Scholarlink

Background <p>Individualizing follicle-stimulating hormone (FSH) dosing during controlled ovarian stimulation (COS) is critical for optimizing outcomes in assisted reproduction but remains difficult due to patient heterogeneity. Most existing models are limited to static predictions of initial doses and do not support real-time adjustments throughout stimulation.</p> Methods <p>We developed a deep learning model that integrates cross-temporal and cross-feature encoding (CTFE) to predict personalized daily FSH doses in patients undergoing COS using the GnRH agonist long protocol. A total of 13,788 IVF/ICSI cycles conducted between January 2018 and December 2020 were retrospectively analyzed. Women with baseline antral follicle counts between 7 and 30 were included. Data were randomly divided into training (n = 6761), validation (n = 2898), and test (n = 4135) sets. The model encodes both static (e.g., age, BMI, basic&#xa0;hormone levels) and dynamic (e.g., follicle development, hormone trends during COS) variables across stimulation days. Final dose predictions were generated using a K-nearest neighbor algorithm applied to low-dimensional latent representations derived from the deep encoder layers.</p> Results <p>The CTFE model achieved a dose classification accuracy of 0.737 (± 0.004) and a weighted F1-score of 0.732 (± 0.005) on the test set. On key stimulation days 1 and 5, the CTFE model significantly outperformed traditional LASSO regression models (F1-score: 0.832 vs 0.699 on day 1; 0.817 vs 0.523 on day 5; p &lt; 0.001). Prediction performance was maintained beyond day 13 using a sliding window mechanism, despite reduced data availability in longer stimulation cycles.</p> Conclusions <p>This is the first study to apply a cross-temporal and cross-feature deep learning framework for daily, individualized FSH dose prediction across the full duration of COS. The model demonstrated superior performance over conventional approaches and offers a promising tool for standardizing COS management. Although currently limited by its retrospective, single-center design, the model may support future clinical decision-making and improve COS outcomes. Prospective, multicenter validation studies are warranted to confirm its utility and generalizability.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Deep learning-based prediction of individualized Real-time FSH doses in GnRH agonist long protocols

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年5月15日

查看全文
  • Na Kong,
  • Yu Xia,
  • Zhilong Wang,
  • Hui Zhang,
  • Liyan Duan,
  • Yingchun Zhu,
  • Chenyang Huang,
  • Guijun Yan,
  • Jie Mei,
  • Wujun Li,
  • Haixiang Sun

摘要

Background

Individualizing follicle-stimulating hormone (FSH) dosing during controlled ovarian stimulation (COS) is critical for optimizing outcomes in assisted reproduction but remains difficult due to patient heterogeneity. Most existing models are limited to static predictions of initial doses and do not support real-time adjustments throughout stimulation.

Methods

We developed a deep learning model that integrates cross-temporal and cross-feature encoding (CTFE) to predict personalized daily FSH doses in patients undergoing COS using the GnRH agonist long protocol. A total of 13,788 IVF/ICSI cycles conducted between January 2018 and December 2020 were retrospectively analyzed. Women with baseline antral follicle counts between 7 and 30 were included. Data were randomly divided into training (n = 6761), validation (n = 2898), and test (n = 4135) sets. The model encodes both static (e.g., age, BMI, basic hormone levels) and dynamic (e.g., follicle development, hormone trends during COS) variables across stimulation days. Final dose predictions were generated using a K-nearest neighbor algorithm applied to low-dimensional latent representations derived from the deep encoder layers.

Results

The CTFE model achieved a dose classification accuracy of 0.737 (± 0.004) and a weighted F1-score of 0.732 (± 0.005) on the test set. On key stimulation days 1 and 5, the CTFE model significantly outperformed traditional LASSO regression models (F1-score: 0.832 vs 0.699 on day 1; 0.817 vs 0.523 on day 5; p < 0.001). Prediction performance was maintained beyond day 13 using a sliding window mechanism, despite reduced data availability in longer stimulation cycles.

Conclusions

This is the first study to apply a cross-temporal and cross-feature deep learning framework for daily, individualized FSH dose prediction across the full duration of COS. The model demonstrated superior performance over conventional approaches and offers a promising tool for standardizing COS management. Although currently limited by its retrospective, single-center design, the model may support future clinical decision-making and improve COS outcomes. Prospective, multicenter validation studies are warranted to confirm its utility and generalizability.