BACKGROUND: In the realm of in vitro fertilization (IVF), artificial intelligence (AI) models serve as invaluable tools for clinicians, offering predictive insights into ovarian stimulation outcomes. Predicting and understanding a patient\'s response to ovarian stimulation can help in personalizing doses of drugs, preventing adverse outcomes (eg, hyperstimulation), and improving the likelihood of successful fertilization and pregnancy. Given the pivotal role of accurate predictions in IVF procedures, it becomes important to investigate the landscape of AI models that are being used to predict the outcomes of ovarian stimulation.
OBJECTIVE: The objective of this review is to comprehensively examine the literature to explore the characteristics of AI models used for predicting ovarian stimulation outcomes in the context of IVF.
METHODS: A total of 6 electronic databases were searched for peer-reviewed literature published before August 2023, using the concepts of IVF and AI, along with their related terms. Records were independently screened by 2 reviewers against the eligibility criteria. The extracted data were then consolidated and presented through narrative synthesis.
RESULTS: Upon reviewing 1348 articles, 30 met the predetermined inclusion criteria. The literature primarily focused on the number of oocytes retrieved as the main predicted outcome. Microscopy images stood out as the primary ground truth reference. The reviewed studies also highlighted that the most frequently adopted stimulation protocol was the gonadotropin-releasing hormone (GnRH) antagonist. In terms of using trigger medication, human chorionic gonadotropin (hCG) was the most commonly selected option. Among the machine learning techniques, the favored choice was the support vector machine. As for the validation of AI algorithms, the hold-out cross-validation method was the most prevalent. The area under the curve was highlighted as the primary evaluation metric. The literature exhibited a wide variation in the number of features used for AI algorithm development, ranging from 2 to 28,054 features. Data were mostly sourced from patient demographics, followed by laboratory data, specifically hormonal levels. Notably, the vast majority of studies were restricted to a single infertility clinic and exclusively relied on nonpublic data sets.
CONCLUSIONS: These insights highlight an urgent need to diversify data sources and explore varied AI techniques for improved prediction accuracy and generalizability of AI models for the prediction of ovarian stimulation outcomes. Future research should prioritize multiclinic collaborations and consider leveraging public data sets, aiming for more precise AI-driven predictions that ultimately boost patient care and IVF success rates.

OBJECTIVE: To investigate whether the ovarian stimulation with follitropin delta in an individualized algorithm-based manner is inferior to recombinant human-follicle stimulating\'s follitropin alfa or follitropin beta conventional dosing regarding a series of established primary endpoints.
METHODS: We conducted a registered systematic review (CRD42024512792) on PubMed-MEDLINE, Web of Science™, Cochrane Database of Systematic Reviews, and Scopus. Our search was designed to cover all relevant literature, particularly randomized controlled trials. We critically and comparatively analyzed the outcomes for each primary endpoint based on the intervention, reflected by the positive βhCG test, clinical pregnancy, vital pregnancy, ongoing pregnancy, live birth, live birth at 4 weeks, and multiple pregnancies.
RESULTS: Six randomized controlled trials were included in the quality assessment as priority manuscripts, revealing an 83.3% low risk of bias. Follitropin delta led to non-significant differences in each parameter of interest from positive βhCG test (691; 53.44% vs. 602; 46.55%), ongoing pregnancies (603; 53.79% vs. 518; 46.20%), clinical and vital pregnancies (1,073; 52.80% vs. 959; 47.19%), to live birth and at 4 weeks (595; 54.14% vs. 504; 45.85%) with only 2 losses, and even multiple pregnancies (8; 66.66% vs. 4; 33.33%). However, follitropin delta was well-tolerated among hypo- and hyper-responders without significant risk of ovarian hyperstimulation syndrome and/or preventive interventions in contrast with follitropin alfa or follitropin beta.
CONCLUSIONS: The personalized individualized-based algorithm dosing with follitropin delta is non-inferior to conventional follitropin alfa or follitropin beta. It is as effective in promoting a similar response in women without significant comparable adverse effects.

