Artificial Intelligence in Reproductive Medicine: Transforming Assisted Reproductive Technologies

Day 2 embryo transfer (ET) and day 3 ET afford similar reproductive outcomes in the poor responder

People in low- and middle-income countries face many obstacles when trying to access fertility treatments. These challenges include high costs, the need for specialized medical facilities, and cultural beliefs that may discourage seeking help. This paper explores how artificial intelligence (AI) and automation could help overcome some of these barriers and make fertility treatments more widely available. It examines how AI may improve the accuracy, efficiency, and consistency of different steps in fertility treatments, such as choosing the healthiest embryos, analyzing sperm, evaluating eggs, and planning treatment. The paper also discusses how automation could simplify laboratory procedures, from growing embryos and freezing them for future use to the possibility of fully automating the in vitro fertilization (IVF) process, which could help lower costs and make these treatments more accessible. Finally, this paper addresses the ethical and practical challenges associated with using these technologies, including potential biases in AI, equitable access, quality control, data privacy, job implications, and cultural sensitivities.Lay summaryThis paper explores how AI and automation could help make fertility treatments more accessible in low- and middle-income countries (LMICs). Many individuals and couples face difficulties conceiving, and assisted reproductive technology (ART) – which includes procedures such as intrauterine insemination (IUI) and IVF – offers them a chance to build a family. However, ART is often out of reach in LMICs due to high costs, the need for specialized medical facilities, and cultural barriers. AI and automation have the potential to improve accuracy, efficiency, and consistency in ART procedures, such as embryo selection, sperm and egg assessment, and treatment planning. Automation could also streamline laboratory processes, including embryo culture and freezing, which may eventually lead to more affordable and scalable fertility treatments. By reducing human error and dependence on highly trained specialists, AI-driven technologies could help lower costs and make ART available to more people. This paper also considers the ethical and practical challenges of using AI in reproductive medicine, including potential biases in AI algorithms, fairness in access to treatment, data privacy, workforce impact, and cultural sensitivities. Fertility treatments can be life-changing for those struggling with infertility due to medical conditions, age, or personal circumstances. They also provide opportunities for same-sex couples and individuals who want to start a family. However, in LMICs, infertility is often surrounded by social stigma, economic hardship, and limited medical resources, making access to ART even more difficult. By integrating AI and automation into reproductive medicine, it may be possible to break down these barriers, reduce costs, and create more inclusive and accessible fertility care. These advancements have the potential to bring hope to millions who dream of parenthood but currently lack the means to pursue it.

After completing this article, readers should be able to: 1. Describe the outcomes of assisted reproductive technologies (ART) for singleton, twin, and other multiple births. 2. Describe the role of fertility in adverse outcomes seen with ART births. 3. Review the association of birth defects with ART. 4. Delineate the association of disease of genomic imprinting with ART. 5. Describe the relationship between ART and the subsequent incidence of neurodevelopmental sequelae. In the 1977 ruling “Carey v. Population Services International,” the United States Supreme Court ruled that the decision to bear children is constitutionally protected. (1) Significant interest already had been shown in the development and improvements of in vitro fertilization (IVF) for infertile couples. The first human pregnancy and human birth using IVF were reported by Steptoe and Edwards in the United Kingdom. (2) Their work resulted in the first baby born via reproductive technologies, Louise Brown, born on July 25, 1978, at Oldham General Hospital in Oldham, United Kingdom. (3) She was born via a planned cesarean section, and her birthweight was 2.61 kg. The first successful viable IVF in the United States was performed by Jones and Seager-Jones in 1981 in Norfolk, Virginia. (4) Assisted reproductive technologies (ART) have seen a recent surge in popularity. The Centers for Disease Control and Prevention (CDC) reported that 122,872 cycles of ART were initiated in 2003, resulting in the delivery of 48,756 neonates, (5) accounting for approximately 1% of all neonates delivered in the United States. The percentage is higher in many countries, including Denmark, where it is estimated that 5% of all deliveries are with the assistance of ART. (6) Couples pursue ART for myriad reasons, including tubal transport factors, ovulatory dysfunction, uterine factors, endometriosis, male- and female-specific factors, and when a cause of infertility is unknown. (5) It would be very …

This review did not find sufficient evidence to support the use of one cycle regimen in preference to another in preparation for FET in subfertile women with regular ovulatory cycles. The most common modalities for FET are natural cycle with or without HCG trigger or endometrial preparation with HT, with or without GnRHa suppression. We identified only four direct comparisons of these two modalities and there was insufficient evidence to support the use of either one in preference to the other.

