TY  - JOUR
AU  - Keyl, Julius
AU  - Keyl, Philipp
AU  - Montavon, Grégoire
AU  - Hosch, René
AU  - Brehmer, Alexander
AU  - Mochmann, Liliana
AU  - Jurmeister, Philipp
AU  - Dernbach, Gabriel
AU  - Kim, Moon
AU  - Koitka, Sven
AU  - Bauer, Sebastian
AU  - Bechrakis, Nikolaos
AU  - Forsting, Michael
AU  - Führer-Sakel, Dagmar
AU  - Glas, Martin
AU  - Grünwald, Viktor
AU  - Hadaschik, Boris
AU  - Haubold, Johannes
AU  - Herrmann, Ken
AU  - Kasper, Stefan
AU  - Kimmig, Rainer
AU  - Lang, Stephan
AU  - Rassaf, Tienush
AU  - Roesch, Alexander
AU  - Schadendorf, Dirk
AU  - Siveke, Jens
AU  - Stuschke, Martin
AU  - Sure, Ulrich
AU  - Totzeck, Matthias
AU  - Welt, Anja
AU  - Wiesweg, Marcel
AU  - Baba, Hideo A
AU  - Nensa, Felix
AU  - Egger, Jan
AU  - Müller, Klaus-Robert
AU  - Schuler, Martin
AU  - Klauschen, Frederick
AU  - Kleesiek, Jens
TI  - Decoding pan-cancer treatment outcomes using multimodal real-world data and explainable artificial intelligence.
JO  - Nature cancer
VL  - 6
IS  - 2
SN  - 2662-1347
CY  - London
PB  - Nature Research
M1  - DKFZ-2025-00258
SP  - 307-322
PY  - 2025
N1  - 2025 Feb;6(2):307-322
AB  - 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
LB  - PUB:(DE-HGF)16
C6  - pmid:39885364
DO  - DOI:10.1038/s43018-024-00891-1
UR  - https://inrepo02.dkfz.de/record/298360
ER  -