Streamlining follicular monitoring during controlled ovarian stimulation: a data-driven approach to efficient IVF care in the new era of social distancing

Harnessing Artificial Intelligence to Predict Ovarian Stimulation Outcomes in In Vitro Fertilization: Scoping Review

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.

Monitoring of controlled ovarian stimulation in IVF

Since the inception of in vitro fertilization (IVF), monitoring of controlled ovarian stimulation (COS) has traditionally involved numerous appointments for ultrasound and laboratory testing to guide medication use and dosing, determine trigger timing, and allow for measures to reduce the risk of ovarian hyperstimulation syndrome (OHSS). Recent advances in the field of assisted reproductive technology (ART) have called into question the timing and frequency of COS monitoring appointments, as discussed in this commentary.

The prospect of artificial intelligence to personalize assisted reproductive technology

Infertility affects 1-in-6 couples, with repeated intensive cycles of assisted reproductive technology (ART) required by many to achieve a desired live birth. In ART, typically, clinicians and laboratory staff consider patient characteristics, previous treatment responses, and ongoing monitoring to determine treatment decisions. However, the reproducibility, weighting, and interpretation of these characteristics are contentious, and highly operator-dependent, resulting in considerable reliance on clinical experience. Artificial intelligence (AI) is ideally suited to handle, process, and analyze large, dynamic, temporal datasets with multiple intermediary outcomes that are generated during an ART cycle. Here, we review how AI has demonstrated potential for optimization and personalization of key steps in a reproducible manner, including: drug selection and dosing, cycle monitoring, induction of oocyte maturation, and selection of the most competent gametes and embryos, to improve the overall efficacy and safety of ART.

Fertility Preservation During the COVID-19 Pandemic: Modified But Uncompromised

Purpose: Throughout COVID-19, our clinic remained operational for patients requiring urgent fertility preservation (FP). This study aimed to characterize changes to clinical protocols during the first wave of COVID-19 and compare outcomes to historical controls.

Methods: We performed a retrospective cohort study at a university fertility center examining all patients who underwent medically indicated FP cycles during the American Society for Reproductive Medicine (ASRM) COVID-19 Task Force-recommended suspension of fertility treatment (March 17–May 11, 2020) and patients from the same time period in 2019. FP care was modified for safety during the first wave of COVID-19 with fewer monitoring visits and infection control measures. FP cycle characteristics and outcomes were compared across years.

Results: The volume of cycles was nearly 30% higher in 2020 versus 2019 (27 vs. 19). Diagnoses, age, and anti-Mullerian hormone were similar between cohorts. More patients elected to pursue embryo cryopreservation over oocyte cryopreservation in 2020 versus 2019 (45.8% vs. 5.2%, p < 0.005). Patients managed during COVID-19 had fewer monitoring visits (5 ± 1 vs. 6 ± 1, p = 0.02), and 37.5% of cycles utilized a blind trigger injection. There was no difference in total days of ovarian stimulation (11 ± 1 vs. 11 ± 2, p > 0.05), but 2020 cycles utilized more gonadotropin (4770 ± 1480 vs. 3846 ± 1438, p = 0.04). There was no difference in total oocytes retrieved (19 ± 14 vs. 22 ± 12, p > 0.05) or mature oocytes vitrified (15 ± 12 vs. 17 ± 9, p > 0.05) per cycle.

Conclusions: FP continued during COVID-19, and more cycles were completed in 2020 versus 2019. Despite minimized monitoring, outcomes were optimal and equivalent to historical controls, suggesting FP care can be adapted without compromising outcomes.