Personalized prediction of live birth prior to the first in vitro fertilization treatment: a machine learning method

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.

Predicting personalized cumulative live birth rate after a complete in vitro fertilization cycle: an analysis of 32,306 treatment cycles in China

BACKGROUND

The cumulative live birth rate (CLBR) has been regarded as a key measure of in vitro fertilization (IVF) success after a complete treatment cycle. Women undergoing IVF face great psychological pressure and financial burden. A predictive model to estimate CLBR is needed in clinical practice for patient counselling and shaping expectations.

METHODS

This retrospective study included 32,306 complete cycles derived from 29,023 couples undergoing IVF treatment from 2014 to 2020 at a university-affiliated fertility center in China. Three predictive models of CLBR were developed based on three phases of a complete cycle: pre-treatment, post-stimulation, and post-treatment. The non-linear relationship was treated with restricted cubic splines. Subjects from 2014 to 2018 were randomly divided into a training set and a test set at a ratio of 7:3 for model derivation and internal validation, while subjects from 2019 to 2020 were used for temporal validation.

RESULTS

Predictors of pre-treatment model included female age (non-linear relationship), antral follicle count (non-linear relationship), body mass index, number of previous IVF attempts, number of previous embryo transfer failure, type of infertility, tubal factor, male factor, and scarred uterus. Predictors of post-stimulation model included female age (non-linear relationship), number of oocytes retrieved (non-linear relationship), number of previous IVF attempts, number of previous embryo transfer failure, type of infertility, scarred uterus, stimulation protocol, as well as endometrial thickness, progesterone and luteinizing hormone on trigger day. Predictors of post-treatment model included female age (non-linear relationship), number of oocytes retrieved (non-linear relationship), cumulative Day-3 embryos live-birth capacity (non-linear relationship), number of previous IVF attempts, scarred uterus, stimulation protocol, as well as endometrial thickness, progesterone and luteinizing hormone on trigger day. The C index of the three models were 0.7559, 0.7744, and 0.8270, respectively. All models were well calibrated (p = 0.687, p = 0.468, p = 0.549). In internal validation, the C index of the three models were 0.7422, 0.7722, 0.8234, respectively; and the calibration P values were all greater than 0.05. In temporal validation, the C index were 0.7430, 0.7722, 0.8234 respectively; however, the calibration P values were less than 0.05.

CONCLUSIONS

This study provides three IVF models to predict CLBR according to information from different treatment stage, and these models have been converted into an online calculator ( https://h5.eheren.com/hcyc/pc/index.html#/home ). Internal validation and temporal validation verified the good discrimination of the predictive models. However, temporal validation suggested low accuracy of the predictive models, which might be attributed to time-associated amelioration of IVF practice.

Predictors of success after in vitro fertilization

The last few decades have witnessed a rise in the global uptake of in vitro fertilization (IVF) treatment. To ensure optimal use of this technology, it is important for patients and clinicians to have access to tools that can provide accurate estimates of treatment success and understand the contribution of key clinical and laboratory parameters that influence the chance of conception after IVF treatment. The focus of this review was to identify key predictors of IVF treatment success and assess their impact in terms of live birth rates. We have identified 11 predictors that consistently feature in currently available prediction models, including age, duration of infertility, ethnicity, body mass index, antral follicle count, previous pregnancy history, cause of infertility, sperm parameters, number of oocytes collected, morphology of transferred embryos, and day of embryo transfer.

Improved prediction of clinical pregnancy using artificial intelligence with enhanced inner cell mass and trophectoderm images

This study aimed to assess the performance of an artificial intelligence (AI) model for predicting clinical pregnancy using enhanced inner cell mass (ICM) and trophectoderm (TE) images. In this retrospective study, we included static images of 2555 day-5-blastocysts from seven in vitro fertilization centers in South Korea. The main outcome of the study was the predictive capability of the model to detect clinical pregnancies (gestational sac). Compared with the original embryo images, the use of enhanced ICM and TE images improved the average area under the receiver operating characteristic curve for the AI model from 0.716 to 0.741. Additionally, a gradient-weighted class activation mapping analysis demonstrated that the enhanced image-trained AI model was able to extract features from crucial areas of the embryo in 99% (506/512) of the cases. Particularly, it could extract the ICM and TE. In contrast, the AI model trained on the original images focused on the main areas in only 86% (438/512) of the cases. Our results highlight the potential efficacy of using ICM- and TE-enhanced embryo images when training AI models to predict clinical pregnancy.

Pretreatment prediction for IVF outcomes: generalized applicable model or centre-specific model?

STUDY QUESTION

What was the performance of different pretreatment prediction models for IVF, which were developed based on UK/US population (McLernon 2016 model, Luke model, Dhillon model, and McLernon 2022 model), in wider populations?

SUMMARY ANSWER

For a patient in China, the published pretreatment prediction models based on the UK/US population provide similar discriminatory power with reasonable AUCs and underestimated predictions.

