AI-driven synthetic data generation for accelerating hepatology research: A study of the United Network for Organ Sharing (UNOS) database
Artificial intelligence-generated synthetic data derived from diffusion models can faithfully replicate complex hepatology datasets, maintain key clinical signals, and ensure strong privacy safeguards. This approach can help address data scarcity, enhance model generalizability, foster multi-institutional collaboration, and accelerate progress in hepatology research.
Authors
- Patrick S. Kamath (ORCID: https://orcid.org/0000-0002-7888-1165)
- Xiaotong Shen (ORCID: https://orcid.org/0009-0000-1297-6949)
- Yung‐Kyun Noh (ORCID: https://orcid.org/0000-0002-6372-9267)
- Rohit S. Loomba (ORCID: https://orcid.org/0000-0002-9116-2835)
- Vijay H. Shah (ORCID: https://orcid.org/0000-0001-7620-573X)
- Douglas A. Simonetto (ORCID: https://orcid.org/0000-0003-4095-8144)
- Joseph Ahn (ORCID: https://orcid.org/0000-0001-6994-2870)
- Mingzhao Hu (ORCID: https://orcid.org/0000-0002-0375-0355)
Institutions
- University of Minnesota (US)
- Mayo Clinic (US)
- University of Minnesota System (US)
- WinnMed (US)
- University of California San Diego (US)
- Mayo Clinic in Arizona (US)
- Mayo Clinic in Florida (US)
- Hanyang University (KR)
Publication Details
- Journal
- Hepatology
- Published
- 2025-03-11
- DOI
- https://doi.org/10.1097/hep.0000000000001299
- Citations
- 6
- Primary Topic
- MRI in cancer diagnosis
- Type
- article
- Field-Weighted Citation Impact
- 8.16