Multiparametric Modelling of Survival in Pancreatic Ductal Adenocarcinoma Using Clinical, Histomorphological, Genetic and Image-Derived Parameters.

Georgios A KaissisFriederike JungmannSebastian ZiegelmayerFabian K LohöferFelix N HarderAnna Melissa SchlitterAlexander MuckenhuberKatja SteigerRebekka SchirrenHelmut FriessRoland SchmidWilko WeichertMarcus R MakowskiRickmer F Braren

Published in: Journal of clinical medicine (2020)

Imaging-derived features represent an independent survival predictor in PDAC and enable the multiparametric, machine learning-assisted modelling of postoperative overall survival with a high performance compared to clinical and morpho-molecular/genetic parameters. We propose that future studies systematically include imaging-derived features to benchmark their additive value when evaluating biomarker-based model performance.

Keyphrases

machine learning
high resolution
free survival
genome wide
deep learning
patients undergoing
copy number
artificial intelligence
current status
mass spectrometry
photodynamic therapy
case control