PuSH - Publikationsserver des Helmholtz Zentrums München

Mathes, S.* ; Ferber, D.* ; Dreyer, T.* ; Borm, K.J.* ; Modersohn, L.* ; Willem, T. ; Dirven, R.* ; Vibert, J.* ; Kreutzfeldt, S.* ; Perez-Lopez, R.* ; Prelaj, A.* ; Strand, F.* ; Baird, R.D.* ; Boeker, M.* ; Kather, J.N.* ; Tschochohei, M.* ; Lammert, J.*

Collaborative framework on responsible AI in LLM-driven CDSS for precision oncology leveraging real-world patient data.

npj Precis. Oncol., DOI: 10.1038/s41698-025-01180-5 (2025)
Postprint Forschungsdaten DOI PMC
Creative Commons Lizenzvertrag
Open Access Gold möglich sobald Verlagsversion bei der ZB eingereicht worden ist.
Precision oncology leverages real-world data, essential for identifying biomarkers and therapies. Large language models (LLMs) can aid at structuring unstructured data, overcoming current bottlenecks in precision oncology. We propose a framework for responsible LLM integration into precision oncology, co-developed by multidisciplinary experts and supported by Cancer Core Europe. Five thematic dimensions and ten principles for practice are outlined and illustrated through application to uterine carcinosarcoma in a thought experiment.
Altmetric
Weitere Metriken?
[➜Einloggen]
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Journalartikel
Dokumenttyp Wissenschaftlicher Artikel
ISSN (print) / ISBN 2397-768X
e-ISSN 2397-768X
Zeitschrift npj Precision Oncology
Verlag Springer
Begutachtungsstatus Peer reviewed
Institut(e) Helmholtz Artifical Intelligence Cooperation Unit (HAICU)