Patients with haematologic malignancies represent one of the most common groups referred for fertility preservation before gonadotoxic oncological treatment. The aim of this systematic review and meta-analysis was to evaluate the effect of haematologic cancer on ovarian reserve and response to ovarian stimulation compared with healthy controls. A total of eight observative studies were included in the final quantitative analysis. Despite a younger age (mean difference -4.17, 95% CI -6.20 to -2.14; P < 0.0001), patients with haematologic malignancy had lower serum anti-Müllerian hormone levels compared with the control group (MD -1.04, 95% CI -1.80 to -0.29; P = 0.007). The marginally higher total recombinant FSH dose (MD 632.32, 95% CI -187.60 to 1452.24; P = 0.13) and significantly lower peak oestradiol serum level (MD -994.05, 95% CI -1962.09 to -26.02; P = 0.04) were demonstrated in the study group compared with the healthy controls. A similar number of retrieved oocytes were achieved in both groups (MD 0.20, 95% CI -0.80 to 1.20; P = 0.69). In conclusion, haematologic malignancies may detrimentally affect ovarian function manifesting in decreased AMH serum levels despite a younger age compared with healthy controls. This effect can be overcome by the application of relevant IVF protocols and stimulation doses to achieve an adequate oocyte yield.

BACKGROUND: Follitropin delta is a novel recombinant follicle stimulating hormone preparation uniquely expressed in a human fetal retinal cell line by recombinant DNA technology. To date, no systematic review was available about the safety and the efficacy of the follitropin delta. The objective of this study was systematically reviewing the available literature and to provide updated evidence regarding the efficacy-safety profile of follitropin delta when compared to other gonadotropin formulations for ovarian stimulation in in vitro fertilization (IVF) and intracytoplasmic sperm injection (ICSI) cycles.
METHODS: An extensive search was performed to identify phase 1, phase 2 and phase 3 RCTs in humans focused on follitropin delta use for ovarian stimulation in IVF/ICSI cycles. The risk of bias and the overall quality of the evidence was analyzed. All data were extracted and analyzed using the intention-to-treat principle and expressed per woman randomized.
RESULTS: A total of 7 RCTs (1 phase 1 RCT, 2 phase 2 RCTs and 4 phase 3 RCTs) were included in the qualitative analysis, whereas data of three phase 3 RCTs were meta-analyzed. All trials compared personalized recombinant follitropin delta treatment versus conventional recombinant follitropin alfa/beta administration in potentially normo-responder patients who receive ovarian stimulation in GnRH antagonist IVF/ICSI cycles. No difference between two regimens was detected for clinical pregnancy rate [odds ratio (OR) 1.06; 95% confidence intervals (CI): 0.90, 1.24; P = 0.49; I2 = 26%], ongoing pregnancy rate (OR 1.15; 95%CI: 0.90, 1.46; P = 0.27; I2 = 40%), and live birth rate (OR 1.18; 95%CI: 0.89, 1.55; P = 0.25; I2 = 55%). No data were available regarding cumulative success rates. The rate of adoption of strategies to prevent ovarian hyperstimulation syndrome (OHSS) development (OR 0.45; 95%CI: 0.30, 0.66; P < 0.0001; I2 = 0%), and the rate of both early OHSS (OR 0.62; 95%CI: 0.43, 0.88; P = 0.008; I2 = 0%) and all forms of OHSS (OR 0.61; 95%CI: 0.44, 0.84; P = 0.003; I2 = 0%) were significantly lower in the group of patients treated with personalized follitropin delta treatment compared to those treated with conventional follitropin alfa/beta administration.
CONCLUSIONS: Personalized follitropin delta treatment is associated with a lower risk of OHSS compared to conventional follitropin alfa/beta administration in potentially normo-responder patients who receive ovarian stimulation in GnRH antagonist IVF/ICSI cycles. The absence of cumulative data does not allow definitive conclusions to be drawn regarding the comparison of the effectiveness of the two treatments.
UNASSIGNED: CRD42023470352 (available at http://www.crd.york.ac.uk/PROSPERO ).

