Related Experiment Video
Updated: May 22, 2026
Fertility Preservation Through Oocyte Vitrification: Clinical and Laboratory Perspectives
Published on: September 16, 2021
Revisiting the Trigger-to-Oocyte Retrieval Interval: A Machine Learning-Guided Strategy for Improving Oocyte Yield in
Yoko Suzuki1,2, Ying Liu2, Michihiro Tanikawa1
1Department of Obstetrics and Gynecology, Graduate School of Medicine The University of Tokyo Tokyo Japan.
Purpose:
In IVF, the trigger-to-oocyte retrieval interval (TOI) is typically 34-36 h to avoid spontaneous ovulation. In women with diminished ovarian reserve (DOR) or advanced age, standard protocols often result in premature ovulation or empty follicles. Nonsteroidal anti-inflammatory drugs (NSAIDs) can extend the ovulatory window, enabling exploration of extending TOI. We aimed to evaluate the impact of TOI and to develop a machine learning model for individualized TOI optimization.
Methods:
Retrospective study on 15,033 IVF cycles to evaluate the effects of TOI extension (≥ 36 h) on the mature oocyte rate (MOR) and oocyte retrieval rate (ORR). Seven machine learning models were trained to predict matured oocytes counts (MII) and retrieved oocyte count (Oocount), then calculate for MOR and ORR as the primary endpoints, following external validation of 387 unseen cases.
Results:
TOI extension significantly improved MOR p = 0.00034 and ORR p = 0.0051 in POSEIDON groups 3 and 4. Extreme gradient boosting (XGBoost) model exhibited the best predictive accuracy. In external validation, R 2 decreased while MAE and RMSE remained.
Conclusions:
TOI extension enhances both MOR and ORR in DOR patients. Machine learning models reliably predict MII and Oocount, enabling the calculation of MOR and ORR across different TOIs and facilitating the optimal retrieval timing.