WHAT IS KNOWN ALREADY

Several pretreatment prediction models for IVF allow patients and clinicians to estimate the cumulative probability of live birth in a cycle before the treatment, but they are mostly based on the population of Europe or the USA, and their performance and applicability in the countries and regions beyond these regions are largely unknown.

STUDY DESIGN, SIZE, DURATION

A total of 26 382 Chinese patients underwent oocyte pick-up cycles between January 2013 and December 2020.

PARTICIPANTS/MATERIALS, SETTING, METHODS

UK/US model performance was externally validated according to the coefficients and intercepts they provided. Centre-specific models were established with XGboost, Lasso, and generalized linear model algorithms. Discriminatory power and calibration of the models were compared as the forms of the AUC of the Receiver Operator Characteristic and calibration curves.

MAIN RESULTS AND THE ROLE OF CHANCE

The AUCs for McLernon 2016 model, Luke model, Dhillon model, and McLernon 2022 model were 0.69 (95% CI 0.68-0.69), 0.67 (95% CI 0.67-0.68), 0.69 (95% CI 0.68-0.69), and 0.67 (95% CI 0.67-0.68), respectively. The centre-specific yielded an AUC of 0.71 (95% CI 0.71-0.72) with key predictors including age, duration of infertility, and endocrine parameters. All external models suggested underestimation. Among the external models, the rescaled McLernon 2022 model demonstrated the best calibration (Slope 1.12, intercept 0.06).

LIMITATIONS, REASONS FOR CAUTION

The study is limited by its single-centre design and may not be representative elsewhere. Only per-complete cycle validation was carried out to provide a similar framework to compare different models in the sample population. Newer predictors, such as AMH, were not used.

WIDER IMPLICATIONS OF THE FINDINGS

Existing pretreatment prediction models for IVF may be used to provide useful discriminatory power in populations different from those on which they were developed. However, models based on newer more relevant datasets may provide better calibrations.

STUDY FUNDING/COMPETING INTEREST(S)

This work was supported by the National Natural Science Foundation of China [grant number 22176159], the Xiamen Medical Advantage Subspecialty Construction Project [grant number 2018296], and the Special Fund for Clinical and Scientific Research of Chinese Medical Association [grant number 18010360765].

TRIAL REGISTRATION NUMBER

N/A.

Using serum anti-Müllerian hormone levels to predict the chance of live birth after spontaneous or assisted conception: a systematic review and meta-analysis

STUDY QUESTION

Is serum anti-Müllerian hormone (AMH) level predictive of cumulative live birth (CLB) rate after ART or in women trying to conceive naturally?

SUMMARY ANSWER

Serum AMH level is linked to CLB after IVF/ICSI but data are lacking after IUI or in women trying to conceive without ART.

WHAT IS KNOWN ALREADY

Serum AMH level is a marker of ovarian reserve and a good predictor of ovarian response after controlled ovarian stimulation. It is unclear whether AMH measurement can predict CLB in spontaneous or assisted conception.

STUDY DESIGN, SIZE, DURATION

A systematic review and meta-analysis was undertaken to assess whether serum AMH level may predict chances of CLB in infertile women undergoing IVF/ICSI or IUI and/or chances of live birth in women having conceived naturally.

PARTICIPANTS/MATERIALS, SETTING, METHODS

A systematic review and meta-analysis was performed using the following keywords: 'AMH', 'anti-mullerian hormone', 'live-birth', 'cumulative live birth'. Searches were conducted from January 2004 to April 2021 on PubMed and Embase. Two independent reviewers carried out study selection, quality, and risk of bias assessment as well as data extraction. Odds ratios were estimated using a random-effect model. Pre-specified sensitivity analyses and subgroup analyses were performed. The primary outcome was CLB.

MAIN RESULTS AND THE ROLE OF CHANCE

A total of 32 studies were included in the meta-analysis. Overall, 27 articles were included in the meta-analysis of the relation between AMH and CLB or AMH and LB after IVF/ICSI. A non-linear positive relation was found in both cases. A polynomial fraction was the best model to describe it but no discriminant AMH threshold was shown, especially no serum AMH level threshold below which live birth could not be achieved after IVF/ICSI. After IVF-ICSI, only four studies reported CLB rate according to AMH level. No statistically significant differences in mean serum AMH levels were shown between patients with and without CLB, but with a high heterogeneity. After exclusion of two studies with high risks of bias, there was no more heterogeneity [I2 = 0%] and the mean AMH level was statistically significantly higher in women with CLB. There were not enough articles/data to assess the ability of AMH to predict CLB rate or find an AMH threshold after IUI or in women without history of infertility trying to conceive without ART.

LIMITATIONS, REASONS FOR CAUTION

The systematic review and meta-analysis had some limitations owing to the limits and bias of the studies included. In the present meta-analysis, heterogeneity may have been caused by different baseline characteristics in study participants, different stimulating protocols for ART, different serum AMH level thresholds used and the use of various assays for serum AMH. This could explain, in part, the absence of a discriminating AMH threshold found in this analysis.

