大连医科大学附属第一医院与牛津大学联合评估AI标准化患者(AI-SP)的临床培训效果
From simulation to pedagogy: multi-model and randomized evaluation of structured AI standardized patients
该研究通过三阶段评估AI标准化患者(AI-SP)的临床培训效果:Phase 1对350次模拟咨询的专家盲评显示,学习者表现差异主要源于架构设计(η²=0.31)而非模型选择(η²=0.06)。
- Article
- Open access
- Published: 23 October 2026
- Ping Wu1,
- Yu Han ORCID: orcid.org/0000-0002-0527-636X2,
- Jing Zhang ORCID: orcid.org/0000-0001-6660-25041,
- Yunqi Li1,
- Mengna Jiang1,
- Xinyu Lu1,
- Haibin Zhang1,3,
- Danyang Xu1,4,
- Hao Ming1,5,
- Lihong Wang1,6 &
- …
- Qingping Wen1
npj Digital Medicine (2026) Cite this article
We’re sharing this article early to provide faster access to peer-reviewed, accepted research. It is citable and carries a permanent DOI. This version is subject to further edits and will be replaced automatically by the final Version of Record. All legal disclaimers apply.
Abstract
Standardized patients (SPs) are central to clinical communication training but remain constrained by cost, scalability, and reliance on trained actors. We present AI standardized patients (AI-SPs), large language model–driven patient simulators built on a three-layer information architecture that adaptively modulates information disclosure according to learner skill. In Phase 1, blinded expert assessment of 350 simulated consultations generated by five frontier LLMs showed that, under a common architecture, learner skill level accounted for more of the observed performance variation than model choice (η2 = 0.31 vs. 0.06); whether this reflects the architecture itself cannot be determined without comparing models with and without it. In Phase 1b, analysis of 155 live student consultations identified systematic failures to elicit safety-critical information, enabling automated curriculum diagnostics without expert observation. In a Phase 2 three-arm pilot randomized study (n = 58), OSCE performance gains with AI-SP training did not differ significantly from those with human SP training; the trial was designed to estimate effect sizes for a future confirmatory study, not to demonstrate equivalence. Self-efficacy gains were numerically largest with AI-SP training, but this exploratory difference did not survive correction for multiple comparisons. These findings suggest that architecture-driven AI-SPs could provide a scalable, model-portable approach to clinical communication training.
Acknowledgements
The authors thank the expert evaluators for their contributions to the fidelity assessment, the graduate student standardised patient actors in Phase 2, and all 92 participating medical students from Dalian Medical University.
Funding
This work was supported by the Centre for School Development and Planning under the Ministry of Education (Grant No. CSDP26FC5A425) and by the General Project of the Undergraduate Teaching Reform Research Programme of Liaoning Provincial Institutions of Higher Education (Grant No. 2025YBXM0491). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
Author information
Authors and Affiliations
Department of Anesthesiology, The First Affiliated Hospital of Dalian Medical University, Dalian, 116000, China
Ping Wu, Jing Zhang, Yunqi Li, Mengna Jiang, Xinyu Lu, Haibin Zhang, Danyang Xu, Hao Ming, Lihong Wang & Qingping Wen
Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxfordshire, UK
Yu Han
Department of Anesthesiology, First Hospital of Shanxi Medical University, Taiyuan, 030001, China
Haibin Zhang
Department of Anesthesiology, Affiliated Hospital of Chifeng University, Chifeng, 024000, China
Danyang Xu
Department of Anesthesiology, Shandong Second Provincial General Hospital, Jinan, 250000, China
Hao Ming
Department of Anesthesiology, Chifeng Obstetrics and Gynecology Hospital, Chifeng, 024000, China
Lihong Wang
Authors
- Ping Wu
- Yu Han
- Jing Zhang
- Yunqi Li
- Mengna Jiang
- Xinyu Lu
- Haibin Zhang
- Danyang Xu
- Hao Ming
- Lihong Wang
- Qingping Wen
Corresponding author
Correspondence to Qingping Wen.
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Wu, P., Han, Y., Zhang, J. et al. From simulation to pedagogy: multi-model and randomized evaluation of structured AI standardized patients. npj Digit. Med. (2026). https://doi.org/10.1038/s41746-026-03372-0
Received: 28 March 2026
Accepted: 26 September 2026
Published: 23 October 2026
DOI: https://doi.org/10.1038/s41746-026-03372-0
来源:Nature 健康护理主题 · nature.com