation of endometrial receptivity. A total of 205 pregnant women who were admitted at Wenzhou People's Hospital between January 2021 and December 2022 were selected. Three-dimensional transvaginal sonography and real-time shear wave elastography were performed in the proliferative phase and receptive phase of the endometrium, and the average elastic modulus of the endometrium in the two phases was obtained and compared. According to whether the pregnancy was successful or not, the participants were divided into the pregnancy group (n= 72) and non-pregnancy group (n= 133), and the differences in intimal thickness, 3D blood flow parameters, and average elastic modulus of intima were compared between the two groups. The average elastic modulus of the endometrium in the proliferative phase and receptive phase was (23.92 ± 2.31) kPa and (11.82 ± 2.24) kPa, respectively, and the difference was statistically significant P< 0.05. The average elastic modulus of the endometrium in the pregnancy group and non-pregnancy group was (9.97 ± 1.08) kPa and (12.82 ± 2.06) kPa, respectively, and the difference was statistically significant P< 0.05. The area under the curve of predicting pregnancy by the average elastic modulus of the endometrium in the receptive phase was 0.888 (0.841∼0.934), with corresponding P value < 0.05. The critical value was 11.15, with a corresponding sensitivity of 81.7% and specificity of 78.2%. Real-time shear wave elastography can quantitatively evaluate endometrial elasticity, indirectly reflect the endometrial phase, and provide a new diagnostic concept for evaluating endometrial receptivity and predicting pregnancy outcome in infertile patients.

P-174 Are new machine learning (ML) models worth it: Equivalence of iDA, KIDscore, and Gardner Scoring in Predicting IVF Pregnancy

Abstract Study question Is there a significant difference in predicting pregnancy outcomes among iDAScore 1.0, KIDScoreD5, and Gardner Score in elective blastocyst transfers? Summary answer Contrary to previous studies, iDAScore v1.0 does not demonstrate a significant Receiver Operating Characteristic (ROC) curve advantage over the traditional Scores in predicting pregnancy outcomes. What is known already iDAScore 1.0, a deep neural network integrated into the EmbryoScope system, and KIDscoreD5 have shown potential in ML-driven embryo assessment, potentially easing the workload of embryologists. While recent studies have highlighted their superior performance in predicting pregnancy outcomes, our study offers a contrasting perspective. Study design, size, duration This retrospective analysis encompassed 1762 embryos from 1112 cycles with 1424 fresh and 338 frozen single embryo transfer cycles conducted from November 2018 to September 2023 across three IVF clinics in New Zealand. No PGT cases were included. All embryos that fulfilled the defined study criteria and transferred were included in this analysis. An extended Gardner Scoring was used at our clinics: A, B, C and X, where X being poorest grades, get discarded. Participants/materials, setting, methods Retrospectively computed KID and iDAScores were analyzed alongside the pregnancy prediction accuracy of conventional grading. Gardner scores were converted to a ranked ordinal value with ‘AA’ (5), ‘AB’ and ‘BA’ at 4, ‘BB’ at 3, and both ‘AC’, ‘BC’ as 2 and ‘CC’ as 1 among the age groups; &amp;lt;35, 35-37, 38-40, 41-42, &amp;gt;42. Differences in overall predictive capacity were compared via AUC curves within age groups via paired Delong tests. P-values reported are nominal. Main results and the role of chance The study found no statistically significant differences in AUC between any of the 3 tests examined even before adjusting for multiple comparisons. Notably, in 35-37 years olds (n = 495), AUCs were 0.63 for iDAScore, 0.62 for KIDScore, and 0.61 for Gardner criteria, showing a robust ability to predict pregnancy across all methods. Similar patterns were observed in all other age groups, with no significant disparities in pregnancy prediction models (P-value &amp;gt; 0.05). Limitations, reasons for caution Given its retrospective nature, this study has inherent limitations. A prospective, controlled study would provide more definitive insights. Wider implications of the findings ML-based models are innovative, but they do not significantly exceed the predictive ability of traditional embryo assessment across a range of patient ages. Such models are not a panacea yet, but a data tool to increase reproducibility that might have over-promised and under delivered on clinical impact. Trial registration number not applicable

