JMIR Publications

ABSTRACT

Background:

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 (e.g. hyper-stimulation), 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 employed to predict the outcomes of ovarian stimulation.

Objective:

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:

Methods:

Six 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 two reviewers against the eligibility criteria. The extracted data were then consolidated and presented through narrative synthesis.

Results:

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 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 (SVM). As for the validation of AI algorithms, the hold-out cross-validation method was the most prevalent. Area under the curve (AUC-ROC) 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 was 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 non-public datasets.

Conclusions:

Conclusion: 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 prediction of ovarian stimulation outcomes. Future research should prioritize multi-clinic collaborations and consider leveraging public datasets, aiming for more precise AI-driven predictions that ultimately boost patient care and IVF success rates.