Artificial Intelligence in Ovarian Stimulation

IF 3.5 2区医学 Q1 OBSTETRICS & GYNECOLOGY Reproductive biomedicine online Pub Date : 2024-11-01 Epub Date: 2024-12-04 DOI:10.1016/j.rbmo.2024.104513

Fernanda Pacheco, Nabil Arrach

{"title":"Artificial Intelligence in Ovarian Stimulation","authors":"Fernanda Pacheco, Nabil Arrach","doi":"10.1016/j.rbmo.2024.104513","DOIUrl":null,"url":null,"abstract":"<div><div>Ovarian stimulation is a critical step in assisted reproductive technologies (ART), involving numerous decisions about medication protocols, dosing, and timing, which can be tailored to each patient's unique profile. According to the 2020 ESHRE Guidelines<sup>1</sup>, there are 84 recommendations overall, including 7 for pre-stimulation management and 40 for pituitary suppression. However, with variability in patient response, big data generated at <em>in vitro</em> fertilization (IVF) clinics, and the complexity of decision-making, few doctors have the training and experience to make the most efficient choices consistently.</div><div>Artificial Intelligence (AI) offers a promising solution, enabling individualized and optimized decision-making in ovarian stimulation. By analyzing large datasets from previous IVF cycles, AI can support fertility doctors by recommending personalized treatment plans, optimizing the number of oocytes retrieved, and improving patient outcomes.</div><div>AI has the potential to enhance several critical areas in the ovarian stimulation process:</div><div>1. Gonadotropin Dosing: AI models can predict the optimal starting dose of gonadotropins based on patient characteristics such as age, ovarian reserve, and hormone levels. This reduces the risk of over- or under-stimulation, lowering the chances of ovarian hyperstimulation syndrome (OHSS) or a failed cycle.</div><div>2. Trigger Timing: AI can analyze follicular growth and hormone levels to recommend the best time to administer the trigger shot, ensuring the retrieval of mature oocytes at the optimal time. AI's ability to provide real-time data analysis supports more precise decisions regarding when to induce ovulation.</div><div>3. Predictive Models for Success: AI tools can estimate the probability of achieving live birth (LB) with each cycle, using data from thousands of previous cycles. These predictions can help doctors provide more personalized counseling, set realistic expectations, and adjust treatment plans accordingly.</div><div>A literature review on PubMed found 19 relevant studies on the subject. Notably, Banerjee et al.<sup>3</sup> developed an AI tool to predict live birth (LB) in the second cycle (C2) based on data from the first cycle (C1). Their model, trained on 1,676 cycles, showed LB rates of 29% for C1, 18% for C2, and 14% for C3. Of those who did not achieve live birth in C1, 71% returned for C2, while 39% dropped out. External validation with an independent dataset (2007-2008) demonstrated that the AI model predicted LB 35.5% better than age-only models, providing valuable insights for patient counseling and treatment planning.</div><div>Letterie and MacDonald<sup>4</sup> tested a decision-support system for four critical decisions in ovarian stimulation: continuing or stopping stimulation, triggering or canceling the cycle, adjusting medication, and determining follow-up intervals. Compared to experts' decisions, the system had an accuracy of 96% for triggering or canceling cycles, although medication adjustments showed lower accuracy (82%).</div><div>Reuvenny <sup>5</sup> et al. conducted a retrospective study with over 9,000 ICSI and freeze-all cycles to test AI's ability to predict optimal trigger timing. They found that AI-recommended timing resulted in an average increase of 4.8 oocytes and 3.4 mature oocytes (MII) in freeze-all cycles compared to physician-led decisions. The AI system often recommended later triggers than physicians, who tended to trigger earlier.</div><div>While AI offers numerous advantages—such as objectivity, precision, standardization, automation, and time optimization—there are several barriers to its widespread adoption:</div><div>1. Data Quality and Integration: AI models rely on vast amounts of high-quality data, but variability in clinic practices, protocols, and record-keeping can hinder data standardization and integration.</div><div>2. Validation and Diversity: AI systems need validation across diverse populations to ensure accuracy and applicability. Current datasets may need to represent the global IVF patient population adequately.</div><div>3. Physician Trust and Education: For AI to be fully embraced, fertility specialists need to trust AI's recommendations and understand how they are derived. Continuous education and training on AI technologies are essential for successful clinic adoption.</div><div>4. Ethical and Regulatory Concerns: Using AI in clinical decision-making raises ethical questions, particularly regarding accountability in cases where AI-led decisions result in adverse outcomes. Regulatory frameworks must also evolve to support the integration of AI into clinical practice.</div><div><strong>Conclusion</strong> Integrating AI in ovarian stimulation can revolutionize IVF practice, particularly in clinics with limited staff or resources. By enhancing objectivity, standardization, precision, and efficiency, AI can optimize patient outcomes and reduce variability in treatment success. However, challenges related to data quality, diversity, regulation, and physician education must be addressed to unlock AI's full potential. With the proper support, AI can empower fertility doctors to make better, more informed decisions, ultimately improving patient experiences and success rates in assisted reproduction.</div></div>","PeriodicalId":21134,"journal":{"name":"Reproductive biomedicine online","volume":"49 ","pages":"Article 104513"},"PeriodicalIF":3.5000,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Reproductive biomedicine online","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1472648324007028","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/12/4 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"OBSTETRICS & GYNECOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Ovarian stimulation is a critical step in assisted reproductive technologies (ART), involving numerous decisions about medication protocols, dosing, and timing, which can be tailored to each patient's unique profile. According to the 2020 ESHRE Guidelines¹, there are 84 recommendations overall, including 7 for pre-stimulation management and 40 for pituitary suppression. However, with variability in patient response, big data generated at in vitro fertilization (IVF) clinics, and the complexity of decision-making, few doctors have the training and experience to make the most efficient choices consistently.

