Personalized prediction of first-cycle in vitro fertilization success

Improving IVF Utilization with Patient-Centric Artificial Intelligence-Machine Learning (AI/ML): A Retrospective Multicenter Experience

Objectives: In vitro fertilization (IVF) has the potential to give babies to millions more people globally, yet it continues to be underutilized. We established a globally applicable and locally adaptable IVF prognostics report and framework to support patient-provider counseling and enable validated, data-driven treatment decisions. This study investigates the IVF utilization rates associated with the usage of machine learning, center-specific (MLCS) prognostic reports (the Univfy® report) in provider-patient pre-treatment and IVF counseling. Methods: We used a retrospective cohort comprising 24,238 patients with new patient visits (NPV) from 2016 to 2022 across seven fertility centers in 17 locations in seven US states and Ontario, Canada. We tested the association of Univfy report usage and first intra-uterine insemination (IUI) and/or first IVF usage (a.k.a. conversion) within 180 days, 360 days, and "Ever" of NPV as primary outcomes. Results: Univfy report usage was associated with higher direct IVF conversion (without prior IUI), with odds ratios (OR) 3.13 (95% CI 2.83, 3.46), 2.89 (95% CI 2.63, 3.17), and 2.04 (95% CI 1.90, 2.20) and total IVF conversion (with or without prior IUI), OR 3.41 (95% CI 3.09, 3.75), 3.81 (95% CI 3.49, 4.16), and 2.78 (95% CI 2.59, 2.98) in 180-day, 360-day, and Ever analyses, respectively; p < 0.05. Among patients with Univfy report usage, after accounting for center as a factor, older age was a small yet independent predictor of IVF conversion. Conclusions: Usage of a patient-centric, MLCS-based prognostics report was associated with increased IVF conversion among new fertility patients. Further research to study factors influencing treatment decision making and real-world optimization of patient-centric workflows utilizing the MLCS reports is warranted.

Development and validation of a nomogram for predicting ongoing pregnancy in single vitrified-warmed blastocyst embryo transfer cycles

Introduction

The global adoption of the "freeze-all strategy" has led to a continuous increase in utilization of single vitrified-warmed blastocyst embryo transfer (SVBT) owing to its clinical effectiveness. Accurate prediction of clinical pregnancy is crucial from a patient-centered perspective. However, this remains challenging, with inherent limitations due to the absence of precise and user-friendly prediction tools. Thus, this study primarily aimed to develop and assess a nomogram based on quantitative clinical data to optimize the efficacy of personalized prognosis assessment.

Materials and methods

We conducted a retrospective cohort analysis of ongoing pregnancy data from 658 patients with infertility who underwent SVBT at our center between October 17, 2017, and December 18, 2021. Patients were randomly assigned to the training (n=461) or validation (n=197) cohort for nomogram development and testing, respectively. A nomogram was constructed using the results of the multivariable logistic regression (MLR), which included clinical covariates that were assessed for their association with ongoing pregnancy.

Results

The MLR identified eight significant variables that independently predicted ongoing pregnancy outcomes in the study population. These predictors encompassed maternal physiology, including maternal age at oocyte retrieval and serum anti-Müllerian hormone levels; uterine factors, such as adenomyosis; and various embryo assessment parameters, including the number of fertilized embryos, blastocyst morphology, blastulation day, blastocyst re-expansion speed, and presence of embryo string. The area under the receiver operating characteristic curve in our prediction model was 0.675 (95% confidence interval [CI], 0.622-0.729) and 0.656 (95% CI, 0.573-0.739) in the training and validation cohorts, respectively, indicating good discrimination performance in both cohorts.

Conclusions

Our individualized nomogram is a practical and user-friendly tool that can provide accurate and useful SVBT information for patients and clinicians. By offering this model to patients, clinical stakeholders can alleviate uncertainty and confusion about fertility treatment options and enhance patients' confidence in making informed decisions.

Nomogram prediction for the prediction of clinical pregnancy in Freeze-thawed Embryo Transfer

BACKGROUND

This study aimed to identify multiple endometrial receptivity related factors by applying non-invasive, repeatable multimodal ultrasound methods. Combined with basic clinical data, we further established a practical prediction model for early clinical outcomes in Freeze-thawed Embryo Transfer (FET).

METHODS

Retrospective analysis of clinical data of infertility patients undergoing FET cycle in our Center from January 2017 to September 2019. Receiver operating characteristic (ROC) curve and decision curve analyses were performed by 500 bootstrap resamplings to assess the determination and clinical value of the nomogram, respectively.

