Detecting New Lesions Using a Large Language Model: Applications in Real‐World Multiple Sclerosis Datasets
Extracting discrete information from narrative imaging reports using an large language model is feasible and efficient. This approach could augment many real-world analyses of MS disease evolution and treatment response. ANN NEUROL 2025;98:308-316.
Authors
- Kanishka Koshal (ORCID: https://orcid.org/0000-0002-0612-0738)
- Amit Akula (ORCID: https://orcid.org/0000-0003-2867-7569)
- Danelvis Paredes (ORCID: https://orcid.org/0000-0002-3525-7696)
- Andreas M. Rauschecker (ORCID: https://orcid.org/0000-0003-0633-9876)
- Jaeleene Wijangco (ORCID: https://orcid.org/0009-0006-1561-6547)
- William Rowles (ORCID: https://orcid.org/0000-0002-5613-0483)
- Jens Wuerfel (ORCID: https://orcid.org/0000-0002-0034-8053)
- Vishakha Sharma (ORCID: https://orcid.org/0000-0002-9677-2325)
- Shane T. Poole (ORCID: https://orcid.org/0000-0002-3203-151X)
- Riley M. Bove (ORCID: https://orcid.org/0000-0002-2034-8800)
- Roland G. Henry (ORCID: https://orcid.org/0000-0002-8232-7562)
- Nikki Sisodia (ORCID: https://orcid.org/0009-0006-7270-595X)
- Chelsea Chen (ORCID: https://orcid.org/0000-0001-7776-4509)
- Kyra Henderson
Institutions
- Roche (Switzerland) (CH)
- Roche (United States) (US)
- University of California, San Francisco (US)
Publication Details
- Journal
- Annals of Neurology
- Published
- 2025-04-25
- DOI
- https://doi.org/10.1002/ana.27251
- Citations
- 4
- Primary Topic
- Multiple Sclerosis Research Studies
- Type
- article
- Field-Weighted Citation Impact
- 5.89
Funders
- F. Hoffmann-La Roche