The use of insulin-sensitising agents, such as metformin, in women with polycystic ovary syndrome (PCOS) who are undergoing ovulation induction or in vitro fertilisation (IVF) cycles has been widely studied. Suppression of insulin levels with metformin might reduce the hyperinsulinaemia and hyperandrogenism suppression of the ovarian response. As a consequence, metformin could improve both pregnancy and live birth rates. To determine the effectiveness of metformin as a co-treatment during IVF or intra-cytoplasmic sperm injection (ICSI) in achieving pregnancy or live birth in women with PCOS. The Menstrual Disorders and Subfertility Group Trials Register, Cochrane Central Register of Controlled Trials (CENTRAL) (The Cochrane Library), MEDLINE, EMBASE, LILACS, the meta Register of Controlled Trials, and reference lists of articles were searched (to week 4, September 2008). Types of studies: randomised controlled trials (RCTs) comparing metformin treatment with placebo or no treatment in women with PCOS who underwent IVF or ICSI treatment. women of reproductive age with anovulation due to PCOS with or without co-existing infertility factors.Types of interventions: metformin administered before and during IVF or ICSI treatment.Types of outcome measures: live birth rate, clinical pregnancy rate, miscarriage rate, incidence of ovarian hyperstimulation syndrome (OHSS), incidence of patient-reported side effects, serum estradiol level on the day of trigger, serum androgen level, and fasting insulin and glucose levels. Two review authors independently extracted the data according to the protocol. The methods of randomisation and allocation concealment, and characteristics of the studied groups were evaluated. This review found no evidence that metformin treatment before or during assisted reproductive technique (ART) cycles improved live birth or clinical pregnancy rates. The pooled odds ratio (OR) for live birth rate (3 RCTs) was 0.77 ( 95% CI 0.27 to 2.18) and for clinical pregnancy rate (5 RCTS) was 0.71 (95% CI 0.39 to 1.28). The risk of OHSS in women with PCOS and undergoing IVF or ICSI cycles was reduced with metformin (pooled OR 0.27, 95% CI 0.16 to 0.47). This review found no evidence that metformin treatment before or during ART cycles improves live birth or pregnancy rates. The risk of OHSS in women with PCOS and undergoing IVF or ICSI cycles was reduced with metformin. Further large RCTs are necessary to definitively answer if the use of metformin in PCOS women undergoing ART improves live birth and pregnancy rates.

What does the SART success rate for a given IVF program mean?

Acknowledgements: We would like to thank the following for their contributions to the 2020 update. All staff at the editorial base of the Cochrane Gynaecology and Fertility Review Group; and in particular, Helen Nagels (Managing Editor) and Information Specialist Marian Showell, for help with the literature searches. Drs Jeanette MacKenzie, Evi Vogiatzi and Rik van Eekelen who provided peer review comments. We also thank all the authors who replied to our email queries about their study: Dr Elisabet Clua, Dr Maria Luisa López‐Regalado and Dr OM Abuzeid. We also thank the following. Zabeena Pandian, who was the lead author of the original review and two subsequent updates. Other co‐authors for their contribution in the previous versions: Allan Templeton, Ozkan Ozturk, Gamal Serour, and Jane Marjoribanks. Statistician Andy Vail (University of Manchester University, UK) for methodological advice.

To analyze cumulative and single-cycle success rates of IVF and intracytoplasmic sperm injection (ICSI) separately in relation to female age, fertilization modality, and first-cycle outcome. The study involved 2997 patients and couples, respectively, who underwent 5339 fresh and 3006 cryo cycles using pronuclear-stage oocytes. Fertilization was achieved by the conventional IVF or ICSI. Because of legal restrictions in Germany, no embryo selection was performed. All cycles were documented prospectively. Kaplan-Meier survival rates were calculated for all treatment cycles and transferred embryos. Essentially, the success of assisted reproductive technology (ART) depends on a woman's age and on skilful counselling. Cumulative pregnancy and live-birth rates are the best indicators of successful ART. Probably for the first time, we determined these cumulative rates separately for IVF and ICSI, and found them to be almost identical. Live-birth rates reached 70-95%, except for women aged over 40years, whose chances of life birth are limited to about 25%. Live-birth rate per retrieval was 25.61% for IVF and 26.3% for ICSI. Time to pregnancy was shorter for women who underwent a successful treatment in their first cycle. The primary intention for the choice of fertilization modality between IVF and ICSI is the prevention of a relative or total fertilization failure. Such treatment failure is best prevented through ICSI, which results in slightly higher clinical pregnancy rates per started cycle. After embryo transfer, there are no differences in the success rates of IVF and ICSI. The supposed cumulative live-birth rates are useful as a basis for counselling subfertile couples to help reduce the high discontinuation rate, which is still the main reason for inefficacy in ART. Following an unsuccessful first treatment cycle, the prognosis remains positive, but until success is achieved, more treatment cycles are necessary.