RESULTS

A total of 2457 FET cycles were included. We developed simple nomograms that predict the early clinical outcomes in FET cycles by using the parameters of age, BMI, type and number of embryos transferred, endometrial thickness, FI, RI, PI and number of endometrial and sub-endometrial blood flow. In the training cohort, the area under the ROC curve (AUC) showed statistical accuracy (AUC = 0.698), and similar results were shown in the subsequent validation cohort (AUC = 0.699). Decision curve analysis demonstrated the clinical value of this nomogram.

CONCLUSIONS

Our nomogram can predict clinical outcomes and it can be used as a simple, affordable and widely implementable tool to provide guidance and treatment recommendations for FET patients.

Predicting the probability of a live birth after a freeze-all based in vitro fertilization-embryo transfer (IVF-ET) treatment strategy

BACKGROUND

The predictors for live birth rate (LBR) following one episode of in vitro fertilization (IVF) cycle for patients using a "freeze-all" strategy are not entirely clear.

METHODS

A retrospective cohort study utilizing a prediction model was developed to assess the relationship to the LBR. Women undergoing IVF with a freeze-all strategy were screened. Univariate models were first fitted for female age at oocytes retrieval/frozen-thawed embryo transfer (FET), body mass index (BMI), duration and etiology of infertility, previous IVF failures, total dose and duration of gonadotrophin, ovarian sensitivity index (OSI), number of oocytes collected, method of fertilization, number of embryos created, number and stage of embryos frozen, type and number of FET cycles, endometrial thickness (EMT)/pattern, hormone level on transplantation day, storage duration, number of embryos thawed and damaged thawed embryos, number and stage of embryos transferred and number of different quality embryos transferred. Variables with P<0.05 in the univariate model were selected for further analysis of the final multivariate discrete-time logistic regression model.

RESULTS

A total of 7,602 women undergoing one ovarian stimulation resulted in 9,964 FETs, of whom 3,066 (40.33%) had a live-birth after their first FET and 3,929 (51.68%) after total FETs. The EMT and woman's age at oocyte retrieval were the most important predictors. In the first FET, the LBR of women with an EMT ≤8 mm [27.40%; 95% confidence interval (CI): (21.60-33.81%)] was significantly lower than that of women with EMT between 9 and 11 mm [36.51%; 95% CI: (34.25-38.81%)] and thicker than 12 mm [44.23%; 95% CI: (42.22-46.25%)] (P<0.05). The optimistic and conservative cumulative LBRs of women younger than 31 years [87.5%; 95% CI: (86.32-88.61%) and 63.04%; 95% CI: (61.36-64.69%)] were significantly decreased in women aged 31-35, 36-40 and >40 (P<0.001).

CONCLUSIONS

Our study provides an effective prediction model for a woman's chance of having a baby after a "freeze-all" policy. The use of EMT and female age as tools to identify LBR are shown to be justified, and repeated FETs cannot reverse the age-dependent decline in fertility.

Informative predictors of pregnancy after first IVF cycle using eIVF practice highway electronic health records

The aim of this study is to determine the most informative pre- and in-cycle variables for predicting success for a first autologous oocyte in-vitro fertilization (IVF) cycle. This is a retrospective study using 22,413 first autologous oocyte IVF cycles from 2001 to 2018. Models were developed to predict pregnancy following an IVF cycle with a fresh embryo transfer. The importance of each variable was determined by its coefficient in a logistic regression model and the prediction accuracy based on different variable sets was reported. The area under the receiver operating characteristic curve (AUC) on a validation patient cohort was the metric for prediction accuracy. Three factors were found to be of importance when predicting IVF success: age in three groups (38-40, 41-42, and above 42 years old), number of transferred embryos, and number of cryopreserved embryos. For predicting first-cycle IVF pregnancy using all available variables, the predictive model achieved an AUC of 68% + /- 0.01%. A parsimonious predictive model utilizing age (38-40, 41-42, and above 42 years old), number of transferred embryos, and number of cryopreserved embryos achieved an AUC of 65% + /- 0.01%. The proposed models accurately predict a single IVF cycle pregnancy outcome and identify important predictive variables associated with the outcome. These models are limited to predicting pregnancy immediately after the IVF cycle and not live birth. These models do not include indicators of multiple gestation and are not intended for clinical application.

Multivariate analysis of the factors associated with live births during in vitro fertilisation in Southeast Asia: a cross-sectional study of 104,015 in vitro fertilisation records in Taiwan

PURPOSE

To investigate the factors associated with live births and the interaction between age and the number of embryos transferred after in vitro fertilisation (IVF) treatment.

METHODS

This study analyses data from a population-based-assisted reproductive database of all registered artificial reproduction institutions (n = 80) from 2010 to 2016 in Taiwan. The probability of a live birth in correlation with the treatment parameters was measured with multivariate logistic regression analyses using the generalised additive model (GAM) and Pearson's chi-square exact test.

