%0 Journal Article
%A Keyl, Julius
%A Keyl, Philipp
%A Montavon, Grégoire
%A Hosch, René
%A Brehmer, Alexander
%A Mochmann, Liliana
%A Jurmeister, Philipp
%A Dernbach, Gabriel
%A Kim, Moon
%A Koitka, Sven
%A Bauer, Sebastian
%A Bechrakis, Nikolaos
%A Forsting, Michael
%A Führer-Sakel, Dagmar
%A Glas, Martin
%A Grünwald, Viktor
%A Hadaschik, Boris
%A Haubold, Johannes
%A Herrmann, Ken
%A Kasper, Stefan
%A Kimmig, Rainer
%A Lang, Stephan
%A Rassaf, Tienush
%A Roesch, Alexander
%A Schadendorf, Dirk
%A Siveke, Jens
%A Stuschke, Martin
%A Sure, Ulrich
%A Totzeck, Matthias
%A Welt, Anja
%A Wiesweg, Marcel
%A Baba, Hideo A
%A Nensa, Felix
%A Egger, Jan
%A Müller, Klaus-Robert
%A Schuler, Martin
%A Klauschen, Frederick
%A Kleesiek, Jens
%T Decoding pan-cancer treatment outcomes using multimodal real-world data and explainable artificial intelligence.
%J Nature cancer
%V 6
%N 2
%@ 2662-1347
%C London
%I Nature Research
%M DKFZ-2025-00258
%P 307-322
%D 2025
%Z 2025 Feb;6(2):307-322
%X Despite advances in precision oncology, clinical decision-making still relies on limited variables and expert knowledge. To address this limitation, we combined multimodal real-world data and explainable artificial intelligence (xAI) to introduce AI-derived (AID) markers for clinical decision support. We used xAI to decode the outcome of 15,726 patients across 38 solid cancer entities based on 350 markers, including clinical records, image-derived body compositions, and mutational tumor profiles. xAI determined the prognostic contribution of each clinical marker at the patient level and identified 114 key markers that accounted for 90
%F PUB:(DE-HGF)16
%9 Journal Article
%$ pmid:39885364
%R 10.1038/s43018-024-00891-1
%U https://inrepo02.dkfz.de/record/298360