TY  - JOUR
AU  - Ferber, Dyke
AU  - El Nahhas, Omar S M
AU  - Wölflein, Georg
AU  - Wiest, Isabella C
AU  - Clusmann, Jan
AU  - Leßmann, Marie-Elisabeth
AU  - Foersch, Sebastian
AU  - Lammert, Jacqueline
AU  - Tschochohei, Maximilian
AU  - Jäger, Dirk
AU  - Salto-Tellez, Manuel
AU  - Schultz, Nikolaus
AU  - Truhn, Daniel
AU  - Kather, Jakob Nikolas
TI  - Development and validation of an autonomous artificial intelligence agent for clinical decision-making in oncology.
JO  - Nature cancer
VL  - 6
IS  - 8
SN  - 2662-1347
CY  - London
PB  - Nature Research
M1  - DKFZ-2025-01180
SP  - 1337-1349
PY  - 2025
N1  - 2025 Aug;6(8):1337-1349
AB  - Clinical decision-making in oncology is complex, requiring the integration of multimodal data and multidomain expertise. We developed and evaluated an autonomous clinical artificial intelligence (AI) agent leveraging GPT-4 with multimodal precision oncology tools to support personalized clinical decision-making. The system incorporates vision transformers for detecting microsatellite instability and KRAS and BRAF mutations from histopathology slides, MedSAM for radiological image segmentation and web-based search tools such as OncoKB, PubMed and Google. Evaluated on 20 realistic multimodal patient cases, the AI agent autonomously used appropriate tools with 87.5
LB  - PUB:(DE-HGF)16
C6  - pmid:40481323
DO  - DOI:10.1038/s43018-025-00991-6
UR  - https://inrepo02.dkfz.de/record/301910
ER  -