WIDER IMPLICATIONS OF THE FINDINGS

Serum AMH level is linked to CLB rate after IVF/ICSI but no discriminating threshold can be established, therefore low serum AMH level should not be used as the sole criterion for rejecting IVF treatment, especially in young patients. Data are lacking concerning its predictive value after IUI or in women trying to conceive without ART. Our findings may be helpful to counsel candidate couples to IVF-ICSI.

STUDY FUNDING/COMPETING INTERESTS

No external funding was obtained for this study. There are no conflicts of interest.

REGISTRATION NUMBER

PROSPERO CRD42021269332.

Deep Inception-ResNet: A Novel Approach for Personalized Prediction of Cumulative Pregnancy Outcomes in Vitro Fertilization Treatment (IVF)

Background

Infertility is one of the major causes of socioeconomic stress worldwide due to social stigma and stressful lifestyles. Despite technological advances, couples still undergo several IVF cycles for conceiving without knowing their true prognosis which is causing a huge social and medical impact, and the live birth rate continues to be relatively low (~ 25%). A prediction model that predicts IVF prognosis accurately considering the pre-treatment parameters before starting the IVF cycle will help clinicians and patients to make better-informed choices.

Methods

In this study, clinical details of 2268 patients with 79 features who underwent IVF/ICSI procedure from January 2018 to December 2020, at the Center of IVF and Human Reproduction, Sir Ganga Ram Hospital were retrospectively collected. The machine learning model was developed considering features such as maternal age, number of IVF cycle, type of infertility, duration of infertility, AMH, indication for IVF, sperm type, BMI, embryo transfer, and β-hCG value at the end of a fresh cycle and/or one subsequent frozen embryo transfer cycle was selected as the measure of outcome.

Results

Compared to other classifiers, for an 80:20 train-test split with feature selection, the proposed Deep Inception-Residual Network architecture-based neural network gave the best accuracy (76%) and ROC-AUC score of 0.80. For tabular datasets, the applied approach has remained unexplored in previously made studies for reproductive health.

Conclusion

This model is the starting point for providing a personalized prediction of a successful outcome for an infertile couple before they enter the IVF procedure.

Supplementary Information

The online version contains supplementary material available at 10.1007/s13224-023-01773-9.

Construction of the machine learning-based live birth prediction models for the first in vitro fertilization pregnant women

BACKGROUND

This study was to conduct prediction models based on parameters before and after the first cycle, respectively, to predict live births in women who received fresh or frozen in vitro fertilization (IVF) or intracytoplasmic sperm injection (ICSI) for the first time.

METHODS

This retrospective cohort study population consisted of 1,857 women undergoing the IVF cycle from 2019 to 2021 at Huizhou Municipal Central Hospital. The data between 2019 and 2020 were completely randomly divided into a training set and a validation set (8:2). The data from 2021 was used as the testing set, and the bootstrap validation was carried out by extracting 30% of the data for 200 times on the total data set. In the training set, variables are divided into those before the first cycle and after the first cycle. Then, predictive factors before the first cycle and after the first cycle were screened. Based on the predictive factors, four supervised machine learning algorithms were respectively considered to build the predictive models: logistic regression (LR), random forest (RF), extreme gradient boosting (XGBoost), and light gradient boosting machine (LGBM). The performances of the prediction models were evaluated by the area under the receiver operator characteristic curve (AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy.

RESULTS

Totally, 851 women (45.83%) had a live birth. The LGBM model showed a robust performance in predicting live birth before the first cycle, with AUC being 0.678 [95% confidence interval (CI): 0.651 to 0.706] in the training set, 0.612 (95% CI: 0.553 to 0.670) in the validation set, 0.634 (95% CI: 0.511 to 0.758) in the testing set, and 0.670 (95% CI: 0.626 to 0.715) in the bootstrap validation. The AUC value in the training set, validation set, testing set, and bootstrap of LGBM to predict live birth after the first cycle was 0.841 (95% CI: 0.821 to 0.861), 0.816 (95% CI: 0.773 to 0.859), 0.835 (95% CI: 0.743 to 0.926), and 0.839 (95% CI: 0.806 to 0.871), respectively.

CONCLUSION

The LGBM model based on the predictive factors before and after the first cycle for live birth in women showed a good predictive performance. Therefore, it may assist fertility specialists and patients to adjust the appropriate treatment strategy.

