From "standardized patients" to "digital twin patients": Disciplinary logic and technical divergence of five patient modeling paradigms
- VernacularTitle:从“标准化患者”到“数字孪生患者”：五类患者建模范式的学科逻辑和技术分野
- Author:
Xingyuan ZHU
1
;
Jiaqing WANG
2
,
3
;
Zhongfang YANG
4
;
Zong'an HUANG
5
;
Zheng ZHU
2
,
6
Author Information
1. School of Nursing, Dali University, Dali, 671000, Yunnan, P. R. China
2. Yulin AI-Enhanced Healthcare Lab, Shanghai, 200032, P. R. China
3. Shanghai Lianhong Technology Co., Ltd. Shanghai, 200032, P. R. China
4. School of Nursing, Medical College of Soochow University, Suzhou, 215006, Jiangsu, P. R. China
5. School of Computer Science and Technology, Fudan University, Shanghai, 200433, P. R. China
6. School of Nursing, Fudan University, Shanghai, 200032, P. R. China
- Publication Type:Journal Article
- Keywords:
Large language models;
patient modeling;
medical simulation;
AI patients;
digital twin patients
- From:
Chinese Journal of Clinical Thoracic and Cardiovascular Surgery
2026;33(07):1023-1033
- CountryChina
- Language:Chinese
-
Abstract:
With the rapid development of large language models and related technologies, various forms of patient modeling have emerged, including virtual patients, synthetic patients, artificial intelligence patients, and digital twin patients. Although these forms all share the core objective of patient simulation, they exhibit significant differences in theoretical ontology, data sources, modeling logic, and application orientation. Based on the abstraction levels of simulation objects and system mapping logic, this study systematically compares five paradigms—standardized patients, virtual patients, synthetic patients, AI patients, and digital twin patients—to clarify their conceptual boundaries and technical positioning. The findings indicate that these paradigms represent distinct modeling pathways: behavioral reproduction, scenario simulation, data generation, cognitive interaction, and individual system mapping, respectively. By constructing a multidimensional comparative framework, this study provides a theoretical foundation for the conceptual standardization of patient modeling and the strategic deployment of intelligent healthcare systems.