RESULTS

A total of 104,015 IVF treatments performed between 2010 and 2016 were included in our analysis. From these treatments, 31,467 (30.3%) were successfully delivered, and 40,565 test-tube babies were born. Pearson's chi-square exact test indicated that parents' age, cause of infertility, type of ovarian stimulation, additional assisted reproductive technology techniques, donated egg or sperm, fresh or frozen embryo, presence or absence of ovarian hyperstimulation syndrome, and day of embryo transfer were significantly associated with live births after an IVF cycle (p < 0.05). Multiple logistic regression analysis with the GAM revealed that the odds of a live birth with IVF treatment in patients < 34 years of age were 2.55 times higher than that in patients ≥ 45 years of age (odds ratio = 2.55, 95% confidence interval = 1.69-2.90) for patients who underwent a single-embryo transfer (SET); a similar pattern was observed when two or more embryos were transferred. Egg donation, the assisted hatching technique, oral ovarian stimulation agents, and implantation of frozen embryos during SET were shown to improve the chance of a live birth by 29-90%. Implantation of the embryo after the 5th day of culture yielded the highest odds of a live birth. The interaction plot revealed that maternal age, especially < 40 years, was associated with the probability of a live birth. SET and double-embryo transfer showed similar associations with the probability of a live birth across age groups. Transferring more than two embryos might reduce the probability of a live birth during IVF treatment for women ≥ 40 years of age.

CONCLUSIONS

Implanting a greater number of embryos did not improve the age-related decrease in fertility for patients undergoing IVF. Therefore, we suggested that ≤ 2 blastocysts could be transferred during IVF treatments for women ≥ 40 years. Transferring a blastocyst on day 5 of culture was associated with a significant increase in the odds of a live birth resulting from IVF.

Can methods of artificial intelligence aid in optimizing patient selection in patients undergoing intrauterine inseminations?

Purpose

AI and its machine learning algorithms have proven useful in several fields of medicine, including medically assisted reproduction. The purpose of the study was to construct several predictive models based on clinical data and select the best models to predict IUI procedure outcomes.

Methods

Clinical data (patient baseline characteristics, sperm quality, hormonal status, and cycle data) from 1029 IUI procedures performed in 413 couples stimulated by clomiphene citrate, letrozole, or gonadotropins were used to build several models to predict clinical pregnancy. The models included ANN, random forest, PLS, SVM, and linear models using the caret package in R. The models were evaluated using ROC analysis by means of random CV on test data.

Results

Out of the best performing models, the random forest model achieved an AUC of 0.66, a sensitivity of 0.432, and a specificity of 0.756. This performance was followed by the PLS model, which achieved a sensitivity of 0.459 and specificity of 0.734. The other models achieved significantly lower AUCs. When adjusting the predictive cutoff value, confusion matrices show that clinical pregnancy is twice as likely in the case of positive prediction.

Conclusion

Among the compared methods, the random forest and PLS models demonstrated superior performance in predicting the clinical outcome of IUI. With additional research and clinical validation, AI methods may be successfully used in improving patient selection and consequently lead to better clinical results.

Individualized embryo selection strategy developed by stacking machine learning model for better in vitro fertilization outcomes: an application study

BACKGROUND

To minimize the rate of in vitro fertilization (IVF)- associated multiple-embryo gestation, significant efforts have been made. Previous studies related to machine learning in IVF mainly focused on selecting the top-quality embryos to improve outcomes, however, in patients with sub-optimal prognosis or with medium- or inferior-quality embryos, the selection between SET and DET could be perplexing.

METHODS

This was an application study including 9211 patients with 10,076 embryos treated during 2016 to 2018, in Tongji Hospital, Wuhan, China. A hierarchical model was established using the machine learning system XGBoost, to learn embryo implantation potential and the impact of double embryos transfer (DET) simultaneously. The performance of the model was evaluated with the AUC of the ROC curve. Multiple regression analyses were also conducted on the 19 selected features to demonstrate the differences between feature importance for prediction and statistical relationship with outcomes.

RESULTS

For a single embryo transfer (SET) pregnancy, the following variables remained significant: age, attempts at IVF, estradiol level on hCG day, and endometrial thickness. For DET pregnancy, age, attempts at IVF, endometrial thickness, and the newly added P1 + P2 remained significant. For DET twin risk, age, attempts at IVF, 2PN/ MII, and P1 × P2 remained significant. The algorithm was repeated 30 times, and averaged AUC of 0.7945, 0.8385, and 0.7229 were achieved for SET pregnancy, DET pregnancy, and DET twin risk, respectively. The trend of predictive and observed rates both in pregnancy and twin risk was basically identical. XGBoost outperformed the other two algorithms: logistic regression and classification and regression tree.

