Adaptive data-driven models to best predict the likelihood of live birth as the IVF cycle moves on and for each embryo transfer

Artificial intelligence and assisted reproductive technology: A comprehensive systematic review

The objective of this review is to evaluate the contributions of Artificial Intelligence (AI) to Assisted Reproductive Technologies (ART), focusing on its role in enhancing the processes and outcomes of fertility treatments. This study analyzed 48 relevant articles to assess the impact of AI on various aspects of ART, including treatment efficacy, process optimization, and outcome prediction. The effectiveness of different machine learning paradigms-supervised, unsupervised, and reinforcement learning-in improving ART-related procedures was particularly examined. The findings indicate that AI technologies significantly enhance ART processes by refining tasks such as embryo and sperm analysis and facilitating personalized treatment plans based on predictive modeling. Notable improvements were observed in the accuracy of diagnosing and predicting successful outcomes in fertility treatments. AI-driven models provided more precise forecasts of the optimal timing for clinical interventions such as egg retrieval and embryo transfer, which are critical to the success of ART cycles. The integration of AI into ART represents a transformative advancement, substantially improving the precision and efficiency of fertility treatments. The continuous evolution of AI methodologies is likely to further revolutionize this field, enabling more tailored and successful treatment approaches. AI is becoming an indispensable tool in reproductive medicine, enhancing both the effectiveness of treatments and the clinical decision-making process. This review underscores the potential of AI to act as a catalyst for innovative solutions in the optimization of ART.

Patient-Centric In Vitro Fertilization Prognostic Counseling Using Machine Learning for the Pragmatist

Although in vitro fertilization (IVF) has become an extremely effective treatment option for infertility, there is significant underutilization of IVF by patients who could benefit from such treatment. In order for patients to choose to consider IVF treatment when appropriate, it is critical for them to be provided with an accurate, understandable IVF prognosis. Machine learning (ML) can meet the challenge of personalized prognostication based on data available prior to treatment. The development, validation, and deployment of ML prognostic models and related patient counseling report delivery require specialized human and platform expertise. This review article takes a pragmatic approach to review relevant reports of IVF prognostic models and draws from extensive experience meeting patients' and providers' needs with the development of data and model pipelines to implement validated ML models at scale, at the point-of-care. Requirements of using ML-based IVF prognostics at point-of-care will be considered alongside clinical ML implementation factors critical for success. Finally, we discuss health, social, and economic objectives that may be achieved by leveraging combined human expertise and ML prognostics to expand fertility care access and advance health and social good.

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.

Nonlinear relationship between gonadotropin total dose applied and live birth rates in non-PCOS patients: a retrospective cohort study

The purpose of this article is to explore the relationship between the total dose of follicle-stimulating hormone (FSH) applied during controlled ovulation stimulation and the live birth rates (LBRs) in non-PCOS population. Many studies have found no difference between the dose of FSH application and pregnancy outcomes such as clinical pregnancy rates after fresh embryo transfer. However, a recent large retrospective analysis found a negative correlation between live birth rates and increasing dose of FSH. It is still controversial about the association between FSH dose and LBRs. In addition, no studies have yet explored the nonlinear relationship between FSH and LBRs. This cohort study included a total of 11,645 patients who had accepted IVF/intracytoplasmic sperm injection (ICSI) at the second hospital of Hebei medical university between December 2014 to December 2019. PCOS was identified by Rotterdam PCOS criteria. We researched the association between FSH total dose and live birth rates (LBRs) using multivariate regression analysis. In addition, a model for nonlinear relationships based on a two-part linear regression was applied. The analysis of threshold effects indicated that LBR increased with every 1000 IU FSH when the concentration of FSH was lower than 1410 IU (OR 1.55, 95% CI [1.05, 2.28]); however, a negative association between FSH dose and LBR (OR 0.94, 95% CI [0.89, 0.99]) was found when the FSH total dose was higher than 1410 IU. It is worth noting that the relationship between LBR and FSH dose varied among patients of different ages (OR 0.92 vs 1.06, P for interaction < 0.05).

Associations between Phthalate Metabolite Concentrations in Follicular Fluid and Reproductive Outcomes among Women Undergoing in Vitro Fertilization/Intracytoplasmic Sperm Injection Treatment

BACKGROUND

Phthalates have been reported to impair fertility in various studies. However, evidence exploring the associations between phthalate metabolites in follicular fluid (FF) and reproductive outcomes is lacking.