P-444 The battle between a machine learning model, a gynecologist and an embryologist to predict pregnancy outcomes after single day-5 embryo transfer

Abstract Study question Are algorithms more effective than clinicians/embryologists at predicting pregnancy outcomes in the context of Assisted Reproductive Technology (ART) following the transfer of a single blastocyst? Summary answer Evaluation of a pregnancy prediction algorithm, trained on local data and assessed by two ART professionals, yielded an accuracy comparable to a coin toss. What is known already Artificial Intelligence’s ability to synthesize multifaceted embryological and clinical data and process extensive datasets holds promise for elevating IVF success rates through data-driven, individualized treatments. Refining embryo selection through deep learning and computer vision, individualizing treatment protocols, predicting oocyte retrieval after Controlled Ovarian Hyperstimulation (COH) and ultimately predicting Live Birth (LB) following embryo transfer are one of the early promises of this technology. Study design, size, duration A retrospective analysis was conducted on 475 stimulation cycles that resulted in a single day-5 blastocyst transfer (fresh or frozen, classical IVF or ICSI) from January 2015 to January 2022 at the Poissy/Saint-Germain-En-Laye hospital, France. The study encompassed 32 clinical and biological parameters, ranging from general characteristics of patients to controlled ovarian hyperstimulation (COH) details and embryo grading. Exclusively, embryos fertilized with autologous oocytes and sperm were considered, excluding any donor-fertilized embryos. Participants/materials, setting, methods Preliminary testing with Machine Learning algorithms (XGboost, LightGBM, Random Forest (RF), Support Vector Machine (SVM), Multi-layer Perceptron (MLP)) were conducted before selecting XGboost model for this study. Data was split into a training (n = 331) and testing (n = 144) set. Pregnancy outcome predictions (binary) were compared between the model, a clinician, and an embryologist. Feature extraction was conducted, and both professionals were asked to give the top 5 most relevant parameters used to make the pregnancy predictions. Main results and the role of chance The study analyzed 475 stimulation cycles, including 362 frozen and 114 fresh transfers. Participants’ mean age was 33, with a Body Mass Index (BMI) of 24.9. The average Antral Follicle Count (AFC) was 16.8, and the mean starting gonadotropin dose was 225 UI, yielding 8.3 MII oocytes on average. 36 patients were active smokers. Preliminary AUC results showed XGboost leading (AUC = 0.57) compared to LightGBM (AUC = 0.56), Random Forest (AUC = 0.56), SVM (AUC = 0.49), and MLP (AUC = 0.47) in predicting pregnancy outcomes. After hyperparameter optimization via GridSearch, the XGboost model enhanced its AUC to 0.61, outperforming the embryologist (AUC = 0.58) and the gynecologist (AUC = 0.44). Top predictive features identified after feature extraction included endometrial thickness at or before ovulation trigger, AMH levels at patient admission, AFC, BMI, and age. The gynecologist primarily prioritized age, BMI, embryo grading (TE and ICM), and the number of mature oocytes retrieved. The embryologist, valued embryo grading (TE and ICM) foremost, followed by age, smoking status, BMI, and COH duration. Limitations, reasons for caution The study’s limited dataset due to dynamic practices and difficulty maintaining curated data over the years, necessitates caution. The selected 32 parameters from 762 available reflect typical incomplete datasets in such settings, highlighting the importance of careful interpretation and potential need for broader data integration to enhance representativeness and reliability. Wider implications of the findings The findings advocate for developing ART-specific AI, integrating multimodal data and novel parameters, to enhance live birth predictions. This approach underscores the complex synergy between algorithmic precision and clinical expertise in ART, highlighting the stochastic nature of pregnancy prediction and the potential of tailored, data-driven strategies to improve outcomes. Trial registration number not applicable