%0 Journal Article
%A Ferber, Dyke
%A El Nahhas, Omar S M
%A Wölflein, Georg
%A Wiest, Isabella C
%A Clusmann, Jan
%A Leßmann, Marie-Elisabeth
%A Foersch, Sebastian
%A Lammert, Jacqueline
%A Tschochohei, Maximilian
%A Jäger, Dirk
%A Salto-Tellez, Manuel
%A Schultz, Nikolaus
%A Truhn, Daniel
%A Kather, Jakob Nikolas
%T Development and validation of an autonomous artificial intelligence agent for clinical decision-making in oncology.
%J Nature cancer
%V 6
%N 8
%@ 2662-1347
%C London
%I Nature Research
%M DKFZ-2025-01180
%P 1337-1349
%D 2025
%Z 2025 Aug;6(8):1337-1349
%X 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
%F PUB:(DE-HGF)16
%9 Journal Article
%$ pmid:40481323
%R 10.1038/s43018-025-00991-6
%U https://inrepo02.dkfz.de/record/301910