DNA Methylation of Window of Implantation Genes in Cervical Secretions Predicts Ongoing Pregnancy in Infertility Treatment

Window of implantation (WOI) genes have been comprehensively identified at the single cell level. DNA methylation changes in cervical secretions are associated with in vitro fertilization embryo transfer (IVF-ET) outcomes. Using a machine learning (ML) approach, we aimed to determine which methylation changes in WOI genes from cervical secretions best predict ongoing pregnancy during embryo transfer. A total of 2708 promoter probes were extracted from mid-secretory phase cervical secretion methylomic profiles for 158 WOI genes, and 152 differentially methylated probes (DMPs) were selected. Fifteen DMPs in 14 genes (BMP2, CTSA, DEFB1, GRN, MTF1, SERPINE1, SERPINE2, SFRP1, STAT3, TAGLN2, TCF4, THBS1, ZBTB20, ZNF292) were identified as the most relevant to ongoing pregnancy status. These 15 DMPs yielded accuracy rates of 83.53%, 85.26%, 85.78%, and 76.44%, and areas under the receiver operating characteristic curves (AUCs) of 0.90, 0.91, 0.89, and 0.86 for prediction by random forest (RF), naïve Bayes (NB), support vector machine (SVM), and k-nearest neighbors (KNN), respectively. SERPINE1, SERPINE2, and TAGLN2 maintained their methylation difference trends in an independent set of cervical secretion samples, resulting in accuracy rates of 71.46%, 80.06%, 80.72%, and 80.68%, and AUCs of 0.79, 0.84, 0.83, and 0.82 for prediction by RF, NB, SVM, and KNN, respectively. Our findings demonstrate that methylation changes in WOI genes detected noninvasively from cervical secretions are potential markers for predicting IVF-ET outcomes. Further studies of cervical secretion of DNA methylation markers may provide a novel approach for precision embryo transfer.

Combining Machine Learning with Metabolomic and Embryologic Data Improves Embryo Implantation Prediction

This study investigated whether combining metabolomic and embryologic data with machine learning (ML) models improve the prediction of embryo implantation potential. In this prospective cohort study, infertile couples (n=56) undergoing day-5 single blastocyst transfer between February 2019 and August 2021 were included. After day-5 single blastocyst transfer, spent culture medium (SCM) was subjected to metabolite analysis using nuclear magnetic resonance (NMR) spectroscopy. Derived metabolite levels and embryologic parameters between successfully implanted and failed groups were incorporated into ML models to explore their predictive potential regarding embryo implantation. The SCM of blastocysts that resulted in successful embryo implantation had significantly lower pyruvate (p<0.05) and threonine (p<0.05) levels compared to medium control but not compared to SCM related to embryos that failed to implant. Notably, the prediction accuracy increased when classical ML algorithms were combined with metabolomic and embryologic data. Specifically, the custom artificial neural network (ANN) model with regularized parameters for metabolomic data provided 100% accuracy, indicating the efficiency in predicting implantation potential. Hence, combining ML models (specifically, custom ANN) with metabolomic and embryologic data improves the prediction of embryo implantation potential. The approach could potentially be used to derive clinical benefits for patients in real-time.

Prediction of Prednisolone Dose Correction Using Machine Learning

Wrong dose, a common prescription error, can cause serious patient harm, especially in the case of high-risk drugs like oral corticosteroids. This study aims to build a machine learning model to predict dose-related prescription modifications for oral prednisolone tablets (i.e., highly imbalanced data with very few positive cases). Prescription data were obtained from the electronic medical records at a single institute. Cluster analysis classified the clinical departments into six clusters with similar patterns of prednisolone prescription. Two patterns of training datasets were created with/without preprocessing by the SMOTE method. Five ML models (SVM, KNN, GB, RF, and BRF) and logistic regression (LR) models were constructed by Python. The model was internally validated by five-fold stratified cross-validation and was validated with a 30% holdout test dataset. Eighty-two thousand five hundred fifty-three prescribing data for prednisolone tablets containing 135 dose-corrected positive cases were obtained. In the original dataset (without SMOTE), only the BRF model showed a good performance (in test dataset, ROC-AUC:0.917, recall: 0.951). In the training dataset preprocessed by SMOTE, performance was improved on all models. The highest performance models with SMOTE were SVM (in test dataset, ROC-AUC: 0.820, recall: 0.659) and BRF (ROC-AUC: 0.814, recall: 0.634). Although the prescribing data for dose-related collection are highly imbalanced, various techniques such as the following have allowed us to build high-performance prediction models: data preprocessing by SMOTE, stratified cross-validation, and BRF classifier corresponding to imbalanced data. ML is useful in complicated dose audits such as oral prednisolone.

Supplementary Information

The online version contains supplementary material available at 10.1007/s41666-023-00128-3.

Prediction model for missed abortion of patients treated with IVF-ET based on XGBoost: a retrospective study

Aim

In this study, we established a model based on XGBoost to predict the risk of missed abortion in patients treated with in vitro fertilization-embryo transfer (IVF-ET), evaluated its prediction ability, and compared the model with the traditional logical regression model.

Methods

We retrospectively collected the clinical data of 1,017 infertile women treated with IVF-ET. The independent risk factors were screened by performing a univariate analysis and binary logistic regression analysis, and then, all cases were randomly divided into the training set and the test set in a 7:3 ratio for constructing and validating the model. We then constructed the prediction models by the traditional logical regression method and the XGBoost method and tested the prediction performance of the two models by resampling.