MP42-05 EFFECT OF VARICOCELE REPAIR ON PREGNANCY AND LIVE BIRTH RATES IN SEVERE OLIGOSPERMIC PATIENTS UNDERGOING ASSISTED REPRODUCTIVE TECHNOLOGY

Novel technologies for selecting the best sperm for in vitro fertilization and intracytoplasmic sperm injection

IntroductionMany patients who undergo assisted reproductive technology (ART) suffer from recurrent implantation failure (RIF). The addition of hyaluronic acid (HA) to the transfer medium is one of several methods to improve pregnancy outcomes. We investigated whether HA could improve the live birth and clinical pregnancy rates of RIF patients.MethodsThis study included 248 RIF patients, who were divided into two groups: the control (CTL) group (n=137), which received transfer medium without HA, and the HA group (n=111), which received transfer medium with HA. The two groups were compared according to the ART outcome.ResultsThe primary outcomes were the clinical pregnancy and live birth rates. Secondary outcomes include a positive urine pregnancy test, the implantation, ongoing pregnancy, multiple pregnancy, clinical miscarriage, and ectopic pregnancy rates, foetal or congenital defects, obstetric complications, infant birth weight and any related adverse events. Regarding the primary outcomes, the clinical pregnancy rate was significantly higher in the HA group than in the control group, and there was no significant difference in the live birth rate (LBR) between the HA and control groups. Regarding the secondary outcomes, the implantation, multiple pregnancy and ectopic pregnancy rates were similar between the two groups.DiscussionOur findings supported the conclusion that HA can improve the clinical pregnancy rate of patients with RIF undergoing FET cycles, but the live birth rate was not significantly improved with the addition of HA to the traditional transfer medium.

Outcomes of assisted reproductive technology after radical abdominal trachelectomy for early-stage cervical cancer

Background Previously, low molecular weight heparin (LMWH) has shown good anti-thrombotic effects and helped improve pregnancy outcomes for women with thrombotic diseases undergoing assisted reproductive technology (ART), prompting its use in women without thrombotic disease. However, there are few standardized medication guidelines for LMWH use in non-thrombotic patients, and it is unclear whether LMWH truly benefits pregnancy outcomes in these patients. There we want to investigate whether LMWH affects pregnancy outcomes of patients without thrombophilia undergoing ART. Methods A total of 3067 infertile women who were undergoing their fresh in vitro fertilization (IVF)/intracytoplasmic sperm injection (ICSI) cycle in the Reproductive Medicine Center, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology in 2019 were finally eligible for this retrospective cohort study, with 119 and 2948 administered with LMWH and without LMWH respectively. Clinical pregnancy rate (CPR) and the secondary outcomes include live birth rate (LBR), miscarriage rate (MR), multiple pregnancy rates (MPR), biochemical pregnancy rate (BPR) and ectopic pregnancy rate (EPR) were compared among these two groups. Results Before adjustment for confounders, MPR (8.4% vs. 3.1%, P = 0.001) and MR (15.1% vs. 6.2%, P<0.001) were higher in the LMWH group while CPR (53.8% vs. 46.8%, P = 0.133), LBR (37.8% vs. 40.5%, P = 0.553), BPR (6.7% vs. 6.0%, P = 0.759) and EPR (0.0% vs. 0.7%, P = 1.000) were similar compared to the control group. To investigate the correlation of LMWH administration, confounding variables were adjusted by multivariable logistic regression model and three Propensity score (PS) methods. In multivariable logistic regression, there were significantly higher CPR (AOR = 1.54; 95% CI, 1.05–2.27; P = 0.027) and MR (AOR = 2.93; 95% CI, 1.73–4.97; P < 0.001) among patients with LMWH, without an increase in LBR (AOR = 1.03; 95% CI, 0.70–1.53; P = 0.877), MPR (AOR = 1.29; 95% CI, 0.59–2.81; P = 0.529), BPR (OR = 1.17, 95% CI, 0.56–2.45; P = 0.674), which were consistent in PS Adjustment, and Inverse Probability of Treatment Weighting using propensity score (IPTW), but not in the Propensity score matching (PSM) (1:1) analysis. Subgroup analyses showed that CPR and MR were increased in the LMWH group in the patients with age ≤ 35 years, body mass index (BMI) ≤ 24 and without recurrent pregnancy loss (RPL). Conclusions Low molecular weight heparin may improve clinical pregnancy but not live birth in non-thrombophilic women undergoing ART.

