000307503 001__ 307503 000307503 005__ 20260122141454.0 000307503 0247_ $$2doi$$a10.1016/j.ejca.2025.116189 000307503 0247_ $$2pmid$$apmid:41468770 000307503 0247_ $$2ISSN$$a0959-8049 000307503 0247_ $$2ISSN$$a0014-2964 000307503 0247_ $$2ISSN$$a1879-0852 000307503 0247_ $$2ISSN$$a(1990) 000307503 0247_ $$2ISSN$$a1879-2995 000307503 0247_ $$2ISSN$$a(1965) 000307503 037__ $$aDKFZ-2026-00008 000307503 041__ $$aEnglish 000307503 082__ $$a610 000307503 1001_ $$aSchneider, François$$b0 000307503 245__ $$aThe basis for future personalized therapy approaches - Machine learning-generated 1-year survival rate, metastatic status and therapy-dependent survival in pancreatic cancer patients. 000307503 260__ $$aAmsterdam [u.a.]$$bElsevier$$c2026 000307503 3367_ $$2DRIVER$$aarticle 000307503 3367_ $$2DataCite$$aOutput Types/Journal article 000307503 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1769087667_2905066 000307503 3367_ $$2BibTeX$$aARTICLE 000307503 3367_ $$2ORCID$$aJOURNAL_ARTICLE 000307503 3367_ $$00$$2EndNote$$aJournal Article 000307503 500__ $$a2026 Feb 5;234:116189 000307503 520__ $$aPancreatic 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 % / 70 %) and radiological metastatic M0/M1 status (Accuracy, internal/external cohort 79 % / 72 %). Moreover, distinct ML-based survival models were trained for approved first-line adjuvant and palliative chemotherapy regimen (mFOLFIRINOX, gemcitabine with or without nab-paclitaxel) across resected (C-index = 0.60), locally advanced (C-index = 0.71) and metastatic (C-index = 0.71) PDAC subgroups, demonstrating that predictive performance is best for palliative regimens.The models developed in this study may serve as a foundation for supporting tumor board decisions and demonstrate that personalized, ML-based therapy concepts are feasible in the near future. In addition, the models proposed in this study are helpful for generating ML-based synthetic control arms in future clinical trials. 000307503 536__ $$0G:(DE-HGF)POF4-899$$a899 - ohne Topic (POF4-899)$$cPOF4-899$$fPOF IV$$x0 000307503 588__ $$aDataset connected to CrossRef, PubMed, , Journals: inrepo02.dkfz.de 000307503 650_7 $$2Other$$aClinical Decision Suppor 000307503 650_7 $$2Other$$aGradient Boosting 000307503 650_7 $$2Other$$aMachine learning 000307503 650_7 $$2Other$$aModel Interpretation 000307503 650_7 $$2Other$$aOncology 000307503 650_7 $$2Other$$aPancreatic cancer 000307503 650_7 $$2Other$$aPersonalized medicine 000307503 650_7 $$2Other$$aPrognostic modeling 000307503 650_7 $$2Other$$aRandom Forest 000307503 650_7 $$2Other$$aRandom Survival Forest 000307503 650_7 $$2Other$$aScenario-Based Simulation 000307503 650_7 $$2Other$$aSurvival analysis 000307503 650_7 $$2Other$$aSurvival prediction 000307503 650_7 $$2Other$$aTreatment Simulation 000307503 7001_ $$aChen, Haotian$$b1 000307503 7001_ $$aPelzer, Uwe$$b2 000307503 7001_ $$aCompton, Richard G$$b3 000307503 7001_ $$aDuwe, Gregor$$b4 000307503 7001_ $$0P:(DE-He78)396821e874b632341e4bcabd27bcad3f$$aDragomir, Mihnea P$$b5$$udkfz 000307503 7001_ $$aHilfenhaus, Georg$$b6 000307503 7001_ $$aVecchione, Loredana$$b7 000307503 7001_ $$aAlig, Annabel$$b8 000307503 7001_ $$aFelsenstein, Matthäus$$b9 000307503 7001_ $$aLerchbaumer, Markus$$b10 000307503 7001_ $$aRieke, Damian T$$b11 000307503 7001_ $$aBahra, Marcus$$b12 000307503 7001_ $$aKutsche, Ralf$$b13 000307503 7001_ $$aTschulik, Kristina$$b14 000307503 7001_ $$aStintzing, Sebastian$$b15 000307503 7001_ $$aKeilholz, Ulrich$$b16 000307503 7001_ $$aNeumann, Christopher C M$$b17 000307503 773__ $$0PERI:(DE-600)1468190-0$$a10.1016/j.ejca.2025.116189$$gVol. 234, p. 116189 -$$p116189$$tEuropean journal of cancer$$v234$$x0959-8049$$y2026 000307503 909CO $$ooai:inrepo02.dkfz.de:307503$$pVDB 000307503 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)396821e874b632341e4bcabd27bcad3f$$aDeutsches Krebsforschungszentrum$$b5$$kDKFZ 000307503 9131_ $$0G:(DE-HGF)POF4-899$$1G:(DE-HGF)POF4-890$$2G:(DE-HGF)POF4-800$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bProgrammungebundene Forschung$$lohne Programm$$vohne Topic$$x0 000307503 9141_ $$y2025 000307503 915__ $$0StatID:(DE-HGF)0420$$2StatID$$aNationallizenz$$d2024-12-18$$wger 000307503 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2024-12-18 000307503 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2024-12-18 000307503 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2024-12-18 000307503 915__ $$0StatID:(DE-HGF)1050$$2StatID$$aDBCoverage$$bBIOSIS Previews$$d2024-12-18 000307503 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2024-12-18 000307503 915__ $$0StatID:(DE-HGF)1030$$2StatID$$aDBCoverage$$bCurrent Contents - Life Sciences$$d2024-12-18 000307503 915__ $$0StatID:(DE-HGF)1190$$2StatID$$aDBCoverage$$bBiological Abstracts$$d2024-12-18 000307503 915__ $$0StatID:(DE-HGF)1110$$2StatID$$aDBCoverage$$bCurrent Contents - Clinical Medicine$$d2024-12-18 000307503 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2024-12-18 000307503 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2024-12-18 000307503 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bEUR J CANCER : 2022$$d2024-12-18 000307503 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search$$d2024-12-18 000307503 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC$$d2024-12-18 000307503 915__ $$0StatID:(DE-HGF)9905$$2StatID$$aIF >= 5$$bEUR J CANCER : 2022$$d2024-12-18 000307503 9201_ $$0I:(DE-He78)BE01-20160331$$kBE01$$lDKTK Koordinierungsstelle Berlin$$x0 000307503 980__ $$ajournal 000307503 980__ $$aVDB 000307503 980__ $$aI:(DE-He78)BE01-20160331 000307503 980__ $$aUNRESTRICTED