机器学习辅助确定卵巢刺激中FSH起始剂量
本研究为观察性研究,纳入五个私立生殖中心的首次IVF周期,开发阶段2713例(2011-2019),验证阶段774例(2020-2021)。机器学习模型在开发阶段平均性能评分为0.87(95%CI 0.86-0.88),显著优于临床医生处方(0.83,95%CI 0.82-0.84;P=2.44e-10);验证阶段模型评分为0.89(95%CI 0.88-0.90),亦显著优于临床医生(0.84,95%CI 0.82-0.86;P=3.81e-05)。模型表现超越标准实践。
要点
- 模型在开发阶段平均性能评分0.87,显著优于临床医生处方的0.83(P=2.44e-10)。
- 验证阶段模型评分0.89,显著优于临床医生的0.84(P=3.81e-05)。
- 该模型可作为新临床医生的培训工具及有经验临床医生的质量控制工具。
核心结论
- 该机器学习模型在推荐FSH起始剂量方面的表现超越标准实践,可作为培训和学习工具以及质量控制工具。
研究设计与样本
- 观察性研究,纳入2011年至2021年首次使用自身卵子的IVF周期,开发阶段2713例(2011-2019),验证阶段774例(2020-2021),来自五个私立生殖中心。
- 预测变量包括年龄、BMI、AMH、AFC和既往活产数。
主要发现
- 纳入周期女性年龄37.7±4.4岁(18-45岁),BMI 23.5±4.2 kg/m2,AMH 2.4±2.3 ng/ml,AFC 11.3±7.6,平均获MII卵数6.9±5.4。
- 开发阶段模型平均性能评分0.87(95%CI 0.86-0.88),显著优于临床医生为同一批患者处方的评分0.83(95%CI 0.82-0.84;P=2.44e-10)。
- 验证阶段模型推荐的平均性能评分0.89(95%CI 0.88-0.90),显著优于临床医生的0.84(95%CI 0.82-0.86;P=3.81e-05)。
关键数值与推荐
- 性能评分基于获MII卵数及所接受剂量、推荐剂量或两者计算。
临床怎么用
- 作者认为该机器学习模型可作为新临床医生的培训和学习工具,以及有经验临床医生的质量控制工具。
局限性
- 原文未报告局限性
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
RESEARCH QUESTION: Is it possible to identify accurately the optimal first dose of FSH in ovarian stimulation by means of a machine learning model? DESIGN: Observational study (2011-2021) including first IVF cycles with own oocytes. A total of 2713 patients from five private reproductive centres were included in the development phase (2011-2019) and 774 in the validation phase (2020-2021). Predictor variables included age, BMI, AMH, AFC and previous live births. Performance was measured with a proposed score based on the number of MII oocytes retrieved and dose received, recommended, or both. RESULTS: The included cycles were from women aged 37.7 ± 4.4 years (18-45 years), with a BMI of 23.5 ± 4.2 kg/m2, AMH of 2.4 ± 2.3 ng/ml, AFC of 11.3 ± 7.6, and an average number of MII obtained 6.9 ± 5.4. The model reached a mean performance score of 0.87 (95% CI 0.86 to 0.88) in the development phase, significantly better than for doses prescribed by clinicians for the same patients (0.83, 95% CI 0.82 to 0.84; P = 2.44 e-10). Mean performance score of the model recommendations was 0.89 (95% CI 0.88 to 0.90) in the validation phase, also significantly better than clinicians (0.84, 95% CI 0.82 to 0.86; P = 3.81 e-05). The model was shown to surpass the performance of standard practice. CONCLUSION: This machine learning model could be used as a training and learning tool for new clinicians, and as quality control for experienced clinicians.
引用
- Correa N, Cerquides J, Arcos JL, et al. Supporting first FSH dosage for ovarian stimulation with machine learning. Reprod Biomed Online. 2022. PMID: 35915001. doi:10.1016/j.rbmo.2022.06.010
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。