% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Karunamuni:157070,
author = {R. A. Karunamuni and M.-P. Huynh-Le and C. C. Fan and R. A.
Eeles and D. F. Easton and Z. Kote-Jarai and A. Amin Al
Olama and S. Benlloch Garcia and K. Muir and H. Gronberg and
F. Wiklund and M. Aly and J. Schleutker and C. Sipeky and T.
L. J. Tammela and B. G. Nordestgaard and T. J. Key and R. C.
Travis and D. E. Neal and J. L. Donovan and F. C. Hamdy and
P. Pharoah and N. Pashayan and K.-T. Khaw and S. N.
Thibodeau and S. K. McDonnell and D. J. Schaid and C. Maier
and W. Vogel and M. Luedeke and K. Herkommer and A. S. Kibel
and C. Cybulski and D. Wokolorczyk and W. Kluzniak and L.
Cannon-Albright and H. Brenner$^*$ and B. Schöttker$^*$ and
B. Holleczek$^*$ and J. Y. Park and T. A. Sellers and H.-Y.
Lin and C. Slavov and R. Kaneva and V. Mitev and J. Batra
and J. A. Clements and A. Spurdle and M. R. Teixeira and P.
Paulo and S. Maia and H. Pandha and A. Michael and I. G.
Mills and O. A. Andreassen and A. M. Dale and T. M. Seibert},
collaboration = {A. P. C. BioResource and P. Consortium},
title = {{T}he effect of sample size on polygenic hazard models for
prostate cancer.},
journal = {European journal of human genetics},
volume = {28},
number = {10},
issn = {1476-5438},
address = {Basingstoke},
publisher = {Stockton Press},
reportid = {DKFZ-2020-01361},
pages = {1467-1475},
year = {2020},
note = {2020 Oct;28(10):1467-1475},
abstract = {We determined the effect of sample size on performance of
polygenic hazard score (PHS) models in prostate cancer. Age
and genotypes were obtained for 40,861 men from the
PRACTICAL consortium. The dataset included 201,590 SNPs per
subject, and was split into training and testing sets.
Established-SNP models considered 65 SNPs that had been
previously associated with prostate cancer. Discovery-SNP
models used stepwise selection to identify new SNPs. The
performance of each PHS model was calculated for random
sizes of the training set. The performance of a
representative Established-SNP model was estimated for
random sizes of the testing set. Mean HR98/50 (hazard ratio
of top $2\%$ to average in test set) of the Established-SNP
model increased from 1.73 $[95\%$ CI: 1.69-1.77] to 2.41
[2.40-2.43] when the number of training samples was
increased from 1 thousand to 30 thousand. Corresponding
HR98/50 of the Discovery-SNP model increased from 1.05
[0.93-1.18] to 2.19 [2.16-2.23]. HR98/50 of a representative
Established-SNP model using testing set sample sizes of 0.6
thousand and 6 thousand observations were 1.78 [1.70-1.85]
and 1.73 [1.71-1.76], respectively. We estimate that a study
population of 20 thousand men is required to develop
Discovery-SNP PHS models while 10 thousand men should be
sufficient for Established-SNP models.},
cin = {C070 / C120 / HD01},
ddc = {610},
cid = {I:(DE-He78)C070-20160331 / I:(DE-He78)C120-20160331 /
I:(DE-He78)HD01-20160331},
pnm = {313 - Cancer risk factors and prevention (POF3-313)},
pid = {G:(DE-HGF)POF3-313},
typ = {PUB:(DE-HGF)16},
pubmed = {pmid:32514134},
doi = {10.1038/s41431-020-0664-2},
url = {https://inrepo02.dkfz.de/record/157070},
}