基于机器学习的卵巢刺激中首次 FSH 剂量的支持。

Supporting first FSH dosage for ovarian stimulation with machine learning.

机构信息

Clínica Eugin-Eugin Group, Carrer de Balmes 236, Barcelona 08006, Spain; Instituto de Investigación en Inteligencia Artificial, Consejo Superior de Investigaciones Científicas (IIIA-CSIC), Campus de la UAB, Carrer de Can Planas, Zona 2, Cerdanyola de Valles Barcelona 08193, Spain; Universitat Autònoma de Barcelona (UAB), Plaça Cívica, Bellaterra Barcelona 08193, Spain.

Instituto de Investigación en Inteligencia Artificial, Consejo Superior de Investigaciones Científicas (IIIA-CSIC), Campus de la UAB, Carrer de Can Planas, Zona 2, Cerdanyola de Valles Barcelona 08193, Spain.

出版信息

Reprod Biomed Online. 2022 Nov;45(5):1039-1045. doi: 10.1016/j.rbmo.2022.06.010. Epub 2022 Jun 18.

DOI:10.1016/j.rbmo.2022.06.010

PMID:35915001

Abstract

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/m, 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.

摘要

研究问题

是否可以通过机器学习模型准确确定卵巢刺激的最佳起始剂量 FSH？

设计

观察性研究（2011-2021 年），包括使用自身卵子的首次 IVF 周期。来自五个私人生殖中心的 2713 名患者被纳入发展阶段（2011-2019 年），774 名患者纳入验证阶段（2020-2021 年）。预测变量包括年龄、BMI、AMH、AFC 和既往活产。性能通过基于获得的 MII 卵母细胞数量和剂量的推荐值进行测量，包括推荐剂量和实际剂量。

结果

纳入的周期来自年龄为 37.7 ± 4.4 岁（18-45 岁）的女性，BMI 为 23.5 ± 4.2kg/m，AMH 为 2.4 ± 2.3ng/ml，AFC 为 11.3 ± 7.6，平均获得的 MII 卵母细胞数为 6.9 ± 5.4。该模型在发展阶段的平均性能评分为 0.87（95%CI 0.86-0.88），明显优于同一患者的临床医生规定的剂量（0.83，95%CI 0.82-0.84；P=2.44e-10）。模型推荐剂量的平均性能评分为 0.89（95%CI 0.88-0.90），在验证阶段也明显优于临床医生（0.84，95%CI 0.82-0.86；P=3.81e-05）。该模型被证明优于标准实践。