AI Center for Precision Health, Weill Cornell Medicine-Qatar, Doha, Qatar.
Reproductive Medicine Unit, Sidra Medicine, Doha, Qatar.
J Med Internet Res. 2024 Jul 5;26:e53396. doi: 10.2196/53396.
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.
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.
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.
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.
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.
在体外受精（IVF）领域，人工智能（AI）模型为临床医生提供了宝贵的工具，可对卵巢刺激结果进行预测分析。预测和了解患者对卵巢刺激的反应有助于个性化药物剂量，预防不良后果（例如过度刺激），并提高受精和妊娠成功的可能性。鉴于准确预测在 IVF 程序中的重要作用，因此研究用于预测卵巢刺激结果的 AI 模型的现状变得尤为重要。
本综述的目的是全面研究文献，探讨用于预测 IVF 中卵巢刺激结果的 AI 模型的特点。
共检索了 6 个同行评审文献电子数据库，使用了 IVF 和 AI 的概念及其相关术语，检索时间截至 2023 年 8 月之前。由 2 位评审员独立根据纳入标准筛选记录。提取的数据通过叙述性综合进行整合和呈现。
在对 1348 篇文章进行审查后，有 30 篇符合预定的纳入标准。文献主要集中在预测取卵数量上。显微镜图像是主要的真实参考。综述研究还强调，最常采用的刺激方案是促性腺激素释放激素（GnRH）拮抗剂。在使用触发药物方面，人绒毛膜促性腺激素（hCG）是最常选择的药物。在机器学习技术中，支持向量机是首选。对于 AI 算法的验证，最常用的方法是留一交叉验证。曲线下面积是主要的评估指标。文献中用于 AI 算法开发的特征数量差异很大，从 2 到 28054 个特征不等。数据主要来源于患者人口统计学特征，其次是实验室数据，特别是激素水平。值得注意的是，绝大多数研究仅限于单个不孕诊所，且仅依赖非公开数据集。
这些研究结果突出表明，迫切需要使数据来源多样化，并探索不同的 AI 技术，以提高 AI 模型对卵巢刺激结果预测的准确性和泛化能力。未来的研究应优先进行多诊所合作，并考虑利用公共数据集，以实现更精确的 AI 驱动预测，从而最终提高患者护理和 IVF 成功率。