CONCLUSION

Artificial intelligence based on determinant-weighting analysis could offer an individualized embryo selection strategy for any given patient, and predict clinical pregnancy rate and twin risk, therefore optimizing clinical outcomes.

Correlation between biochemical, ultrasonographic and demographic parameters with ovarian response to IVF/ICSI treatments in Mexican women

Objective:

Ovarian response from a conventional ovarian stimulation protocol is a crucial step in IVF/ICSI treatments. This ovarian response encompasses a wide range of outcomes at the extremes, leading to either excessive responses with the risk of life-threatening conditions like ovarian hyperstimulation syndrome (OHSS), or poor ovarian response (POR) with poor outcomes. This study aims to integrate biochemical, ultrasonographic and demographic parameters into a mathematical formula able to predict ovarian response to stimulation in IVF/ICSI in gonadotropin-releasing hormone (GnRH) antagonist protocols.

Methods:

This retrospective analysis included 147 patients submitted to an ovarian stimulation protocol combining recombinant FSH and gonadotropin-releasing hormone antagonist. All the parameters were correlated with the Spearman Rho and Pearson´s correlation coefficient. Once the data was normalized, we used the multiple linear regression models, checking the results with the progressive discriminating analysis.

Results:

We classified the database according to the correlation with the number of oocytes retrieved; the progressive discriminating analysis resulted in the following equation: oocytes retrieved = 2.312-0.130 (FSH) + 0.562 (AFC).

Conclusions:

The incorporation of 2 ovarian reserve parameters into a regression equation enables knowing the number of retrieved oocytes in each patient with 80.5% sensitivity and 55.4% specificity.

Prediction of live birth probability after in vitro fertilization and intracytoplasmic sperm injection treatment: A multi-center retrospective study in Chinese population

AIM

To develop a prediction model to estimate the chances of live birth over multiple cycles of in vitro fertilization (IVF) and intracytoplasmic sperm injection (ICSI) treatment.

METHODS

A retrospective cohort study was launched in three reproductive centers including 10 824 couples who received 14 106 treatment cycles with known pregnancy outcomes by the end of 2016. Discrete time logistic regression was used to establish the model and a nomogram was developed to predict the chance of live birth on plain paper-based final predictors.

RESULTS

Among 10 824 couples, 5809 (53.7%) ended up with a live birth with several successive transplant cycles. What's more, we found that younger female age (p < 0.001), smaller cycle number (p < 0.001), female body mass index (p < 0.001), male factor (p < 0.001), ovulation disorder (p = 0.006), and higher endometrial thickness (p < 0.001) were significantly associated with increased live birth rate. Discrimination of the model expressed by area under the curve (AUC) was 0.66.

CONCLUSION

Our study will help shape couples' expectations of their ART outcome, allowing them to plan their treatments more efficiently and prepare emotionally and financially.

predicting and improving the probability of live birth for women undergoing frozen-thawed embryo transfer: a data-driven estimation and simulation model

BACKGROUND AND OBJECTIVE

Frozen-thawed embryo transfer (FET) is now widely used for the treatment of infertility. For many couples and clinicians, concerns over the probability and how to increase the chance of a successful birth are very common. Currently, there is not a single model to predict the live birth outcomes for FET. To estimate the probability of live birth (PLB) in FET and to provide advice on potential treatment options by a data-driven predictive (DDP) model.

METHODS

2,189 FET cycles from Jan 2012 to Dec 2015 were recruited in a single center. 815 cycles of FET outcomes were live births and 1,374 cycles of FET outcomes failed. To verify the consistency of the DDP model, we carried out 10-fold cross-validation, and the mean and standard deviation of the accuracy were measured. Moreover, the performance of this model was evaluated by the mean and standard deviation of receiver operating characteristic curve and area under the curve (AUC).

RESULTS

Nine dominant factors, including age, BMI, HOMA-IR, basal follicle stimulating hormone, basal luteinizing hormone, basal estradiol, endometrial thickness, the number of embryo transfers and the total number of embryos, were automatically extracted from 28 candidate factors. The accuracy of our prediction model is 76.9%±1.6%, and the AUC is 0.83. Then, the PLB is estimated by the random forest algorithm. On this basis, the DDP model can comprehensively traverse and dynamically visualize the impact of several factors on live birth outcomes. Finally, optimal suggestions for the treatment of patients before FET are attempted to be made by the genetic algorithm.

CONCLUSION

The DDP model can not only provide satisfactory performance for predicting live birth outcomes in FET but also offer a visual estimation and simulation tool for clinicians to make treatment plans.

