Real-world implementation of AI-assisted starting gonadotropin dosing in routine ovarian stimulation: an exposure-defined, propensity score-matched observational cohort study
5 affiliations
- 1Center for Reproductive Medicine, Department of Obstetrics and Gynecology, Peking University Third Hospital
- 2Key Laboratory of Assisted Reproduction, Ministry of Education
- 3National Clinical Research Center for Obstetrics and Gynecology
- 4Beijing Key Laboratory of Reproductive Endocrinology and Assisted Reproductive Technology
- 5Big Data Center, Beijing Children’s Hospital, Capital Medical University, National Center for Children’s Health
Abstract
Introduction: Starting gonadotropin dose selection in controlled ovarian stimulation is conventionally guided by clinician experience. This pilot, single-centre, exposure-defined, matched observational cohort study assessed the feasibility of deploying an artificial intelligence-assisted gonadotropin dosing tool (POvaStim) in routine practice, comparing clinicians using the tool versus conventional experience-based judgement. Because AI use was completely confounded with clinician group and clinician experience was not prospectively quantified, the independent contribution of the decision-support tool cannot be isolated.
Methods: Consecutive women undergoing IVF/ICSI with a GnRH-antagonist protocol were treated between August 3 and December 31, 2022; only the starting dose was AI-assisted. One-to-one propensity score matching on body weight, ovarian reserve score and gonadotropin preparation yielded 119 matched pairs. Primary outcomes were cumulative clinical pregnancy and live birth per oocyte retrieval (data-lock 31 December 2024).
Results: Cumulative clinical pregnancy occurred in 67 of 119 (56.3%) in the AI-assisted arm versus 76 of 119 (63.9%) in the control arm (risk difference −7.6%, 95% CI −20.0 to +4.8; P = 0.234), and cumulative live birth in 59 of 119 (49.6%) versus 60 of 119 (50.4%) (risk difference −0.8%, 95% CI −13.5 to +11.9; P = 0.897), counting the 16 women without an ascertainable outcome by the data-lock date as non-events. A complete-case analysis excluding these 16 women gave materially unchanged results. These wide confidence intervals do not exclude clinically important differences; the study was not an equivalence or non-inferiority trial. Starting-dose selection was substantially less variable in the AI-assisted arm (interquartile range 43% narrower; variance 2.43-fold lower, 95% CI 1.69–3.50). Gonadotropin exposure was nonetheless higher in the AI-assisted arm (+27.4 IU/day). POvaStim recommended similar doses in both arms: the AI-assisted dose was rounded upward from it in 94.1% of cycles, while control-arm clinicians, unaware of the recommendation, more often prescribed below it. Elective freeze-all, chiefly for hyperstimulation prevention, was more frequent in the AI-assisted arm (46.2% versus 34.5%; risk difference +11.8%; P = 0.064), although none developed severe hyperstimulation requiring admission; the study was not powered for safety endpoints.
Discussion: AI-assisted starting-dose selection was feasible, with less variable dosing, but given the confound between AI assistance and clinician experience, these differences cannot be attributed to the tool itself.
Related
- Real-world implementation of video-assisted thoracic surgery for lung cancer: a decade-long regional propensity score-weighted cohort study.
- Estimating individualized gonadotropin starting doses in women with PCOS: a target-driven machine learning model for GnRH-antagonist stimulation
- Serum Beta-Human Chorionic Gonadotropin (β-hCG) Trends and Their Association With Abdominal Wound Healing After Cesarean Section: An Observational Study.
- Ultrasound-guided peripheral regional anesthesia vs local infiltration anesthesia for cardiac device implantation: A propensity score–matched prospective observational cohort study
- Localiser-Based Software-Assisted Patient Positioning in Chest CT: A Propensity Score-Matched Study
BibTeX
@article{xu2026realworld,
title = {{Real-world implementation of AI-assisted starting gonadotropin dosing in routine ovarian stimulation: an exposure-defined, propensity score-matched observational cohort study}},
author = {Huiyu Xu and Congcong Ma and Guoshuang Feng and Yaodong Zhang and Lina Wang and Hongbin Chi and Shuo Yang and Rui Yang and Rong Li and Jie Qiao},
journal = {Frontiers in Endocrinology},
year = {2026},
month = nov,
doi = {10.3389/fendo.2026.1944764},
url = {https://www.frontiersin.org/articles/10.3389/fendo.2026.1944764/full},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Real-world implementation of AI-assisted starting gonadotropin dosing in routine ovarian stimulation: an exposure-defined, propensity score-matched observational cohort study
AU - Huiyu Xu
AU - Congcong Ma
AU - Guoshuang Feng
AU - Yaodong Zhang
AU - Lina Wang
AU - Hongbin Chi
AU - Shuo Yang
AU - Rui Yang
AU - Rong Li
AU - Jie Qiao
PY - 2026
DA - 2026/11/05
JO - Frontiers in Endocrinology
DO - 10.3389/fendo.2026.1944764
UR - https://www.frontiersin.org/articles/10.3389/fendo.2026.1944764/full
AB - Introduction: Starting gonadotropin dose selection in controlled ovarian stimulation is conventionally guided by clinician experience. This pilot, single-centre, exposure-defined, matched observational cohort study assessed the feasibility of deploying an artificial intelligence-assisted gonadotropin dosing tool (POvaStim) in routine practice, comparing clinicians using the tool versus conventional experience-based judgement. Because AI use was completely confounded with clinician group and clinician experience was not prospectively quantified, the independent contribution of the decision-support tool cannot be isolated. Methods: Consecutive women undergoing IVF/ICSI with a GnRH-antagonist protocol were treated between August 3 and December 31, 2022; only the starting dose was AI-assisted. One-to-one propensity score matching on body weight, ovarian reserve score and gonadotropin preparation yielded 119 matched pairs. Primary outcomes were cumulative clinical pregnancy and live birth per oocyte retrieval (data-lock 31 December 2024). Results: Cumulative clinical pregnancy occurred in 67 of 119 (56.3%) in the AI-assisted arm versus 76 of 119 (63.9%) in the control arm (risk difference −7.6%, 95% CI −20.0 to +4.8; P = 0.234), and cumulative live birth in 59 of 119 (49.6%) versus 60 of 119 (50.4%) (risk difference −0.8%, 95% CI −13.5 to +11.9; P = 0.897), counting the 16 women without an ascertainable outcome by the data-lock date as non-events. A complete-case analysis excluding these 16 women gave materially unchanged results. These wide confidence intervals do not exclude clinically important differences; the study was not an equivalence or non-inferiority trial. Starting-dose selection was substantially less variable in the AI-assisted arm (interquartile range 43% narrower; variance 2.43-fold lower, 95% CI 1.69–3.50). Gonadotropin exposure was nonetheless higher in the AI-assisted arm (+27.4 IU/day). POvaStim recommended similar doses in both arms: the AI-assisted dose was rounded upward from it in 94.1% of cycles, while control-arm clinicians, unaware of the recommendation, more often prescribed below it. Elective freeze-all, chiefly for hyperstimulation prevention, was more frequent in the AI-assisted arm (46.2% versus 34.5%; risk difference +11.8%; P = 0.064), although none developed severe hyperstimulation requiring admission; the study was not powered for safety endpoints. Discussion: AI-assisted starting-dose selection was feasible, with less variable dosing, but given the confound between AI assistance and clinician experience, these differences cannot be attributed to the tool itself.
SN - 1664-2392
ER -