OBJECTIVES

To investigate the associations between phthalate metabolite concentrations in FF and in vitro fertilization/intracytoplasmic sperm injection (IVF/ICSI) outcomes among women recruited from a fertility clinic.

METHODS

We included 641 women undergoing IVF/ICSI treatment from December 2018 to January 2020. The levels of eight phthalate metabolites, including monoethyl phthalate (MEP), mono-isobutyl phthalate (MiBP), mono-n -butyl phthalate (MBP), monobenzyl phthalate (MBzP), mono(2-ethylhexyl) phthalate (MEHP), mono(2-ethyl-5-hydroxyhexyl) phthalate (MEHHP), mono(2-ethyl-5-oxohexyl) phthalate (MEOHP), and mono(2-ethyl-5-carboxypentyl) phthalate (MECPP), were quantified in FF collected on the oocyte retrieval day. Associations between quartiles of individual phthalate metabolite concentrations and nine IVF/ICSI outcomes, including oocyte yield, mature oocyte number, two distinct pronuclei (2PN) zygote number, fertilization rate, blastocyst formation rate, implantation, clinical pregnancy, miscarriage, and live birth, were estimated with generalized linear models. The effects of phthalate mixtures on IVF/ICSI outcomes were assessed using Bayesian kernel machine regression (BKMR) models.

RESULTS

After adjusting for relevant confounders, elevated quartiles of MBzP, MEHHP, and MEHP in FF were inversely associated with the numbers of retrieved oocytes, mature oocytes, and 2PN zygotes (all p for trends < 0.10 ). In comparison with the lowest quartile, the highest quartile of molar sum of di(2-ethylhexyl) phthalate metabolites (Σ DEHP ) was associated with a reduction of 9.1% [95% confidence interval (CI): - 17.1 % , - 0.37 % ] and 10.3% (95% CI: - 18.8 % , - 0.94 % ) in yielded oocyte and mature oocyte numbers, respectively. Furthermore, the BKMR models revealed inverse associations between phthalate mixtures and the numbers of retrieved oocytes and mature oocytes. We generally found null results for implantation, clinical pregnancy, miscarriage, and live birth.

DISCUSSION

Certain phthalate metabolites in FF are inversely associated with the numbers of retrieved oocytes, mature oocytes, and 2PN zygotes among women undergoing IVF/ICSI treatment. https://doi.org/10.1289/EHP11998.

Oocyte donation outcomes in endometriosis patients with multiple IVF failures

RESEARCH QUESTION

What are the reproductive outcomes and the prognostic factors of live birth rates in patients with endometriosis referred to oocyte donation after multiple IVF failures?

DESIGN

Observational cohort study including all women with endometriosis-related infertility and two or more failed IVF/intracytoplasmic sperm injection (ICSI) cycles referred to oocyte donation between January 2013 and June 2022. Endometriosis was diagnosed based on published imaging criteria, and was confirmed histologically in women who had a history of surgery for endometriosis. The main outcome measured was the cumulative live birth rate (CLBR). The characteristics of women who had a live birth were compared with those who did not using univariate and multivariate analysis to identify determinant factors of fertility outcome.

RESULTS

Fifty-seven patients underwent 90 oocyte donation cycles after 244 failed autologous IVF cycles. The mean ± SD age of the population was 36.8 ± 3.3 years, with a mean duration of infertility of 3.6 ± 2.2 years, and a mean number of autologous IVF/ICSI cycles of 4.4 ± 2.3 cycles per patient. Three patients (5.3%) had superficial peritoneal endometriosis, two patients (3.5%) had ovarian endometriomas, and 52 patients (91.2%) had deep infiltrating endometriosis, among which 30 patients (57.7%) had bowel lesions. Thirty patients (52.6%) had associated adenomyosis. Overall, CLBR per patient was 36/57 (63.2%). After multivariate analysis, only being nulligravida (P=0.002) remained an independent negative predictive factor of the live birth rate. Previous surgery did not impact reproductive outcomes.

CONCLUSION

This study suggests that oocyte donation appears to be a viable option to optimize the live birth rate in women with endometriosis-related infertility and recurrent IVF failures.