Prediction of in vitro fertilization outcome at different antral follicle count thresholds combined with female age, female cause of infertility, and ovarian response in a prospective cohort of 8269 women

Antral follicle count (AFC) has been widely investigated for the prediction of clinical pregnancy or live birth. This study discussed the effects of AFC quartile levels on pregnancy outcomes combined with female age, female cause of infertility, and ovarian response undergoing in vitro fertilization (IVF) treatment. At present, many research about AFC mainly discuss its impact on clinical practice at different thresholds, or the analyses of AFC with respect to assisted reproductive technology outcomes under using different ovarian stimulation protocols. Factors that include ovarian sensitivity index, female age, and infertility cause are all independent predictors of live birth undergoing IVF/intracytoplasmic sperm injection, while few researchers discussed influence of female-related factors for clinical outcomes in different AFC fields.A total of 8269 infertile women who were stimulated with a long protocol with normal menstrual cycles were enrolled in the study, and patients were categorized into 4 groups based on AFC quartiles (1-8, 9-12, 13-17, and ≥18 antral follicles).The clinical pregnancy rates increased in the 4 AFC groups (28.25% vs 35.38% vs 37.38% vs 40.13%), and there was a negative association between age and the 4 AFC groups. In addition, female cause of infertility like polycystic ovary syndrome, Tubal factor, and other causes had great significance on clinical outcome, and ovarian response in medium (9-16 oocytes retrieved) had the highest clinical pregnancy rate at AFC quartiles of 1 to 8, 9 to 12, 13 to 17, and ≥18 antral follicles.This study concludes that the female-related parameters (female cause of infertility, female age, and ovarian response) combined with AFC can be useful to estimate the probability of clinical pregnancy.

An artificial neural network for the prediction of assisted reproduction outcome

PURPOSE

To construct and validate an efficient artificial neural network (ANN) based on parameters with statistical correlation to live birth, to be used as a comprehensive tool for the prediction of the clinical outcome for patients undergoing ART.

METHODS

Data from 257 infertile couples that underwent a total of 426 IVF/ICSI cycles from 2010 to 2017 was collected on an ensemble of 118 parameters for each cycle. Statistical correlation of the parameters with the outcome of live birth was performed, using either t test or χ² test, and the parameters that demonstrated statistical significance were used to construct the ANN. Cross-validation was performed by random separation of data and repeating the training-testing procedure by 10 times.

RESULTS

12 statistically significant parameters out of the initial ensemble were used for the ANN construction, which exhibited a cumulative sensitivity and specificity of 76.7% and 73.4%, respectively. During cross-validation, the system exhibited the following: sensitivity 69.2% ± 2.36%, specificity 69.19% ± 2.8% (OR 5.21 ± 1.27), PPV 36.96 ± 3.44, NPV 89.61 ± 1.09, and OA 69.19% ± 2.69%. A rather small standard deviation in the performance indices between the training and test sets throughout the validation process indicated a stable performance of the constructed ANN.

CONCLUSIONS

The constructed ANN is based on statistically significant variables with the outcome of live birth and represents a stable and efficient system with increased performance indices. Validation of the system allowed an insight of its clinical value as a supportive tool in medical decisions, and overall provides a reliable approach in the routine practice of IVF units in a user-friendly environment.

Prediction of implantation after blastocyst transfer in in vitro fertilization: a machine-learning perspective

OBJECTIVE

To develop a random forest model (RFM) to predict implantation potential of a transferred embryo and compare it with a multivariate logistic regression model (MvLRM), based on data from a large cohort including in vitro fertilization (IVF) patients treated with the use of single-embryo transfer (SET) of blastocyst-stage embryos.

DESIGN

Retrospective study of a 2-year single-center cohort of women undergoing IVF or intracytoplasmatic sperm injection (ICSI).

SETTING

Academic hospital.

PATIENT(S)

Data from 1,052 women who underwent fresh SET in IVF or ICSI cycles were included.

INTERVENTION(S)

None.

MAIN OUTCOME MEASURE(S)

The performance of both RFM and MvLRM to predict pregnancy was quantified in terms of the area under the receiver operating characteristic (ROC) curve (AUC), classification accuracy, specificity, and sensitivity.

RESULT(S)

ROC analysis resulted in an AUC of 0.74 ± 0.03 for the proposed RFM and 0.66 ± 0.05 for the MvLRM for the prediction of ongoing pregnancies of ≥11 weeks. This RFM approach and the MvLRM yielded, respectively, sensitivities of 0.84 ± 0.07 and 0.66 ± 0.08 and specificities of 0.48 ± 0.07 and 0.58 ± 0.08.

CONCLUSION(S)

The performance to predict ongoing implantation will significantly improve with the use of an RFM approach compared with MvLRM.