Artificial Intelligence (AI) offers a promising solution, enabling individualized and optimized decision-making in ovarian stimulation. By analyzing large datasets from previous IVF cycles, AI can support fertility doctors by recommending personalized treatment plans, optimizing the number of oocytes retrieved, and improving patient outcomes.

AI has the potential to enhance several critical areas in the ovarian stimulation process:

1. Gonadotropin Dosing: AI models can predict the optimal starting dose of gonadotropins based on patient characteristics such as age, ovarian reserve, and hormone levels. This reduces the risk of over- or under-stimulation, lowering the chances of ovarian hyperstimulation syndrome (OHSS) or a failed cycle.

2. Trigger Timing: AI can analyze follicular growth and hormone levels to recommend the best time to administer the trigger shot, ensuring the retrieval of mature oocytes at the optimal time. AI's ability to provide real-time data analysis supports more precise decisions regarding when to induce ovulation.

3. Predictive Models for Success: AI tools can estimate the probability of achieving live birth (LB) with each cycle, using data from thousands of previous cycles. These predictions can help doctors provide more personalized counseling, set realistic expectations, and adjust treatment plans accordingly.

A literature review on PubMed found 19 relevant studies on the subject. Notably, Banerjee et al.³ developed an AI tool to predict live birth (LB) in the second cycle (C2) based on data from the first cycle (C1). Their model, trained on 1,676 cycles, showed LB rates of 29% for C1, 18% for C2, and 14% for C3. Of those who did not achieve live birth in C1, 71% returned for C2, while 39% dropped out. External validation with an independent dataset (2007-2008) demonstrated that the AI model predicted LB 35.5% better than age-only models, providing valuable insights for patient counseling and treatment planning.

Letterie and MacDonald⁴ tested a decision-support system for four critical decisions in ovarian stimulation: continuing or stopping stimulation, triggering or canceling the cycle, adjusting medication, and determining follow-up intervals. Compared to experts' decisions, the system had an accuracy of 96% for triggering or canceling cycles, although medication adjustments showed lower accuracy (82%).

Reuvenny ⁵ et al. conducted a retrospective study with over 9,000 ICSI and freeze-all cycles to test AI's ability to predict optimal trigger timing. They found that AI-recommended timing resulted in an average increase of 4.8 oocytes and 3.4 mature oocytes (MII) in freeze-all cycles compared to physician-led decisions. The AI system often recommended later triggers than physicians, who tended to trigger earlier.

While AI offers numerous advantages—such as objectivity, precision, standardization, automation, and time optimization—there are several barriers to its widespread adoption:

1. Data Quality and Integration: AI models rely on vast amounts of high-quality data, but variability in clinic practices, protocols, and record-keeping can hinder data standardization and integration.

2. Validation and Diversity: AI systems need validation across diverse populations to ensure accuracy and applicability. Current datasets may need to represent the global IVF patient population adequately.

3. Physician Trust and Education: For AI to be fully embraced, fertility specialists need to trust AI's recommendations and understand how they are derived. Continuous education and training on AI technologies are essential for successful clinic adoption.

4. Ethical and Regulatory Concerns: Using AI in clinical decision-making raises ethical questions, particularly regarding accountability in cases where AI-led decisions result in adverse outcomes. Regulatory frameworks must also evolve to support the integration of AI into clinical practice.

