TY  - JOUR
AU  - Schneider, François
AU  - Chen, Haotian
AU  - Pelzer, Uwe
AU  - Compton, Richard G
AU  - Duwe, Gregor
AU  - Dragomir, Mihnea P
AU  - Hilfenhaus, Georg
AU  - Vecchione, Loredana
AU  - Alig, Annabel
AU  - Felsenstein, Matthäus
AU  - Lerchbaumer, Markus
AU  - Rieke, Damian T
AU  - Bahra, Marcus
AU  - Kutsche, Ralf
AU  - Tschulik, Kristina
AU  - Stintzing, Sebastian
AU  - Keilholz, Ulrich
AU  - Neumann, Christopher C M
TI  - The basis for future personalized therapy approaches - Machine learning-generated 1-year survival rate, metastatic status and therapy-dependent survival in pancreatic cancer patients.
JO  - European journal of cancer
VL  - 234
SN  - 0959-8049
CY  - Amsterdam [u.a.]
PB  - Elsevier
M1  - DKFZ-2026-00008
SP  - 116189
PY  - 2026
AB  - Pancreatic adenocarcinoma (PDAC) remains one of the most lethal types of cancer, characterized by its unspecific symptoms, aggressive nature and late-stage diagnosis.In this study, Machine Learning (ML) models were trained and applied on the largest international, monocentric database, comprising over 23 clinical variables from 1040 PDAC patients. In this study, the potential of ML models was assessed for the 1-year survival rate, metastatic M0/M1 status and therapy-dependent survival time generating predictive and prognostic ML-based biomarkers.Consistent predictive performance was achieved for the 1-year survival rate (accuracy, internal/external cohort 72 
KW  - Clinical Decision Suppor (Other)
KW  - Gradient Boosting (Other)
KW  - Machine learning (Other)
KW  - Model Interpretation (Other)
KW  - Oncology (Other)
KW  - Pancreatic cancer (Other)
KW  - Personalized medicine (Other)
KW  - Prognostic modeling (Other)
KW  - Random Forest (Other)
KW  - Random Survival Forest (Other)
KW  - Scenario-Based Simulation (Other)
KW  - Survival analysis (Other)
KW  - Survival prediction (Other)
KW  - Treatment Simulation (Other)
LB  - PUB:(DE-HGF)16
C6  - pmid:41468770
DO  - DOI:10.1016/j.ejca.2025.116189
UR  - https://inrepo02.dkfz.de/record/307503
ER  -