Enhancing the Accuracy of Human Phenotype Ontology Identification: Comparative Evaluation of Multimodal Large Language Models
The integration of MLLMs into clinical workflows significantly enhances the accuracy of HPO identification by junior physicians, offering promising potential to improve the diagnosis of rare diseases and standardize phenotype descriptions in medical research. However, the notable hallucination rate observed in MLLMs underscores the necessity for further refinement and rigorous validation before widespread adoption in clinical practice.
Authors
- Chenghong Yin (ORCID: https://orcid.org/0000-0002-2503-3285)
- Yousheng Yan (ORCID: https://orcid.org/0000-0002-0405-1302)
- Dingchuan Peng (ORCID: https://orcid.org/0009-0000-9588-6809)
- Yifan Liu (ORCID: https://orcid.org/0009-0005-7380-7993)
- Wei Zhong (ORCID: https://orcid.org/0000-0001-9823-9500)
- Kai Yang (ORCID: https://orcid.org/0000-0002-7457-3106)
- Yan Liu (ORCID: https://orcid.org/0000-0003-1698-5783)
- Haibin Yan (ORCID: https://orcid.org/0009-0008-2979-9895)
- Ming-yue Sun
- Hao Wan
- Shun Yao
- HuiMin Gao (ORCID: https://orcid.org/0009-0004-8874-6022)
Institutions
- Wannan Medical College (CN)
- First Hospital of Shijiazhuang (CN)
- Beijing Obstetrics and Gynecology Hospital (CN)
- South China University of Technology (CN)
Publication Details
- Journal
- Journal of Medical Internet Research
- Published
- 2025-06-02
- DOI
- https://doi.org/10.2196/73233
- Citations
- 2
- Primary Topic
- Biomedical Text Mining and Ontologies
- Type
- article
- Field-Weighted Citation Impact
- 1.61