Results

The results of the binary logistic regression analysis showed that several factors, including the age of men and women, abnormal ovarian structure, prolactin (PRL), anti-Müllerian hormone (AMH), activated partial thromboplastin time (APTT), anticardiolipin antibody (ACA), and thyroid peroxidase antibody (TPO-Ab), independently influenced missed abortion significantly (P < 0.05). The area under the receiver operating characteristic curve (AUC) score and the F1 score with the training set of the XGBoost model (0.877 ± 0.014 and 0.730 ± 0.019, respectively) were significantly higher than those of the logistic model (0.713 ± 0.013 and 0.568 ± 0.026, respectively). In the test set, the AUC and F1 scores of the XGBoost model (0.759 ± 0.023 and 0.566 ± 0.042, respectively) were also higher than those of the logistic model (0.695 ± 0.030 and 0.550 ± 049, respectively).

Conclusions

We established a prediction model based on the XGBoost algorithm, which can accurately predict the risk of missed abortion in patients with IVF-ET. This model performed better than the traditional logical regression model.

Assessment and quantification of ovarian reserve on the basis of machine learning models

BACKGROUND

Early detection of ovarian aging is of huge importance, although no ideal marker or acknowledged evaluation system exists. The purpose of this study was to develop a better prediction model to assess and quantify ovarian reserve using machine learning methods.

METHODS

This is a multicenter, nationwide population-based study including a total of 1,020 healthy women. For these healthy women, their ovarian reserve was quantified in the form of ovarian age, which was assumed equal to their chronological age, and least absolute shrinkage and selection operator (LASSO) regression was used to select features to construct models. Seven machine learning methods, namely artificial neural network (ANN), support vector machine (SVM), generalized linear model (GLM), K-nearest neighbors regression (KNN), gradient boosting decision tree (GBDT), extreme gradient boosting (XGBoost), and light gradient boosting machine (LightGBM) were applied to construct prediction models separately. Pearson's correlation coefficient (PCC), mean absolute error (MAE), and mean squared error (MSE) were used to compare the efficiency and stability of these models.

RESULTS

Anti-Müllerian hormone (AMH) and antral follicle count (AFC) were detected to have the highest absolute PCC values of 0.45 and 0.43 with age and held similar age distribution curves. The LightGBM model was thought to be the most suitable model for ovarian age after ranking analysis, combining PCC, MAE, and MSE values. The LightGBM model obtained PCC values of 0.82, 0.56, and 0.70 for the training set, the test set, and the entire dataset, respectively. The LightGBM method still held the lowest MAE and cross-validated MSE values. Further, in two different age groups (20-35 and >35 years), the LightGBM model also obtained the lowest MAE value of 2.88 for women between the ages of 20 and 35 years and the second lowest MAE value of 5.12 for women over the age of 35 years.

CONCLUSION

Machine learning methods combining multi-features were reliable in assessing and quantifying ovarian reserve, and the LightGBM method turned out to be the approach with the best result, especially in the child-bearing age group of 20 to 35 years.

Developing machine learning-based models to predict intrauterine insemination (IUI) success by address modeling challenges in imbalanced data and providing modification solutions for them

Background

This study sought to provide machine learning-based classification models to predict the success of intrauterine insemination (IUI) therapy. Additionally, we sought to illustrate the effect of models fitting with balanced data vs original data with imbalanced data labels using two different types of resampling methods. Finally, we fit models with all features against optimized feature sets using various feature selection techniques.

Methods

The data for the cross-sectional study were collected from 546 infertile couples with IUI at the Fatemehzahra Infertility Research Center, Babol, North of Iran. Logistic regression (LR), support vector classification, random forest, Extreme Gradient Boosting (XGBoost) and, Stacking generalization (Stack) as the machine learning classifiers were used to predict IUI success by Python v3.7. We employed the Smote-Tomek (Stomek) and Smote-ENN (SENN) resampling methods to address the imbalance problem in the original dataset. Furthermore, to increase the performance of the models, mutual information classification (MIC-FS), genetic algorithm (GA-FS), and random forest (RF-FS) were used to select the ideal feature sets for model development.

Results

In this study, 28% of patients undergoing IUI treatment obtained a successful pregnancy. Also, the average age of women and men was 24.98 and 29.85 years, respectively. The calibration plot in this study for IUI success prediction by machine learning models showed that between feature selection methods, the RF-FS, and among the datasets used to fit the models, the balanced dataset with the Stomek method had well-calibrating predictions than other methods. Finally, the brier scores for the LR, SVC, RF, XGBoost, and Stack models that were fitted utilizing the Stomek dataset and the chosen feature set using the Random Forest technique obtained equal to 0.202, 0.183, 0.158, 0.129, and 0.134, respectively. It showed duration of infertility, male and female age, sperm concentration, and sperm motility grading score as the most predictable factors in IUI success.

Conclusion

The results of this study with the XGBoost prediction model can be used to foretell the individual success of IUI for each couple before initiating therapy.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12911-022-01974-8.

