Stage-specific machine learning prediction of cumulative live birth in women with diminished ovarian reserve - Takeaways - MDSpire

Stage-specific machine learning prediction of cumulative live birth in women with diminished ovarian reserve

  • By

  • Lidan Liu

  • Bo Liu

  • Qianyi Huang

  • Lang Qin

  • Li Jiang

  • Huimei Wu

  • July 14, 2026

Share

  • 1

    Machine learning models were developed to predict cumulative live birth rates in women with diminished ovarian reserve during embryo transfer cycles.

  • 2

    The study included 1,234 cycles and utilized stage-specific models at baseline, post-stimulation, and pre-transfer decision points.

  • 3

    The CatBoost algorithm demonstrated the highest discrimination for cumulative live birth prediction across different stages.

  • 4

    Embryological parameters significantly improved prediction accuracy, while ovarian response markers provided minimal additional value.

  • 5

    Shapley Additive Explanations (SHAP) were used to enhance model interpretability, highlighting the importance of female age and embryo quality.

Original Source(s)

Stage-specific machine learning prediction of cumulative live birth in women with diminished ovarian reserve

  • by Lidan Liu, Bo Liu, Qianyi Huang, Lang Qin, Li Jiang, Huimei Wu

  • July 14, 2026

Related Content

Establishment of prognostic nomogram in cervical cancer with hepatitis B virus infection: a retrospective study

TGMS-UNet: A dual-branch segmentation network for ultrasound endometrium based on sequence guidance and multi-scale feature correction

Training-only ultrasound-specific augmentation for ovarian tumor segmentation across B-mode and contrast-enhanced ultrasound