Infertility affects up to 17.5% of couples of reproductive age, which significantly increases the demand for assisted reproductive technologies (ART). Despite various transformations and modernisation of programmes, the live birth rate with in vitro fertilisation (IVF) remains low, resulting in the need for several protocols to achieve live births. An important factor in the success of IVF is the qualification of specialists, but despite its high level, the human factor and a certain amount of subjectivity in the work of reproductologists and embryologists cannot be avoided. Artificial Intelligence (AI) offers significant opportunities to improve various aspects of IVF, for example, AI models can accurately predict hormone doses, and automate ultrasound monitoring, reducing examination time. AI also improves sperm selection for intracytoplasmic injection and helps select embryos with the best chance of implantation, improving accuracy and reducing subjective evaluation. In addition, AI can play an important role in training professionals, improving their skills and increasing the accuracy of decision-making. The introduction of AI into clinical practice is a promising area for improving IVF outcomes

Study question Can real-world data (RWD) offer valuable insights into the management of assisted reproductive technology (ART) and enhance patient care? Summary answer OPERA project provided a descriptive analysis of RWD from ART cycles, facilitating an in-depth evaluation to enhance the efficiency and effectiveness of ART procedures. What is known already ART is widely used for infertility treatment, with outcomes influenced by patient characteristics and stimulation protocols. Randomized controlled trials (RCTs) are widely regarded as the gold standard for evaluating the effectiveness of interventions. However, a key limitation of RCTs is that they may not fully reflect the benefits and risks of treatments in the broader patient populations encountered in clinical practice. In contrast, understanding RWD is crucial. RWE offers a complementary approach to RCTs, providing valuable scientific knowledge that can inform clinical decision-making. Study design, size, duration The OPERA project, sponsored by FROM Foundation ETS, is an European observational retrospective academic multicentre study analyzing 95,108 ART cycles performed between 2016 and 2020 in 18 centers across Italy and Germany, all using the same database, MediTex.These 95,108 ART cycles include 64,081 ovarian stimulation cycles and 31,027 frozen embryo transfer (FET) cycles derived from them. Participants/materials, setting, methods Data from the MedITEX database, collected across 18 ART centers, were securely transmitted to the Electronic Data Capture system ICE and managed/anonymized in accordance with GDPR and GxP regulations. The study included patient demographics, hormonal profiles, and ART protocols. Outcomes such as oocyte retrieval, fertilization rates, embryo transfers, and pregnancy results (fresh and frozen) were analyzed. Main results and the role of chance Among the 64,081 ovarian stimulation cycles, recombinant FSH was the most commonly used gonadotropin, accounting for 33.4% of cycles; GnRH antagonists were preferred, accounting for 78.4% of cycles. The median peak estradiol level was 1,028 pg/mL. Ovarian pick-up (OPU) was achieved in 93% of cycles, while the remaining 7% of cycles were cancelled before OPU, mainly due to poor ovarian response. The median number of oocytes retrieved per cycle was 8. ICSI was the predominant insemination technique, used in 72.1% of cycles. In 41,3% of stimulation cycles it was possible to cryopreserve oocytes or embryos. For fresh embryo transfer (ET) cycles, the clinical pregnancy rate (CPR) was 33.8%, and the live birth rate (LBR) was 25.8%. For frozen embryo transfer (FET), CPR and LBR were similar, at 34.2% and 24.3%, respectively, with a slightly higher miscarriage rate in FET cycles (28.9% vs 23.8% in fresh ET). The cumulative pregnancy rate and cumulative live birth rate were 39.3% and 30.2%. Overall, OPERA data indicate that the protocols used are very safe, with the risk of Ovarian hyperstimulation syndrome remaining below 5% of initiated cycles. Limitations, reasons for caution The retrospective design may introduce bias, and data are limited to specific centers and populations. However, by integrating diverse healthcare systems, OPERA provides valuable information into treatment differences and outcomes. Such a broader dataset enhances the ability to analyze and optimize ART procedures, also through the application of artificial intelligence algorithms. Wider implications of the findings OPERA enables a range of comparisons across treatments, laboratory results, and outcomes. It offers a comprehensive descriptive analysis of ART procedures, from couple selection and treatment choices to final outcomes. With the integration of AI, the database has the potential to enhance the efficiency and effectiveness of various interventions. Trial registration number No