TY  - JOUR
AU  - Fan, Ziwen
AU  - Edelmann, Dominic
AU  - Yuan, Tanwei
AU  - Köhler, Bruno Christian
AU  - Hoffmeister, Michael
AU  - Brenner, Hermann
TI  - Developing survival prediction models in colorectal cancer using epigenome-wide DNA methylation data from whole blood.
JO  - npj precision oncology
VL  - 8
IS  - 1
SN  - 2397-768X
CY  - [London]
PB  - Springer Nature
M1  - DKFZ-2024-01806
SP  - 191
PY  - 2024
N1  - #EA:C070#LA:C070#LA:C120#
AB  - While genome-wide association studies are valuable in identifying CRC survival predictors, the benefit of adding blood DNA methylation (blood-DNAm) to clinical features, including the TNM system, remains unclear. In a multi-site population-based patient cohort study of 2116 CRC patients with baseline blood-DNAm, we analyzed survival predictions using eXtreme Gradient Boosting with a 5-fold nested leave-sites-out cross-validation across four groups: traditional and comprehensive clinical features, blood-DNAm, and their combination. Model performance was assessed using time-dependent ROC curves and calibrations. During a median follow-up of 10.3 years, 1166 patients died. Although blood-DNAm-based predictive signatures achieved moderate performances, predictive signatures based on clinical features outperformed blood-DNAm signatures. The inclusion of blood-DNAm did not improve survival prediction over clinical features. M1 stage, age at blood collection, and N2 stage were the top contributors. Despite some prognostic value, incorporating blood DNA methylation did not enhance survival prediction of CRC patients beyond clinical features.
LB  - PUB:(DE-HGF)16
C6  - pmid:39237753
DO  - DOI:10.1038/s41698-024-00689-5
UR  - https://inrepo02.dkfz.de/record/292565
ER  -