Large Language Models in Neurological Practice: Real-World Study
While LLMs show potential as supportive tools in neurology, they currently lack the depth required for independent clinical decision-making when using freely available LLMs without previous specific training. The moderate agreement observed among human raters underscores the variability even in expert judgment and highlights the importance of rigorous validation when integrating artificial intelligence tools into clinical workflows. Future research should focus on refining LLM capabilities and developing evaluation methodologies that reflect the complexities of real-world neurological practice, ensuring effective, responsible, and safe use of such promising technologies.
Authors
- Natale Vincenzo Maiorana (ORCID: https://orcid.org/0000-0002-6547-6304)
- Sara Renata Francesca Marceglia (ORCID: https://orcid.org/0000-0002-0456-866X)
- Tommaso Bocci (ORCID: https://orcid.org/0000-0001-8874-1070)
- Alberto Priori (ORCID: https://orcid.org/0000-0002-1549-3851)
- Matteo Guidetti (ORCID: https://orcid.org/0000-0002-4562-009X)
- Serena Oliveri (ORCID: https://orcid.org/0000-0002-7185-4260)
- Filippo Martinelli Boneschi (ORCID: https://orcid.org/0000-0002-9955-1368)
- Mauro Treddenti
- Mattia Tosi
- Maria Francesca Creta
Institutions
- AOL (United States) (US)
- University of Milan (IT)
- Azienda Socio Sanitaria Territoriale Lariana (IT)
Publication Details
- Journal
- Journal of Medical Internet Research
- Published
- 2025-06-17
- DOI
- https://doi.org/10.2196/73212
- Citations
- 5
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 3.27