Predicting clinical pregnancy using clinical features and machine learning algorithms in in vitro fertilization

INTRODUCTION

Assisted reproductive technology has been proposed for women with infertility. Moreover, in vitro fertilization (IVF) cycles are increasing. Factors contributing to successful pregnancy have been widely explored. In this study, we used machine learning algorithms to construct prediction models for clinical pregnancies in IVF.

MATERIALS AND METHODS

A total of 24,730 patients entered IVF and intracytoplasmic sperm injection cycles with clinical pregnancy outcomes at Taipei Medical University Hospital. Data used included patient characteristics and treatment. We used machine learning methods to develop prediction models for clinical pregnancy and explored how each variable affects the outcome of interest using partial dependence plots.

RESULTS

Experimental results showed that the random forest algorithm outperforms logistic regression in terms of areas under the receiver operating characteristics curve. The ovarian stimulation protocol is the most important factor affecting pregnancy outcomes. Long and ultra-long protocols have shown positive effects on clinical pregnancy among all protocols. Furthermore, total frozen and transferred embryos are positive for a clinical pregnancy, but female age and duration of infertility have negative effects on clinical pregnancy.

CONCLUSION

Our findings show the importance of variables and propensity of each variable by random forest algorithm for clinical pregnancy in the assisted reproductive technology cycle. This study provides a ranking of variables affecting clinical pregnancy and explores the effects of each treatment on successful pregnancy. Our study has the potential to help clinicians evaluate the success of IVF in patients.

Influence of ambient air pollution on successful pregnancy with frozen embryo transfer: A machine learning prediction model

Numerous air pollutants have been reported to influence the outcomes of in vitro fertilization (IVF). However, whether air pollution affects implantation in frozen embryo transfer (FET) process is under debate. We aimed to find the association between ambient air pollution and implantation potential of FET and test the value of adding air pollution data to a random forest model (RFM) predicting intrauterine pregnancy. Using a retrospective study of a 4-year single-center design，we analyzed 3698 cycles of women living in Shanghai who underwent FET between 2015 and 2018. To estimate patients' individual exposure to air pollution, we computed averages of daily concentrations of six air pollutants including PM_2.5, PM₁₀, SO₂, CO, NO₂, and O₃ measured at 9 monitoring stations in Shanghai for the exposure period (one month before FET). Moreover, A predictive model of 15 variables was established using RFM. Air pollutants levels of patients with or without intrauterine pregnancy were compared. Our results indicated that for exposure periods before FET, NO₂ were negatively associated with intrauterine pregnancy (OR: 0.906, CI: 0.816-0.989). AUROC increased from 0.712 to 0.771 as air pollutants features were added. Overall, our findings demonstrate that exposure to NO₂ before transfer has an adverse effect on clinical pregnancy. The performance to predict intrauterine pregnancy will improve with the use of air pollution data in RFM.

Artificial intelligence in the fertility clinic: status, pitfalls and possibilities

In recent years, the amount of data produced in the field of ART has increased exponentially. The diversity of data is large, ranging from videos to tabular data. At the same time, artificial intelligence (AI) is progressively used in medical practice and may become a promising tool to improve success rates with ART. AI models may compensate for the lack of objectivity in several critical procedures in fertility clinics, especially embryo and sperm assessments. Various models have been developed, and even though several of them show promising performance, there are still many challenges to overcome. In this review, we present recent research on AI in the context of ART. We discuss the strengths and weaknesses of the presented methods, especially regarding clinical relevance. We also address the pitfalls hampering successful use of AI in the clinic and discuss future possibilities and important aspects to make AI truly useful for ART.

Machine learning risk score for prediction of gestational diabetes in early pregnancy in Tianjin, China

AIMS

This study aimed to develop a machine learning-based prediction model for gestational diabetes mellitus (GDM) in early pregnancy in Chinese women.

MATERIALS AND METHODS

We used an established population-based prospective cohort of 19,331 pregnant women registered as pregnant before the 15th gestational week in Tianjin, China, from October 2010 to August 2012. The dataset was randomly divided into a training set (70%) and a test set (30%). Risk factors collected at registration were examined and used to construct the prediction model in the training dataset. Machine learning, that is, the extreme gradient boosting (XGBoost) method, was employed to develop the model, while a traditional logistic model was also developed for comparison purposes. In the test dataset, the performance of the developed prediction model was assessed by calibration plots for calibration and area under the receiver operating characteristic curve (AUR) for discrimination.

RESULTS

In total, 1484 (7.6%) women developed GDM. Pre-pregnancy body mass index, maternal age, fasting plasma glucose at registration, and alanine aminotransferase were selected as risk factors. The machine learning XGBoost model-predicted probability of GDM was similar to the observed probability in the test data set, while the logistic model tended to overestimate the risk at the highest risk level (Hosmer-Lemeshow test p value: 0.243 vs. 0.099). The XGBoost model achieved a higher AUR than the logistic model (0.742 vs. 0.663, p < 0.001). This XGBoost model was deployed through a free, publicly available software interface (https://liuhongwei.shinyapps.io/gdm_risk_calculator/).