Unexplained infertility accounts for 25% of infertility causes in the UK. Active intervention methods, such as intrauterine insemination (IUI) or in vitro fertilisation (IVF), are often sought. Despite the National Institute for Health and Care Excellence (NICE) recommending IVF for unexplained infertility, this recommendation has generated an ongoing debate, with few fertility clinics discontinuing the use of IUI as the first-line management of choice. In contrast to NICE, recent guidance released from the European Society for Human Reproduction and Embryology (ESHRE) in August 2023 supports the use of IUI as first-line. High-quality evidence behind such interventions is lacking, with current literature providing conflicting results.
This review aims to provide a literature overview exploring whether IUI or IVF should be used as first-line treatment for couples with unexplained infertility, in the context of current guidelines.
The primary outcome used to assess efficacy of both treatment methods is live birth (LB) rates. Secondary outcomes used are clinical pregnancy (CP) and ongoing pregnancy (OP) rates. A comprehensive literature search of 4 databases: Ovid MEDLINE, EMBASE, Maternity & Infant Care and the Cochrane Library were searched in January 2022. Upon removal of duplications, abstract screening, and full-text screening, a total of 34 papers were selected.
This review highlights a large discrepancy in the literature when examining pregnancy outcomes of IUI and IVF treatments. Evidence shows IUI increases LB and CP rates 3-fold compared to expectant management. Literature comparing IUI to IVF is less certain. The review finds the literature implies IVF should be used for first-line management but the paucity of high-quality randomised controlled trials (RCTs), coupled with heterogeneity of the identified studies and a lack of research amongst women > 40 years warrants the need for further large RCTs. The decision to offer IUI with ovarian stimulation (IUI-OS) or IVF should be based upon patient prognostic factors. We suggest that IUI-OS could be offered as first-line treatment for unexplained infertility for women < 38 years, with good prognosis, and IVF could be offered first to those > 38 years. Patients should be appropriately counselled to enable informed decision making.

The aim of this systematic review and meta-analysis was to quantify the effect of random start ovarian stimulation (RSOS) compared with conventional start ovarian stimulation (CSOS) in cancer patients before gonadotoxic treatment. The final analytical cohort encompassed 688 RSOS and 1076 CSOS cycles of cancer patients before gonadotoxic treatment. Eleven studies were identified by database searches of MEDLINE, Cochrane Library and cited references. The primary outcomes of interest were the number of oocytes and mature oocytes collected, the number of embryos cryopreserved and the metaphase II (MII)-antral follicle count (AFC) ratio. The studies were rated from medium to high quality (from 6 to 9) according to the Newcastle-Ottawa Quality Assessment Scale. The two protocols resulted in similar numbers of oocytes collected, MII oocytes, embryos available for cryopreservation and comparable MII-AFC and fertilization rates. The duration of ovarian stimulation was longer (standardized mean difference [SMD] 0.35, 95% CI 0.09 to 0.61; P = 0.009) and gonadotrophin consumption was higher (SMD 0.23, 95% CI 0.06 to 0.40; P = 0.009) in RSOS compared with CSOS. This systematic review and meta-analysis show that the duration of stimulation is longer, and the total gonadotrophin consumption is higher in cancer patients undergoing RSOS compared with those undergoing CSOS, with no significant effect on mature oocyte yield.

BACKGROUND: Ovarian torsion (OT) is a gynaecological emergency and requires prompt recognition and treatment in order to prevent the loss of ovarian function. Patients who are undergoing fertility treatment are at an increased risk of developing OT.
OBJECTIVE: The diagnosis of OT in patients undergoing fertility treatment can be challenging as they often present with abdominal pain and other non-specific symptoms. We highlight the importance of early diagnosis of suspected torsion and performed a literature review on cases of bilateral OT to review its presentation, investigation, and subsequent management.
METHODS: A 32-year-old nulliparous woman who was undergoing controlled ovarian stimulation presented with lower abdominal pain and was initially managed as ovarian hyperstimulation syndrome (OHSS). Her pain did not subside following conservative management and she proceeded to have a laparoscopy which demonstrated synchronous bilateral ovarian torsion (SBOT), both ovaries were detorted. Eight months later, she was preparing for her frozen embryo transfer (FET) cycle, patient again presented with significant right sided abdominal pain and was found to have a recurrent torsion of the right ovary which was again detorted successfully.
CONCLUSIONS: Clinicians should have a low-threshold to investigate and rule out OT in patients who present with lower abdominal pain, especially in those with additional risk factors for torsion. Patients with confirmed torsion can be successfully managed with detorsion of the ovaries. Further research is needed to determine the best management option for patients with recurrent torsion episodes.

