Neuro-symbolic AI for auditable cognitive information extraction from medical reports
Unlike standalone LLMs, neuro-symbolic AI can safely automate data extraction for clinical research and may provide a path toward trustworthy AI in healthcare practice.
Authors
- George Prenosil (ORCID: https://orcid.org/0000-0001-6673-5374)
- Shaibu Oricha Bello (ORCID: https://orcid.org/0000-0001-5380-5759)
- Giulia Manzini (ORCID: https://orcid.org/0000-0002-8032-8043)
- Clemens Mingels (ORCID: https://orcid.org/0000-0001-6761-5323)
- Thilo Weitzel
- Ali Afshar‐Oromieh (ORCID: https://orcid.org/0000-0002-4492-4243)
- Axel Rominger (ORCID: https://orcid.org/0000-0002-1954-736X)
- Lorenz Meier (ORCID: https://orcid.org/0000-0001-6247-0102)
- Kuangyu Shi (ORCID: https://orcid.org/0000-0002-8714-3084)
Institutions
- University of Bern (CH)
- University Hospital of Bern (CH)
- Martel (CH)
- Spital Muri (CH)
- Scientific Computing Associates (United States) (US)
Publication Details
- Journal
- Communications Medicine
- Published
- 2025-11-21
- DOI
- https://doi.org/10.1038/s43856-025-01194-x
- Citations
- 4
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 9.92
Funders
- Inselspital, Universitätsspital Bern