CONCLUSION

The XGBoost model achieved better performance than the logistic model.

Using Deep Learning in a Monocentric Study to Characterize Maternal Immune Environment for Predicting Pregnancy Outcomes in the Recurrent Reproductive Failure Patients

Recurrent reproductive failure (RRF), such as recurrent pregnancy loss and repeated implantation failure, is characterized by complex etiologies and particularly associated with diverse maternal factors. It is currently believed that RRF is closely associated with the maternal environment, which is, in turn, affected by complex immune factors. Without the use of automated tools, it is often difficult to assess the interaction and synergistic effects of the various immune factors on the pregnancy outcome. As a result, the application of Artificial Intelligence (A.I.) has been explored in the field of assisted reproductive technology (ART). In this study, we reviewed studies on the use of A.I. to develop prediction models for pregnancy outcomes of patients who underwent ART treatment. A limited amount of models based on genetic markers or common indices have been established for prediction of pregnancy outcome of patients with RRF. In this study, we applied A.I. to analyze the medical information of patients with RRF, including immune indicators. The entire clinical samples set (561 samples) was divided into two sets: 90% of the set was used for training and 10% for testing. Different data panels were established to predict pregnancy outcomes at four different gestational nodes, including biochemical pregnancy, clinical pregnancy, ongoing pregnancy, and live birth, respectively. The prediction models of pregnancy outcomes were established using sparse coding, based on six data panels: basic patient characteristics, hormone levels, autoantibodies, peripheral immunology, endometrial immunology, and embryo parameters. The six data panels covered 64 variables. In terms of biochemical pregnancy prediction, the area under curve (AUC) using the endometrial immunology panel was the largest (AUC = 0.766, accuracy: 73.0%). The AUC using the autoantibodies panel was the largest in predicting clinical pregnancy (AUC = 0.688, accuracy: 78.4%), ongoing pregnancy (AUC = 0.802, accuracy: 75.0%), and live birth (AUC = 0.909, accuracy: 89.7%). Combining the data panels did not significantly enhance the effect on prediction of all the four pregnancy outcomes. These results give us a new insight on reproductive immunology and establish the basis for assisting clinicians to plan more precise and personalized diagnosis and treatment for patients with RRF.

Machine learning predicts live-birth occurrence before in-vitro fertilization treatment

In-vitro fertilization (IVF) is a popular method of resolving complications such as endometriosis, poor egg quality, a genetic disease of mother or father, problems with ovulation, antibody problems that harm sperm or eggs, the inability of sperm to penetrate or survive in the cervical mucus and low sperm counts, resulting human infertility. Nevertheless, IVF does not guarantee success in the fertilization. Choosing IVF is burdensome for the reason of high cost and uncertainty in the result. As the complications and fertilization factors are numerous in the IVF process, it is a cumbersome task for fertility doctors to give an accurate prediction of a successful birth. Artificial Intelligence (AI) has been employed in this study for predicting the live-birth occurrence. This work mainly focuses on making predictions of live-birth occurrence when an embryo forms from a couple and not a donor. Here, we compare various AI algorithms, including both classical Machine Learning, deep learning architecture, and an ensemble of algorithms on the publicly available dataset provided by Human Fertilisation and Embryology Authority (HFEA). Insights on data and metrics such as confusion matrices, F1-score, precision, recall, receiver operating characteristic (ROC) curves are demonstrated in the subsequent sections. The training process has two settings Without feature selection and With feature selection to train classifier models. Machine Learning, Deep learning, ensemble models classification paradigms have been trained in both settings. The Random Forest model achieves the highest F1-score of 76.49% in without feature selection setting. For the same model, the precision, recall, and area under the ROC Curve (ROC AUC) scores are 77%, 76%, and 84.60%, respectively. The success of the pregnancy depends on both male and female traits and living conditions. This study predicts a successful pregnancy through the clinically relevant parameters in In-vitro fertilization. Thus artificial intelligence plays a promising role in decision making process to support the diagnosis, prognosis, treatment etc.

Comparison of Multivariable Logistic Regression and Other Machine Learning Algorithms for Prognostic Prediction Studies in Pregnancy Care: Systematic Review and Meta-Analysis

Background

Predictions in pregnancy care are complex because of interactions among multiple factors. Hence, pregnancy outcomes are not easily predicted by a single predictor using only one algorithm or modeling method.

Objective

This study aims to review and compare the predictive performances between logistic regression (LR) and other machine learning algorithms for developing or validating a multivariable prognostic prediction model for pregnancy care to inform clinicians’ decision making.

