LLM-guided multimodal attention network for robust multiclass Parkinson’s disease diagnosis
LLM-guided multimodal fusion via MGCA provides reliable and interpretable approach for PD staging, substantially improving prodromal PD identification by integrating semantic clinical knowledge with neuroimaging representations.
Authors
- Y B Ye
- Taisheng Zeng (ORCID: https://orcid.org/0000-0001-7806-0351)
- Kavimbi Chipusu
- Bijiao Ding
- Muhammad Ibrahim Umar (ORCID: https://orcid.org/0009-0009-1060-9104)
- Yifeng Huang
- Jianlong Huang
Institutions
- Huaqiao University (CN)
- Fujian Medical University (CN)
- Quanzhou Normal University (CN)
- Huazhong University of Science and Technology (CN)
Publication Details
- Journal
- Biomedizinische Technik/Biomedical Engineering
- Published
- 2026-03-02
- DOI
- https://doi.org/10.1515/bmt-2026-0004
- Primary Topic
- Parkinson's Disease Mechanisms and Treatments
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Huaqiao University