TY - JOUR
T1 - Risk estimation and risk prediction using machine-learning methods
AU - Kruppa, Jochen
AU - Ziegler, Andreas
AU - König, Inke R.
PY - 2012/10
Y1 - 2012/10
N2 - After an association between genetic variants and a phenotype has been established, further study goals comprise the classification of patients according to disease risk or the estimation of disease probability. To accomplish this, different statistical methods are required, and specifically machine-learning approaches may offer advantages over classical techniques. In this paper, we describe methods for the construction and evaluation of classification and probability estimation rules. We review the use of machine-learning approaches in this context and explain some of the machine-learning algorithms in detail. Finally, we illustrate the methodology through application to a genome-wide association analysis on rheumatoid arthritis.
AB - After an association between genetic variants and a phenotype has been established, further study goals comprise the classification of patients according to disease risk or the estimation of disease probability. To accomplish this, different statistical methods are required, and specifically machine-learning approaches may offer advantages over classical techniques. In this paper, we describe methods for the construction and evaluation of classification and probability estimation rules. We review the use of machine-learning approaches in this context and explain some of the machine-learning algorithms in detail. Finally, we illustrate the methodology through application to a genome-wide association analysis on rheumatoid arthritis.
UR - http://www.scopus.com/inward/record.url?scp=84866731649&partnerID=8YFLogxK
U2 - 10.1007/s00439-012-1194-y
DO - 10.1007/s00439-012-1194-y
M3 - Scientific review articles
C2 - 22752090
AN - SCOPUS:84866731649
VL - 131
SP - 1639
EP - 1654
JO - Human Molecular Genetics
JF - Human Molecular Genetics
SN - 0964-6906
IS - 10
ER -