Vienna, Austria

ESTRO 2023

Session Item

Tuesday
May 16
08:30 - 09:10
Schubert
Statistical methods and analysis for large datasets
Georgina Fröhlich, Hungary
4000
Teaching Lecture
Interdisciplinary
08:30 - 09:10
Statistical methods and analysis for large datasets
Steffen Löck, Germany
SP-0985

Abstract

Statistical methods and analysis for large datasets
Authors:

Steffen Löck1

1OncoRay – National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden - Rossendorf, Dresden, Germany

Show Affiliations
Abstract Text

In this talk, methods will be presented that are able to deal with big datasets. For that purpose, we will discuss a data analysis workflow from data pre-processing to final model interpretation, including relevant aspects such as unsupervised data aggregation, analysis of batch effects, normalisation, training-validation-test approaches, feature selection, hyperparameter tuning, and model interpretation. The methodological steps will be illustrated with examples from radiomics or transcriptomics.