Luteal phase ovarian stimulation for poor ovarian responders

Objective

To compare the clinical outcomes of follicular versus luteal phase ovarian stimulation in women with poor ovarian response (Bologna criteria) undergoing IVF.

Methods

This retrospective study investigated 446 patients submitted to 507 cycles in three groups. First, the two larger cohorts were examined: 154 patients treated with luteal phase ovarian stimulation (Group Lu); and 231 patients administered follicular phase ovarian stimulation (Group Fo). Then the clinical outcomes of 61 patients submitted to double ovarian stimulation were analyzed. Clinical outcomes included number of retrieved oocytes, fertilization rate, cleavage rate, top-quality embryo rate, clinical pregnancy rate (CPR), and live birth rate (LBR).

Results

Longer stimulation, higher dosages of HMG, and higher MII oocyte rates were achieved in Group Lu (p<0.001). There were no significant differences in CPR and LBR between the two groups offered frozen-thawed embryo transfer (28.4% vs. 33.0%, p=0.484; 22.9% vs. 25.5%, p=0.666). In the double ovarian stimulation group, the number of oocytes retrieved in the luteal phase stimulation protocol was higher (p=0.035), although luteal phase stimulation yielded a lower rate of MII oocytes (p=0.031). CPR and LBR were not statistically different (13.8% vs. 21.4%, p=0.525; 10.3% vs. 14.3%, p=0.706).

Conclusion

Luteal phase ovarian stimulation may be a promising protocol to treat women with POR, particularly for patients unable to yield enough viable embryos through follicular phase ovarian stimulation or other protocols.

Are computational applications the "crystal ball" in the IVF laboratory? The evolution from mathematics to artificial intelligence

Mathematics rules the world of science. Innovative technologies based on mathematics have paved the way for implementation of novel strategies in assisted reproduction. Ascertaining efficient embryo selection in order to secure optimal pregnancy rates remains the focus of the in vitro fertilization scientific community and the strongest driver behind innovative approaches. This scoping review aims to describe and analyze complex models based on mathematics for embryo selection, devices, and software most widely employed in the IVF laboratory and algorithms in the service of the cutting-edge technology of artificial intelligence. Despite their promising nature, the practicing embryologist is the one ultimately responsible for the success of the IVF laboratory and thus the one to approve embracing pioneering technologies in routine practice. Applied mathematics and computational biology have already provided significant insight into the selection of the most competent preimplantation embryo. This review describes the leap of evolution from basic mathematics to bioinformatics and investigates the possibility that computational applications may be the means to foretell a promising future for the IVF clinical practice.

Curvilinear relationship between age and assisted reproduction technique success: retrospective analyses of US National ART Surveillance System data from 2010-2014

In assisted reproduction technique cycles using fresh autologous embryos, the pattern by which outcomes per started cycle (live birth and clinical pregnancy) and per clinical pregnancy (live birth and miscarriage) change with age was determined. A dataset was created with 488,351 cycles. Success rates changed with age following well-fitted, ∩-shaped curvilinear (quadratic, cubic, quartic) regressions. These rates increased steadily from age <24-28 years (P = 0.001; P = 0.02; P = 0.04; respectively) with positive slopes (P ≤ 0.03); live birth and pregnancy rates per cycle were lower in women aged <25 years versus women aged 25-28 years (P = 0.0002; P = 0.01, respectively), and declined steadily thereafter with negative slopes (P < 0.0001). The initial increase occurred at decreasing rates; subsequent decline occurred at increasing rates. Women aged <29 years with successful outcomes were older than those who were unsuccessful (P = 0.001; P = 0.04; P = 0.001; respectively); those with successful outcomes were younger in other age groups (P < 0.0001). Miscarriage followed similar but reverse ∪-shaped curvilinear regressions. Age-driven decline in success rates begins <30 years and occurs at increasing rates, suggesting that women >30 years old with infertility should not delay assisted reproduction, if it is their only option.

Promoting the use of elective single embryo transfer in clinical practice

Background

The transfer of multiple embryos after in vitro fertilization (IVF) increases the risk of twins and higher-order births. Multiple births are associated with significant health risks and maternal and neonatal complications, as well as physical, emotional, and financial stresses that can strain families and increase the incidence of depression and anxiety disorders in parents. Elective single embryo transfer (eSET) is among the most effective methods to reduce the risk of multiple births with IVF.

