EUVIMEDEUVIMED entdecken
Crossref

L26/P-752 Combined clinical and laboratory workload balancing for both oocyte retrievals and fresh/frozen embryo transfers using artificial intelligence algorithms

E. Maman, R. Hourvitz, I. Nevo, S. Reuvenny, E. Moran, A. Luz, M.Y. Youngster, A. Hochberg, M. Baum, A. Hourvitz

Human Reproduction · 01.07.2026 · 41 (Supplement_1)

DOI: 10.1093/humrep/deag083.1079 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Human Reproduction, online erschienen am 08.07.2026. Verfasst von E. Maman und 9 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Study question Can a real-time balancing algorithm evenly distribute oocyte retrievals and fresh and frozen embryo transfers year-round, minimizing daily variability without compromising clinical outcomes? Summary answer A combined clinical–laboratory artificial intelligence (AI) workload-balancing algorithm can reduce daily variability in retrievals and transfers, narrowing workload range without compromising clinical outcomes. What is known already Increasing IVF cycle complexity and staffing demands underscore the need for workload-balancing algorithms to optimize daily scheduling of oocyte retrievals and fresh and frozen embryo transfers. Although a prior algorithm has been shown to successfully balance daily retrieval volumes, laboratory capacity remains a major bottleneck, necessitating additional balancing of embryo transfer workload. To date, no workload-balancing algorithm has integrated both oocyte retrievals and fresh and frozen embryo transfers into a unified, clinically effective scheduling framework, aimed to reduce burnout and ensure adequate laboratory staffing. Study design, size, duration A retrospective cohort study analyzing 6,808 retrieval cycles across all protocols, 3,611 fresh embryo transfers, 1,505 hormone replacement therapy (HRT) frozen embryo transfer (FET) cycles, and 3,368 natural FET cycles, conducted at a large IVF center (2024–2025). Real-time simulation, as described below, utilized only data available up to decision day. Participants/materials, setting, methods The workload-balancing-algorithm comprised five modules: (1) stimulation-initiation-adjustment using historical workload projections; (2) retrieval-estimation, assigning 14-day per-day probabilities; (3) AI-based trigger-day-algorithm, suggesting 1-3 optimal high-MII days; (4) transfer-day-estimation predicting 14-day probabilities for natural/HRT cycles; (5) HRT-FET transfer-date-algorithm allowing up to 3-day postponement within estrogen-only exposure limits (18-days). Laboratory workload was defined as one unit/per retrieval and 0.5/per transfer. Performance was assessed by comparing standard-deviations of daily retrievals, transfers, and workload units with and without algorithm implementation. Main results and the role of chance Implementation of the balancing algorithm in a clinic with an average of 19.36 retrievals, 23.70 transfers and 30.81 lab work units per day, reduced the standard deviation of daily retrievals (5.29 to 3.94), transfers (8.59 to 5.02), and lab work units (8.72 to 5.26). 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 This is the first workload-balancing algorithm integrating both oocyte retrievals and embryo transfers. Implementation of this combined algorithm may reduce clinical and laboratory workload, improve medical and laboratory staff efficiency, lower error rates and costs, and potentially enable clinics to increase their average treatment capacity. Trial registration number No

Zitieren

APA

Maman, E., Hourvitz, R., Nevo, I., Reuvenny, S., Moran, E., Luz, A., Youngster, M., Hochberg, A., Baum, M., & Hourvitz, A. (2026). L26/P-752 Combined clinical and laboratory workload balancing for both oocyte retrievals and fresh/frozen embryo transfers using artificial intelligence algorithms. Human Reproduction, 41(Supplement_1). https://doi.org/10.1093/humrep/deag083.1079

Vancouver

Maman E, Hourvitz R, Nevo I, Reuvenny S, Moran E, Luz A, et al. L26/P-752 Combined clinical and laboratory workload balancing for both oocyte retrievals and fresh/frozen embryo transfers using artificial intelligence algorithms. Human Reproduction. 2026;41(Supplement_1). doi:10.1093/humrep/deag083.1079

BibTeX
@article{Maman2026,
  author = {Maman, E. and Hourvitz, R. and Nevo, I. and Reuvenny, S. and Moran, E. and Luz, A. and Youngster, M.Y. and Hochberg, A. and Baum, M. and Hourvitz, A.},
  title = {L26/P-752 Combined clinical and laboratory workload balancing for both oocyte retrievals and fresh/frozen embryo transfers using artificial intelligence algorithms},
  journal = {Human Reproduction},
  year = {2026},
  volume = {41},
  number = {Supplement_1},
  doi = {10.1093/humrep/deag083.1079}
}
Kostenlos starten →