Can we predict the IVF/ICSI live birth rate?

Clinical data-based modeling of IVF live birth outcome and its application

BACKGROUND

The low live birth rate and difficult decision-making of the in vitro fertilization (IVF) treatment regimen bring great trouble to patients and clinicians. Based on the retrospective clinical data of patients undergoing the IVF cycle, this study aims to establish classification models for predicting live birth outcome (LBO) with machine learning methods.

METHODS

The historical data of a total of 1405 patients undergoing IVF cycle were first collected and then analyzed by univariate and multivariate analysis. The statistically significant factors were identified and taken as input to build the artificial neural network (ANN) model and supporting vector machine (SVM) model for predicting the LBO. By comparing the model performance, the one with better results was selected as the final prediction model and applied in real clinical applications.

RESULTS

Univariate and multivariate analysis shows that 7 factors were closely related to the LBO (with P < 0.05): Age, ovarian sensitivity index (OSI), controlled ovarian stimulation (COS) treatment regimen, Gn starting dose, endometrial thickness on human chorionic gonadotrophin (HCG) day, Progesterone (P) value on HCG day, and embryo transfer strategy. By taking the 7 factors as input, the ANN-based and SVM-based LBO models were established, yielding good prediction performance. Compared with the ANN model, the SVM model performs much better and was selected as the final model for the LBO prediction. In real clinical applications, the proposed ANN-based LBO model can predict the LBO with good performance and recommend the embryo transfer strategy of potential good LBO.

CONCLUSIONS

The proposed model involving all essential IVF treatment factors can accurately predict LBO. It can provide objective and scientific assistance to clinicians for customizing the IVF treatment strategy like the embryo transfer strategy.

Follicle Stimulating Hormone (FSH) as a Predictor of Decreased Oocyte Yield in Patients with Normal Anti-Müllerian Hormone (AMH) and Antral Follicle Count (AFC)

Background

The purpose of the current study was to determine the utility of early follicular phase follicle-stimulating hormone (FSH) testing in patients undergoing in vitro fertilization (IVF).

Methods

This was a retrospective review of patients from 2012 to 2015 at Mayo Clinic in Rochester, Minnesota, USA. Included subjects had a normal anti-Müllerian hormone (AMH) of 1 to 9 ng/ml and antral follicle count (AFC) of 10 to 29. Patients were stratified by FSH level when associated estradiol was less than 50 ng/ml. In total, 225 patients were categorized into three groups: high FSH (FSH ≥10 IU/L; n= 36), normal FSH (>5 IU/L and <10 IU/L; n=170), and low FSH (FSH ≤5 IU/L; n= 19). ANOVA and multiple logistic regression were used for statistical comparisons and for evaluation of the relationships between variables; significance level was set at <0.05.

Results

There were no significant differences in demographics, IVF cycle type, or peak estradiol level between the groups. Patients with a high basal FSH level had a similar clinical pregnancy rate and live birth rate compared to controls and patients with low FSH. High FSH level was associated with decreased follicular development (17 versus 22; p<0.01), oocyte yield (15 versus 18; p=0.02), and embryo yield (8 versus 10; p=0.04) despite higher total doses of gonadotropins.

Conclusion

Patients with normal AMH and AFC levels could be further stratified into lower responders and starting doses of medications can be adjusted based on high basal FSH levels. Therefore, it is suggested to counsel patients on pregnancy outcomes which seem to be quite similar regardless of the FSH level.

Non-coding RNAs from seminal plasma extracellular vesicles and success of live birth among couples undergoing fertility treatment

Background: Infertility remains a global health problem with male-factor infertility accounting for around 50% of cases. Understanding the molecular markers for the male contribution of live birth success has been limited. Here, we evaluated the expression levels of seminal plasma extracellular vesicle (spEV) non-coding RNAs (ncRNAs) in men of couples in relation with those with and without a successful live birth after infertility treatment. Method: Sperm-free spEV small RNA profiles were generated from 91 semen samples collected from male participants of couples undergoing assisted reproductive technology (ART) treatment. Couples were classified into two groups based on successful live birth (yes, n = 28) and (no, n = 63). Mapping of reads to human transcriptomes followed the order: miRNA > tRNA > piRNA > rRNA> "other" RNA > circRNA > lncRNA. Differential expression analysis of biotype-specific normalized read counts between groups were assessed using EdgeR (FDR<0.05). Result: We found a total of 12 differentially expressed spEV ncRNAs which included 10 circRNAs and two piRNAs between the live birth groups. Most (n = 8) of the identified circRNAs were downregulated in the no live birth group and targeted genes related to ontology terms such as negative reproductive system and head development, tissue morphogenesis, embryo development ending in birth or egg hatching, and vesicle-mediated transport. The differentially upregulated piRNAs overlapped with genomic regions including coding PID1 genes previously known to play a role in mitochondrion morphogenesis, signal transduction and cellular proliferation. Conclusion: This study identified novel ncRNAs profiles of spEVs differentiating men of couples with and without live birth and emphasizes the role of the male partner for ART success.

