L26/P-785 Retrieval workload balancing utilizing stimulation-initiation timing and trigger-timing algorithms
Human Reproduction · 01.07.2026 · 41 (Supplement_1)
DOI: 10.1093/humrep/deag083.1112 ↗Kurz gefasst
Fachartikel in der Zeitschrift Human Reproduction, online erschienen am 08.07.2026. Verfasst von A. Hochberg und 9 weiteren Autor:innen.
Abstract (Originalsprache)
Study question Can a real-time balancing algorithm integrating trigger-day suggestion, retrieval-day estimation, and stimulation-initiation timing algorithms evenly distribute oocyte retrievals throughout the year without compromising clinical outcomes? Summary answer A balancing algorithm integrating artificial intelligence (AI)-based models reduces daily retrieval variability while maintaining optimal clinic capacity and without compromising oocyte yield. What is known already Increasing in-vitro fertilization (IVF) cycle complexity and staffing demands highlight the need for workload balancing algorithms to optimize daily oocyte retrieval scheduling in fertility clinics. Effective scheduling is essential to ensure sufficient staffing, reduce burnout, and maintain patient safety. AI-based platforms and predictive models have shown promise in predicting oocyte retrieval timing resulting in optimal mature oocyte yield; however, none have yet demonstrated effective application for workload balancing while integrating trigger-day suggestion, retrieval-day estimation, and stimulation-initiation timing, while preserving optimal clinical outcomes. Study design, size, duration A retrospective cohort study including 6808 retrieval cycles of varied protocol types with documented retrieval dates, performed at a large center serving over 50 physicians, between February 2024 - February 2025. Participants/materials, setting, methods The balancing algorithm comprised three components: (1) an AI-based trigger-suggestion algorithm proposing 1-3 trigger days with higher predicted MII-oocyte yield; (2) An AI retrieval-estimation-algorithm assigning per-day retrieval probabilities over 14 days; (3) A stimulation-initiation balancing algorithm delaying cycle start based on projected workload using historical data. Real-time simulation used only cycle-data available up to decision day. Performance was assessed by comparing the standard deviation of daily retrievals over one year with and without algorithm implementation. Main results and the role of chance Analysis of suggested trigger dates showed that 57.7%, 30.9%, and 11.4% of cycles had one, two, and three trigger options, respectively, providing scheduling flexibility in 42.3% of cycles. The mean number of oocyte retrievals per day at the clinic was 19.4. Implementation of the balancing algorithm reduced the standard deviation (SD) of daily retrievals from 5.3 to 3.8, improving workload distribution. Consequently, the 95% daily retrieval range narrowed from 8. 8–30.0 to 11.7–27.1. Limitations, reasons for caution Our study’s retrospective design may introduce bias from unmeasured confounders, and its single-center setting may limit generalizability. Wider implications of the findings A real-time balancing algorithm can reduce the SD and range of daily retrievals, improving workload distribution. This may enhance medical and laboratory efficiency, reduce errors and costs, and increase clinic capacity without additional resources, thereby shortening waitlists and improving patient care. Trial registration number No
Zitieren
APA
Hochberg, A., Reuvenny, S., Moran, E., Itzhak, N., Luz, A., Hourvitz, R., Youngster, M., Maman, E., Baum, M., & Hourvitz, A. (2026). L26/P-785 Retrieval workload balancing utilizing stimulation-initiation timing and trigger-timing algorithms. Human Reproduction, 41(Supplement_1). https://doi.org/10.1093/humrep/deag083.1112
Vancouver
Hochberg A, Reuvenny S, Moran E, Itzhak N, Luz A, Hourvitz R, et al. L26/P-785 Retrieval workload balancing utilizing stimulation-initiation timing and trigger-timing algorithms. Human Reproduction. 2026;41(Supplement_1). doi:10.1093/humrep/deag083.1112
BibTeX
@article{Hochberg2026,
author = {Hochberg, A. and Reuvenny, S. and Moran, E. and Itzhak, N. and Luz, A. and Hourvitz, R. and Youngster, M. and Maman, E. and Baum, M. and Hourvitz, A.},
title = {L26/P-785 Retrieval workload balancing utilizing stimulation-initiation timing and trigger-timing algorithms},
journal = {Human Reproduction},
year = {2026},
volume = {41},
number = {Supplement_1},
doi = {10.1093/humrep/deag083.1112}
}
EUVIMED