An Approach to Predict Intraocular Diseases by Machine Learning Based on Vitreous Humor Immune Mediator Profile
The random forest algorithm effectively classified 28 immune mediators in the vitreous to accurately predict the diagnosis of vitreoretinal lymphoma, endophthalmitis, and uveal melanoma among 12 representative intraocular diseases. In summary, the results of this study enhance our understanding of potential new biomarkers that may contribute to elucidating the pathophysiology of intraocular diseases in the future.
Authors
- Naoya Nezu
- Masahiko Kuroda (ORCID: https://orcid.org/0000-0001-7052-4289)
- Naoyuki Yamakawa (ORCID: https://orcid.org/0000-0002-4306-1538)
- Hiroshi Gotô (ORCID: https://orcid.org/0000-0002-6462-9524)
- Masaki Asakage
- Akira Saito (ORCID: https://orcid.org/0000-0002-0184-1376)
- Risa Sugawara
- Masahiro Sugimoto (ORCID: https://orcid.org/0000-0003-3316-2543)
- Yoshihiro Wakabayashi (ORCID: https://orcid.org/0000-0002-6241-2487)
- Hiroyuki Komatsu (ORCID: https://orcid.org/0000-0002-8192-3143)
- Yoshihiko Usui (ORCID: https://orcid.org/0000-0002-1258-3587)
- Kinya Tsubota
Institutions
- Tokyo Medical University (JP)
- Tokyo Medical University Hospital (JP)
Publication Details
- Journal
- Investigative Ophthalmology & Visual Science
- Published
- 2025-03-19
- DOI
- https://doi.org/10.1167/iovs.66.3.38
- Citations
- 4
- Primary Topic
- Ocular Diseases and Behçet’s Syndrome
- Type
- article
- Field-Weighted Citation Impact
- 6.83
Funders
- Ministry of Education, Culture, Sports, Science and Technology
- Japan Society for the Promotion of Science