Semi-Supervised Fatty Liver Classification Using Attention-Based Graph Neural Network Models
Attention-based GNNs demonstrated strong predictive performance for fatty liver disease using a small number of labeled samples. This methodological approach illustrates how graph-based learning can leverage relational structures in routine clinical data to support data-efficient, individualized risk assessment in label-constrained settings.
Authors
- Eun Kyung Choe (ORCID: https://orcid.org/0000-0002-7222-1772)
- Sehee Wang (ORCID: https://orcid.org/0000-0001-9192-2411)
- Kyung-Ah Sohn (ORCID: https://orcid.org/0000-0001-8941-1188)
- So Yeon Kim (ORCID: https://orcid.org/0000-0001-5645-2012)
Institutions
- Seoul National University (KR)
- Seoul National University Hospital (KR)
- Ajou University (KR)
Publication Details
- Journal
- Journal of Korean Medical Science
- Published
- 2025-12-19
- DOI
- https://doi.org/10.3346/jkms.2026.41.e30
- Primary Topic
- Artificial Intelligence in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Research Foundation
- Seoul National University
- National Research Foundation of Korea
- Seoul National University Hospital
- Ministry of Science and ICT, South Korea