Anti-müllerian hormone as a predictor for live birth among women undergoing IVF/ICSI in different age groups: an update of systematic review and meta-analysis

PURPOSE

To update the evidence of anti-müllerian hormone (AMH) as predictive factors for live birth outcome in women undergoing assisted conception and discover the modulating effect of age.

METHODS

PubMed, Embase, Medline, and Web of Science were searched for studies published until June 2021. We included studies that measured serum AMH levels and reported the subsequent live birth outcomes. Random effects models and hierarchical summary receiver operating characteristics (HSROC) models were used. The QUADAS-2 checklist was employed to assess the quality of the included studies.

RESULTS

We included 27 studies (27,029 women) investigating the relationship between AMH and live birth outcome after assisted conception. The diagnostic odds ratios (DOR) from random effects models were ruled out due to high heterogeneity. Our findings suggested that AMH was associated with live birth. The DOR was 2.21 (95% CI 1.89-2.59), and 2.49 (95% CI 1.26-4.91) for studies on women with unspecified ovarian reserve and women with low ovarian reserve, respectively. The DOR of those with advanced ages was 2.50 (95% CI 1.87-2.60). For younger women, the DOR was 1.41 (95% CI 0.99-2.02). HSROCs showed that AMH had no predictive ability towards live birth in women with diminished ovarian reserve or younger age. Exclusion of Chinese cohorts lowered the heterogeneity.

CONCLUSIONS

This study revealed that AMH had better prediction for live birth in advanced-age women. AMH may have implicative predictive value for assisted conception counseling of couples of advanced ages.

Stimulation Duration in Patients with Early Oocyte Maturation Triggering Criteria Does Not Impact IVF-ICSI Outcomes

Results from studies reporting the optimal stimulation duration of IVF-ICSI cycles are inconsistent. The aim of this study was to determine whether, in the presence of early ovulation-triggering criteria, prolonged ovarian stimulation modified the chances of a live birth. This cross-sectional study included 312 women presenting triggering criteria beginning from D8 of ovarian stimulation. Among the 312 women included in the study, 135 were triggered for ovulation before D9 (D ≤ nine group) and 177 after D9 (D > nine group). The issues of fresh +/− frozen embryo transfers were taken into consideration. Cumulative clinical pregnancy and live-birth rates after fresh +/− frozen embryo transfers were similar in both groups (37% versus 46.9%, p = 0.10 and 19.3% versus 28.2%, p = 0.09, respectively). No patient characteristics were found to be predictive of a live birth depending on the day of ovulation trigger. Postponing of ovulation trigger did not impact pregnancy or live-birth rates in early responders. A patient’s clinical characteristics should not influence the decision process of ovulation trigger day in early responders. Further prospective studies should be conducted to support these findings.

Predictive value of the number of frozen blastocysts in live birth rates of the transferred fresh embryos

Background

Blastocyst development by extended culture in vitro allows the embryos to ‘select’ themselves, thus successful growth to the blastocyst stage is a reflection of the developmental competence of cleavage stage embryos in a cohort. The study aims to determine whether the number of frozen blastocysts is associated with live birth rates of the transferred fresh embryos.

Method

The retrospective study included 8676 cycles of first fresh embryo transfer from January 2016 to June 2019 at a fertility center of a university hospital. The patients with ≥ 10 oocytes retrieved were divided into three groups according to the number of frozen blastocysts: 0 (group 1), 1–2 (group 2), and ≥ 3 (group 3). The primary outcome measure was the live birth. The secondary outcome measures included clinical pregnancy rates and implantation rates. Logistic regression analysis was also performed.

Results

Live birth rates in patients with ≥ 3 and 1–2 frozen blastocysts were 47.6% and 46.1%, respectively, which were significantly higher than that in patients without blastocyst (36.0%). The clinical pregnancy rate in group 3 was 65.1%, which was also significantly higher than the other two groups (47.0% and 59.2%). The implantation rates were 35.5%, 47.6%, and 56.0% in the three groups, respectively (P < 0.001). Compared with groups of frozen blastocysts, 0 frozen blastocyst yielded a lower rate of live birth (the adjusted odds ratio: 0.526, 95% CI: 0.469, 0.612).

