Large language models with retrieval-augmented generation enhance expert modelling of Bayesian network for clinical decision support
Integrating LLM-RAG into BN modelling enhances efficiency and accuracy. Future work may focus on automated preprocessing, refinements of the user interface, and extending the RAG pipeline with validation steps and external biomedical sources. Generative AI holds promise for expert-driven knowledge modelling.
Authors
- Mario A. Cypko (ORCID: https://orcid.org/0000-0003-2944-9357)
- Matthaeus Stoehr (ORCID: https://orcid.org/0000-0003-4219-4459)
- L. Mark Berliner (ORCID: https://orcid.org/0000-0001-5590-4339)
- Muhammad Salim (ORCID: https://orcid.org/0000-0002-8983-4217)
- Oliver Amft (ORCID: https://orcid.org/0000-0001-6811-3659)
- Andreas Dietz (ORCID: https://orcid.org/0000-0001-8254-1676)
- Aditya Kumar
Institutions
- University of Freiburg (DE)
- Staten Island University Hospital (US)
- Hahn-Schickard-Gesellschaft für angewandte Forschung (DE)
- University Hospital Leipzig (DE)
Publication Details
- Journal
- International Journal of Computer Assisted Radiology and Surgery
- Published
- 2025-11-03
- DOI
- https://doi.org/10.1007/s11548-025-03524-9
- Citations
- 1
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 2.48
Funders
- Universität Leipzig