Virtual Skin Organoids: Building Digital Twins for Skin Diseases
Abstract Skin organoids have emerged as invaluable models for studying skin diseases. However, their broader application is constrained by batch-to-batch variability, lengthy culture periods, and challenges in scaling production. The convergence of artificial intelligence and omics technologies has recently given rise to the concept of the artificial intelligence virtual cells, which are computational models designed to simulate the dynamic behavior of cells, both individually and in populations. Building on this concept, we propose the virtual skin organoid, a next-generation computational model that synthesizes a highly biomimetic representation of skin organoids. The virtual skin organoid leverages large-scale clinical data and fuses multimodal dynamic monitoring with artificial intelligence analytics. The primary objective in developing virtual skin organoids is to construct individualized skin digital twins. This involves enabling dynamic visualization, quantitative analysis, and predictable intervention of skin physiological and pathological processes in vitro. Therefore, beginning with a synthesis of recent progress in skin organoids, this review then examines advances in virtual cells and the role of artificial intelligence. It then introduces the concept of the virtual skin organoid, outlining construction strategies and potential applications, before concluding with a critical analysis of challenges and prospective solutions.
Authors
- Yan Wu
- Jiacan Su (ORCID: https://orcid.org/0000-0001-7080-263X)
- Yingying Jing
- Jianhua Wang
- Shihao Sheng
- Ruiyang Li
- Qirong Zhou
- Yuxiao Lai
Institutions
- Shanghai University (CN)
- Shanghai Jiao Tong University (CN)
- XinHua Hospital (CN)
- Shanghai Institutes for Biological Sciences (CN)
- Shanghai University of Medicine and Health Sciences (CN)
- Shenzhen Institutes of Advanced Technology (CN)
- University of Chinese Academy of Sciences (CN)
Publication Details
- Journal
- Burns & Trauma
- Published
- 2026-11-13
- DOI
- https://doi.org/10.1093/burnst/tkag083
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00