Conclusion

In patients with optimal ovarian response that retrieved ≥ 10 oocytes, fresh embryos transfer followed by having blastocysts frozen is a strong indicator of pregnancy achievement, but the number of frozen blastocysts (if not = 0) has limited value in predicting live birth rates.

In-Vitro Fertilization Outcome Predictors in Women With High Baseline Follicle-Stimulating Hormone Levels: Analysis of Over 1000 Cycles From A Tertiary Center

OBJECTIVE

The present study aimed to evaluate reproductive outcomes and determine the predictors of clinical pregnancy and live birth in women with elevated baseline follicle-stimulating hormone (FSH) levels, who have undergone intracytoplasmic sperm injection (ICSI) treatment.

METHODS

This retrospective study included 1011 ICSI cycles of women with high baseline FSH levels (> 10 IU/L), from a tertiary university IVF center between 2010 and 2015. Logistic regression analysis was performed to evaluate the prognostic factors of clinical pregnancy and live birth.

RESULTS

Among the 1011 ICSI cycles, the clinical pregnancy and live birth rates per oocyte retrieval were 19.5% and 14.3%, respectively. The live birth rates were 21.1% and 1.7% in women aged ≤30 years and those aged ≥40 years, respectively. In addition, the live birth rate was 1.47-fold higher in women from whom >3 oocytes were retrieved, compared to those from whom ≤3 oocytes were retrieved (p=0.047). Logistic regression analysis indicated that the age categories ≤30y, 36-39y and ≥40y, level of baseline FSH (≥20 IU/L) and the ovarian response (≤3 or >3 oocytes retrieved) were significantly associated with live birth.

CONCLUSIONS

Our study indicated that age, baseline FSH level, and ovarian response are independent predictive factors for clinical pregnancy and live birth among women with baseline FSH levels >10 IU/L.

Anti-Müllerian hormone as a predictor of pregnancy in women under 35 years with unexplained infertility undergoing ICSI: a retrospective study

BACKGROUND

Anti-Müllerian hormone (AMH) is a well-established marker for the determination of ovarian reserve. However, its role in the prediction of pregnancy is still under debate. In this retrospective study, we aimed to evaluate the relationship of serum AMH levels with pregnancy rates in patients with unexplained infertility undergoing ICSI. Moreover, we compared the predictive value of AMH with that of antral follicle count (AFC).

METHODS

Records of 76 patients under 35 years of age with AMH levels between 1 and 3.5 ng/ml were examined retrospectively. Participants were divided into groups based on their AMH level and age.

RESULTS

AMH levels in women under 30 years were found significantly higher than those in women over 30 years (P=0.033). 57 of 76 patients (75%) were pregnant. Age did not have a significant effect on the pregnancy rates in the selected study group (P=0.252). On the other hand, despite the poor predictive accuracy, serum AMH was shown to have a predictive value with a cut-off point of 1.95 ng/mL. Logistic regression tests demonstrated a higher pregnancy rate (3.396 fold) with an AMH level 1.95 or above. There was no significant relationship between AFC and pregnancy.

CONCLUSIONS

AMH might have a role in the prediction of pregnancy after ICSI in patients under 35 years with unexplained infertility.

Effects of Different Exposure Days to Gonadotropin-Releasing Hormone Agonist (GnRH-a) on Live Birth Rates in the Depot GnRH-a Protocol: A Retrospective Analysis of 7007 Cycles

Background

In controlled ovarian hyperstimulation protocols worldwide, depot gonadotropin-releasing hormone agonist (GnRH-a) pretreatment is generally used for pituitary desensitization. The delay between the GnRH-a administration and starting gonadotropin treatment varies greatly, from 25 to 60 days. However, the association between exposure days to GnRH-a before the onset of gonadotropin administration and the clinical outcomes remains unknown.

Material/Methods

This retrospective study included 7007 patients who underwent fresh embryo transfers between February 2016 and July 2019. The duration of pituitary downregulation was categorized into 3 groups: group 1, ≤30 days; group 2, 31–35 days; and group 3, ≥36 days. The rates of live birth were compared as the main outcome measure. Logistic regression analysis was also performed after controlling for a range of confounders.

Results

The number of patients in groups 1, 2, and 3 was 2001, 2824, and 2182, respectively. Group 3 (≥36 days) had a noticeably higher live birth rate (48.1%) than the other 2 groups (42.6% and 43.9%, P=0.001). The rate of live birth was remarkably enhanced in group 3 (adjusted odds ratio: 1.264, 95% confidence interval: 1.098, 1.455, P=0.001) after controlling for confounders, while the difference was not found in group 2 (P=0.512) compared with group 1.

Conclusions

In the depot GnRH-a protocol, live birth rates are higher among patients needing a longer time to achieve the goal of pituitary downregulation.