Main body

Current societal guidelines recommend eSET for patients <35 years of age with a good prognosis, yet even this approach is not widely applied. Many patients and clinicians have been reluctant to adopt eSET due to studies reporting higher live birth rates with the transfer of two or more embryos rather than eSET. Additional barriers to eSET include risk of treatment dropout after embryo transfer failure, patient preference for twins, a lack of knowledge about the risks and complications associated with multiple births, and the high costs of multiple IVF cycles. This review provides a comprehensive summary of strategies to increase the rate of eSET, including personalized counseling, access to educational information regarding the risks of multiple pregnancies and births, financial incentives, and tools to help predict the chances of IVF success. The use of comprehensive chromosomal screening to improve embryo selection has been shown to improve eSET outcomes and may increase acceptance of eSET.

Conclusions

eSET is an effective method for reducing multiple pregnancies resulting from IVF. Although several factors may impede the adoption of eSET, there are a number of strategies and tools that may encourage the more widespread adoption of eSET in clinical practice.

Definition by FSH, AMH and embryo numbers of good-, intermediate- and poor-prognosis patients suggests previously unknown IVF outcome-determining factor associated with AMH

BACKGROUND

Though outcome models have been proposed previously, it is unknown whether cutoffs in clinical pregnancy and live birth rates at all ages are able to classify in vitro fertilization (IVF) patients into good-, intermediate- and poor prognosis.

METHODS

We here in 3 infertile patient cohorts, involving 1247, 1514 and 632 women, built logistic regression models based on 3 functional ovarian reserve (FOR) parameters, including (1) number of good quality embryos, (2) follicle stimulating hormone (FSH, mIU/mL) and (3) anti-Müllerian hormone (AMH, ng/mL), determining whether clinical pregnancy and live birth rates can discriminate between good, intermediate and poor prognosis patients.

RESULTS

All models, indeed, allowed at all ages for separation by prognosis, though cut offs changed with age. In the embryo model, increasing embryo production resulted in linear improvement of IVF outcomes despite transfer of similar embryo numbers; in the FSH model outcomes and FSH levels related inversely, while the association of AMH followed a bell-shaped polynomial pattern, demonstrating "best" outcomes at mid-ranges. All 3 models demonstrated increasingly poor outcomes with advancing ages, though "best" AMH even above age 43 was still associated with unexpectedly good pregnancy and delivery outcomes. Excessively high AMH, in contrast, was at all ages associated with spiking miscarriage rates.

CONCLUSIONS

At varying peripheral serum concentrations, AMH, thus, demonstrates hithero unknown and contradictory effects on IVF outcomes, deserving at different concentrations investigation as a potential therapeutic agent, with pregnancy-supporting and pregnancy-interrupting properties.

Antimüllerian hormone levels and antral follicle count as prognostic indicators in a personalized prediction model of live birth

OBJECTIVE

To compare antimüllerian hormone (AMH) and antral follicle count (AFC) separately and in combination with clinical characteristics for the prediction of live birth after controlled ovarian stimulation.

DESIGN

Retrospective development and temporal external validation of prediction model.

SETTING

Outpatient IVF clinic.

PATIENT(S)

We applied the boosted tree method to develop three prediction models incorporating clinical characteristics plus AMH or AFC or the combination on 2,124 linked IVF cycles from 2006 to 2010 and temporally externally validated predicted live-birth probabilities with an independent data set comprising 1,121 cycles from 2011 to 2012.

INTERVENTION(S)

None.

MAIN OUTCOME MEASURE(S)

Predictive power (posterior log of odds ratio compared to age, or PLORA), reclassification, receiver operator characteristic analysis, calibration, dynamic range.

RESULT(S)

Predictive power, was highest for the AMH model (PLORA = 29.1), followed by the AMH-AFC model (PLORA = 28.3) and AFC model (PLORA = 22.5). The prediction errors were 1% to <5% in each prognostic tier for all three models, except for the predicted live-birth probabilities of <10% in the AFC model, where the prediction error was 8%. The improvement in predictive power was highest for the AMH model: 76.2% improvement over age alone relative to 59% improvement for AFC and 73.3% for the combined model. Receiver operating characteristic analysis demonstrated that the AMH and the combined model had comparable discrimination (area under the curve = 0.716) and similar prediction error for high and low strata of live-birth prediction, with an improvement of 6.3% over age alone.

CONCLUSION(S)

The validated prediction model confirmed that AMH when combined with clinical characteristics can accurately identify the likelihood of live birth with a low prediction error. AFC provided no added predictive value beyond AMH.

Predictors of in vitro fertilization outcomes in women with highest follicle-stimulating hormone levels ≥ 12 IU/L: a prospective cohort study

Objective

The purpose of this study is to evaluate factors predictive of outcomes in women with highest follicle-stimulating hormone (FSH) levels ≥12 IU/L on basal testing, undergoing in vitro fertilization (IVF).

