Affordable Access

deepdyve-link
Publisher Website

Statistical learning approaches in the genetic epidemiology of complex diseases.

Authors
  • Boulesteix, Anne-Laure1
  • Wright, Marvin N2, 3
  • Hoffmann, Sabine4
  • König, Inke R5
  • 1 Institute for Medical Information Processing, Biometry and Epidemiology, Ludwig-Maximilians-University, Munich, Germany. [email protected] , (Germany)
  • 2 Leibniz Institute for Prevention Research and Epidemiology-BIPS, Bremen, Germany. , (Germany)
  • 3 Section of Biostatistics, Department of Public Health, University of Copenhagen, Copenhagen, Denmark. , (Denmark)
  • 4 Institute for Medical Information Processing, Biometry and Epidemiology, Ludwig-Maximilians-University, Munich, Germany. , (Germany)
  • 5 Institute of Medical Biometry and Statistics, University of Lübeck, Lübeck, Germany. , (Germany)
Type
Published Article
Journal
Human Genetics
Publisher
Springer-Verlag
Publication Date
May 02, 2019
Identifiers
DOI: 10.1007/s00439-019-01996-9
PMID: 31049651
Source
Medline
Keywords
Language
English
License
Unknown

Abstract

In this paper, we give an overview of methodological issues related to the use of statistical learning approaches when analyzing high-dimensional genetic data. The focus is set on regression models and machine learning algorithms taking genetic variables as input and returning a classification or a prediction for the target variable of interest; for example, the present or future disease status, or the future course of a disease. After briefly explaining the basic motivation and principle of these methods, we review different procedures that can be used to evaluate the accuracy of the obtained models and discuss common flaws that may lead to over-optimistic conclusions with respect to their prediction performance and usefulness.

Report this publication

Statistics

Seen <100 times