Conclusion Integrating AI in ovarian stimulation can revolutionize IVF practice, particularly in clinics with limited staff or resources. By enhancing objectivity, standardization, precision, and efficiency, AI can optimize patient outcomes and reduce variability in treatment success. However, challenges related to data quality, diversity, regulation, and physician education must be addressed to unlock AI's full potential. With the proper support, AI can empower fertility doctors to make better, more informed decisions, ultimately improving patient experiences and success rates in assisted reproduction.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

卵巢刺激中的人工智能

卵巢刺激是辅助生殖技术（ART）的关键一步，涉及到许多关于药物方案、剂量和时间的决定，这些决定可以根据每个患者的独特情况量身定制。根据2020年ESHRE指南1，总共有84项建议，包括7项刺激前管理和40项垂体抑制。然而，由于患者反应的可变性，体外受精（IVF）诊所产生的大数据，以及决策的复杂性，很少有医生受过培训和经验，能够始终如一地做出最有效的选择。人工智能（AI）提供了一个很有前途的解决方案，使卵巢刺激的个性化和优化决策成为可能。通过分析以往试管婴儿周期的大型数据集，人工智能可以通过推荐个性化治疗计划、优化提取卵母细胞的数量和改善患者的治疗结果来支持生育医生。人工智能有可能增强卵巢刺激过程中的几个关键领域：1。促性腺激素剂量：人工智能模型可以根据患者的年龄、卵巢储备和激素水平等特征预测促性腺激素的最佳起始剂量。这可以减少过度或不足刺激的风险，降低卵巢过度刺激综合征（OHSS）或失败周期的机会。触发时间：AI可以分析卵泡生长和激素水平，推荐最佳时间进行触发注射，确保在最佳时间取出成熟卵母细胞。人工智能提供实时数据分析的能力支持在何时诱导排卵方面做出更精确的决定。成功的预测模型：人工智能工具可以使用以前数千个周期的数据来估计每个周期实现活产（LB）的概率。这些预测可以帮助医生提供更个性化的咨询，设定切合实际的期望，并相应地调整治疗计划。PubMed上的一篇文献综述发现了19项有关该主题的相关研究。值得注意的是，Banerjee等人3开发了一种人工智能工具，根据第一周期（C1）的数据预测第二周期（C2）的活产（LB）。他们的模型训练了1676个周期，显示C1的LB率为29%，C2为18%，C3为14%。在C1期没有活产的患者中，71%的人返回C2期，39%的人退出。使用独立数据集（2007-2008）进行的外部验证表明，AI模型对LB的预测比仅考虑年龄的模型高出35.5%，为患者咨询和治疗计划提供了有价值的见解。Letterie和MacDonald4测试了一个决策支持系统，用于卵巢刺激的四个关键决策：继续或停止刺激，触发或取消周期，调整药物，确定随访间隔。与专家的决定相比，该系统在触发或取消周期方面的准确性为96%，尽管药物调整的准确性较低（82%）。Reuvenny 5等人进行了一项回顾性研究，使用了9000多个ICSI和全冷冻周期来测试人工智能预测最佳触发时间的能力。他们发现，与医生主导的决定相比，人工智能推荐的时间导致冻结周期中平均增加4.8个卵母细胞和3.4个成熟卵母细胞（MII）。与医生相比，人工智能系统通常会推荐较晚的触发点，而医生往往会更早触发。虽然人工智能提供了许多优势——比如客观性、精确性、标准化、自动化和时间优化——但它的广泛采用存在一些障碍：数据质量和集成：人工智能模型依赖于大量高质量数据，但临床实践、协议和记录保存的可变性可能会阻碍数据标准化和集成。验证和多样性：人工智能系统需要在不同人群中进行验证，以确保准确性和适用性。目前的数据集可能需要充分代表全球试管婴儿患者群体。医生的信任和教育：为了充分接受人工智能，生育专家需要信任人工智能的建议，并了解它们是如何推导出来的。人工智能技术的持续教育和培训对于成功的临床应用至关重要。伦理和监管问题：在临床决策中使用人工智能会引发伦理问题，特别是在人工智能主导的决策导致不良后果的情况下的问责问题。监管框架也必须发展，以支持将人工智能整合到临床实践中。结论将人工智能技术应用于卵巢刺激，对人工授精治疗具有革命性意义，特别是在人员或资源有限的诊所。通过提高客观性、标准化、精确性和效率，人工智能可以优化患者的治疗结果，减少治疗成功的可变性。然而，必须解决与数据质量、多样性、监管和医生教育相关的挑战，以释放人工智能的全部潜力。在适当的支持下，人工智能可以使生育医生做出更好、更明智的决定，最终改善患者的体验和辅助生殖的成功率。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Reproductive biomedicine online 医学-妇产科学

CiteScore

7.20

自引率

7.50%

发文量

391

审稿时长

50 days

期刊介绍： Reproductive BioMedicine Online covers the formation, growth and differentiation of the human embryo. It is intended to bring to public attention new research on biological and clinical research on human reproduction and the human embryo including relevant studies on animals. It is published by a group of scientists and clinicians working in these fields of study. Its audience comprises researchers, clinicians, practitioners, academics and patients. Context: The period of human embryonic growth covered is between the formation of the primordial germ cells in the fetus until mid-pregnancy. High quality research on lower animals is included if it helps to clarify the human situation. Studies progressing to birth and later are published if they have a direct bearing on events in the earlier stages of pregnancy.