UNASSIGNED: Endometriosis is an oestrogen-dependent disease that can cause subfertility in women who may require assisted reproductive technology (ART) to achieve their pregnancy goals.
UNASSIGNED: The aim of this study was to compare ART outcomes in women with endometriosis following the long GnRH-agonist controlled ovarian stimulation (COS) protocol with those taking the GnRH-antagonist COS protocol.
UNASSIGNED: MEDLINE, Embase and Web of Science were systematically searched in June 2022. Randomized controlled trials (RCTs) and observational studies comparing the long GnRH-agonist COS protocol and the GnRH-antagonist COS protocol in women with all stages/subtypes of endometriosis were included. Data were synthesized into comprehensive tables for systematic review. The Scottish Intercollegiate Guidelines Network (SIGN) checklists were used for the risk of bias assessment of non-randomized studies and randomized studies, and all the included studies were deemed to have acceptable quality.
UNASSIGNED: Eight studies (one RCT and seven observational) with 2695 patients (2761 cycles) were included. Most studies generally reported non-significant differences in clinical pregnancy or live birth rates regardless of the COS protocol used. However, the GnRH-agonist protocol may yield a higher total number of oocytes retrieved, especially mature oocytes. Conversely, the GnRH-antagonist protocol required a shorter COS duration and lower gonadotrophin dose. Adverse outcomes, such as rates of cycle cancellation and miscarriage, were similar between both COS protocols.
UNASSIGNED: Both the long GnRH-agonist and GnRH-antagonist COS protocols generally yield similar pregnancy outcomes. However, the long GnRH-agonist protocol may be associated with a higher cumulative pregnancy rate due to the higher number of retrieved oocytes available for cryopreservation. The underlying mechanisms of the two COS protocols on the female reproductive tract remain unclear. Clinicians should consider treatment costs, stage/subtype of endometriosis and pregnancy goals of their patients when selecting a GnRH analogue for COS. A well-powered RCT is needed to minimize the risk of bias and compare the risk for ovarian hyperstimulation syndrome.
UNASSIGNED: This review was prospectively registered at PROSPERO under Registration No. CRD42022327604.

The available literature is controversial regarding the association between the number of oocytes retrieved and the cumulative live birth rate (CLBR). Although some authors report a continuous increase in the CLBR with the number of oocytes retrieved, others have found a plateau. A systematic review was conducted, including all eligible studies published until June 2022, to determine the optimal number of oocytes retrieved to maximize the CLBR. We found a positive association between the number of oocytes and the CLBR. However, this association varies according to patients\' age. While in patients younger than 35 years, little benefit is derived from increasing the number of oocytes above 25-30, in patients older than 35 years, the number of oocytes seems to improve the CLBR until the extreme of reproductive age is reached. In women aged 44 years or older, the CLBR will be consistently low, independent of the number of oocytes retrieved.

OBJECTIVE: To explore the association between ovulation induction drugs and ovarian cancer.
METHODS: Systematic review and meta-analysis.
METHODS: Not applicable.
METHODS: Women without ovarian cancer who ever or never underwent ovarian induction.
METHODS: An extensive electronic search of the following databases was performed: PubMed, EMBASE, MEDLINE, Google Scholar, Cochrane Library and CNKI, from inception until January 2022. A total of 34 studies fulfilled our inclusion criteria and were included in the final meta-analysis. The odds ratio (OR) and random-effects model were used to estimate the pooled effects. The Newcastle-Ottawa Scale was used to assess the quality of included studies. Funnel plots and Egger tests were used to assess publication bias.
RESULTS: New diagnosed borderline ovarian tumor (BOT) and invasive ovarian cancer (IOC) between ovulation induction (OI) group and control (CT) group considering fertility outcome, OI cycles and specific OI drugs.
RESULTS: Primarily, there was no significant difference in the incidence of IOC and BOT between the OI and CT groups. Secondly, OI treatment did not increase the risk of IOC and BOT in the multiparous women, nor did it increase the risk of IOC in the nulliparous women. However, the risk of BOT appeared to be higher in nulliparous women treated with OI treatment. Thirdly, among women exposed to OI, the risk of IOC and BOT was higher in nulliparous women than in multiparous women. Fourthly, the risk of IOC did not increase with increasing OI cycles. Lastly, exposure to specific OI drugs also did not contribute to the risk of IOC and BOT.
CONCLUSIONS: Overall, OI treatment did not increase the risk of IOC and BOT in most women, regardless of OI drug type and OI cycle. However, nulliparous women treated with OI showed a higher risk of ovarian cancer, necessitating their rigorous monitoring and ongoing follow-up.