Methods

A prospective cohort study was conducted at Stanford University Hospital in the Reproductive Endocrinology and Infertility Center for 12 months. Women age 21 to 43 undergoing IVF with highest FSH levels on baseline testing were included. Donor/Recipient and frozen embryo cycles were excluded from this study. Prognostic factors evaluated in association with clinical pregnancy rates were type of infertility diagnosis and IVF stimulation parameters.

Results

The current study found that factors associated with clinical pregnancy were: increased number of mature follicles on the day of triggering, number of oocytes retrieved, number of Metaphase II oocytes if intracytoplasmic sperm injection was done, and number of embryos developed 24 hours after retrieval.

Conclusions

Our findings suggest that it would be beneficial for women with increased FSH levels to attempt a cycle of IVF. Results of ovarian stimulation, especially embryo quantity appear to be the best predictors of IVF outcomes and those can only be obtained from a cycle of IVF. Therefore, increased basal FSH levels should not discourage women from attempting a cycle of IVF.

Prognostic factors associated with clinical pregnancy in in vitro fertilization using pituitary down-regulation with depot and daily low-dose luteal phase gonadotropin releasing hormone agonists: A single center's experience

AIM:

To review the experience on depot-dose, and daily low-dose gonadotropin releasing hormone agonist (GnRHa) long protocols and identify prognostic factors.

SETTING AND DESIGN:

A chart review was conducted on 2106 depot and 1299 daily low-dose cycles at a university hospital.

METHODS:

Clinical parameters were summarized, and prognostic factors of clinical pregnancy for each protocol were identified by logistic regressions. Missing data were imputed using multiple imputations (MI) and the regression models were rerun after MI.

RESULTS:

Clinical pregnancy rate was 57.5% and 46.9% in the depot and daily low-dose groups, respectively. Logistic regressions with MI identified age (odds ratio [OR]: 0.95, 95% confidence interval [CI]: 0.92–0.98), serum progesterone (OR: 0.62, 95% CI: 0.45–0.84) and endometrial thickness (OR: 1.06, 95% CI: 1.02–1.12) on human chorionic gonadotropin (hCG) day, number of oocytes retrieved (OR: 1.04, 95% CI: 1.01–1.06), fertilization rate (OR: 2.66, 95% CI: 1.46–4.87) and ratio of good-quality D3 embryos (OR: 4.31, 95% CI: 2.79–6.67) as prognostic factors in the depot group. Age (OR: 0.95, 95% CI: 0.92–0.98), endometrial thickness on hCG day (OR: 1.09, 95% CI: 1.03–1.15), ratio of good quality D3 embryos (OR: 2.56, 95% CI: 1.59–4.13) and the number of cryopreserved embryos (OR: 1.07, 95% CI: 1.003–1.15) are prognostic for the daily low-dose protocol. Some regression coefficients that are significant under model-wise deletion become nonsignificant after MI.

CONCLUSIONS:

Age, embryo quality and endometrial thickness on hCG day are important prognostic factors for both 1.0/1.3 mg depot and 0.05/0.1 mg daily low-dose luteal phase GnRHa long protocols. MI is a valuable tool to gauge and address bias caused by missing data in reproductive medicine.

Patient-specific predictions of outcome after gonadotropin ovulation induction/intrauterine insemination

OBJECTIVE

To use patient-specific and cycle-specific characteristics to predict clinical pregnancy, multiple pregnancy, and spontaneous abortion rates after gonadotropin ovulation induction (OI)/IUI.

DESIGN

Retrospective chart review.

SETTING

Academic fertility center.

PATIENT(S)

A total of 1,438 women who underwent 3,375 gonadotropin OI/IUI cycles.

INTERVENTION(S)

Individual and cycle-specific characteristics were evaluated to determine predictors of the rates of clinical pregnancy, multiple pregnancy, and spontaneous abortion. Logistic regression using individual parameters was used to create predictive models.

MAIN OUTCOME MEASURE(S)

Clinical pregnancy (CPR), multiple pregnancy (MPR), and spontaneous abortion rates (SABR).

RESULT(S)

Multiple predictors were identified for CPR, MPR, and SABR. The presence of at least two follicles ≥ 13 mm at ovulation trigger significantly increased CPR (odds ratio [OR], 95% confidence interval [CI] = 1.45, 1.18-1.78) and MPR (OR, 95% CI = 5.17, 2.16-12.41). An E2 level >400 pg/mL significantly increased MPR (OR, 95% CI = 9.54, 2.31-39.42). Logistic regression models were developed for individualized predictions of outcome.

CONCLUSION(S)

Regression analysis reveals the patient and cycle-specific characteristics that are significant predictors of CPR, MPR, and SABR after OI/IUI. Logistic models using significant or nearly significant predictors for CPR, MPR, and SABR offer improved predictive power relative to simpler models, and allow for the development of a risk calculator for personalized patient counseling.