Methods

Research articles from MEDLINE, Scopus, Web of Science, and Google Scholar were reviewed following several guidelines for a prognostic prediction study, including a risk of bias (ROB) assessment. We report the results based on the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Studies were primarily framed as PICOTS (population, index, comparator, outcomes, timing, and setting): Population: men or women in procreative management, pregnant women, and fetuses or newborns; Index: multivariable prognostic prediction models using non-LR algorithms for risk classification to inform clinicians’ decision making; Comparator: the models applying an LR; Outcomes: pregnancy-related outcomes of procreation or pregnancy outcomes for pregnant women and fetuses or newborns; Timing: pre-, inter-, and peripregnancy periods (predictors), at the pregnancy, delivery, and either puerperal or neonatal period (outcome), and either short- or long-term prognoses (time interval); and Setting: primary care or hospital. The results were synthesized by reporting study characteristics and ROBs and by random effects modeling of the difference of the logit area under the receiver operating characteristic curve of each non-LR model compared with the LR model for the same pregnancy outcomes. We also reported between-study heterogeneity by using τ² and I².

Results

Of the 2093 records, we included 142 studies for the systematic review and 62 studies for a meta-analysis. Most prediction models used LR (92/142, 64.8%) and artificial neural networks (20/142, 14.1%) among non-LR algorithms. Only 16.9% (24/142) of studies had a low ROB. A total of 2 non-LR algorithms from low ROB studies significantly outperformed LR. The first algorithm was a random forest for preterm delivery (logit AUROC 2.51, 95% CI 1.49-3.53; I²=86%; τ²=0.77) and pre-eclampsia (logit AUROC 1.2, 95% CI 0.72-1.67; I²=75%; τ²=0.09). The second algorithm was gradient boosting for cesarean section (logit AUROC 2.26, 95% CI 1.39-3.13; I²=75%; τ²=0.43) and gestational diabetes (logit AUROC 1.03, 95% CI 0.69-1.37; I²=83%; τ²=0.07).

Conclusions

Prediction models with the best performances across studies were not necessarily those that used LR but also used random forest and gradient boosting that also performed well. We recommend a reanalysis of existing LR models for several pregnancy outcomes by comparing them with those algorithms that apply standard guidelines.

Trial Registration

PROSPERO (International Prospective Register of Systematic Reviews) CRD42019136106; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=136106

Application of Artificial Intelligence Algorithms to Estimate the Success Rate in Medically Assisted Procreation

The aim of this study was to build an Artificial Neural Network (ANN) complemented by a decision tree to predict the chance of live birth after an In Vitro Fertilization (IVF)/Intracytoplasmic Sperm Injection (ICSI) treatment, before the first embryo transfer, using demographic and clinical data. Overall, 26 demographic and clinical data from 1193 cycles who underwent an IVF/ICSI treatment at Centro de Infertilidade e Reprodução Medicamente Assistida, between 2012 and 2019, were analyzed. An ANN was constructed by selecting experimentally the input variables which most correlated to the target through Pearson correlation. The final used variables were: woman’s age, total dose of gonadotropin, number of eggs, number of embryos and Antral Follicle Count (AFC). A decision tree was developed considering as an initial set the input variables integrated in the previous model. The ANN model was validated by the holdout method and the decision tree model by the 10-fold cross method. The ANN accuracy was 75.0% and the Area Under the Receiver Operating Characteristic (AUROC) curve was 75.2% (95% Confidence Interval (CI): 72.5–77.5%), whereas the decision tree model reached 75.0% and 74.9% (95% CI: 72.3–77.5%). These results demonstrated that both ANN and decision tree methods are fair for prediction the chance of conceive after an IVF/ICSI cycle.

A predictive model for women's assisted fecundity before starting the first IVF/ICSI treatment cycle

PURPOSE

To introduce a prognostic model for women's assisted fecundity before starting the first IVF/ICSI treatment cycle.

METHODS

In contrast to previous predictive models, we analyze two groups of women at the extremes of prognosis. Specifically, 708 infertile women that had either a live birth (LB) event in the first autologous IVF/ICSI cycle ("high-assisted-fecundity women", n = 458) or did not succeed in having a LB event after completing three autologous IVF/ICSI cycles ("low-assisted-fecundity women", n = 250). The initial sample of 708 women was split into two sets in order to develop (n = 531) and internally validate (n = 177) a predictive logistic regression model using a forward-stepwise variable selection.

RESULTS

Seven out of 32 initially selected potential predictors were included into the model: women's age, presence of multiple female infertility factors, number of antral follicles, women's tobacco smoking, occurrence of irregular menstrual cycles, and basal levels of prolactin and LH. The value of the c-statistic was 0.718 (asymptotic 95% CI 0.672-0.763) in the development set and 0.649 (asymptotic 95% CI: 0.560-0.738) in the validation set. The model adequately fitted the data with no significant over or underestimation of predictor effects.

CONCLUSION

Women's assisted fecundity may be predicted using a relatively small number of predictors. This approach may complement the traditional procedure of estimating cumulative and cycle-specific probabilities of LB across multiple complete IVF/ICSI cycles. In addition, it provides an easy-to-apply methodology for fertility clinics to develop and actualize their own predictive models.