Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2018 Dec;42(8):754-771.
doi: 10.1002/gepi.22159. Epub 2018 Oct 12.

Prediction of treatment response in rheumatoid arthritis patients using genome-wide SNP data

Svetlana Cherlin  1 , Darren Plant  2 , John C Taylor  3   4 , Marco Colombo  5 , Athina Spiliopoulou  5 , Evan Tzanis  6 , Ann W Morgan  4   7 , Michael R Barnes  6 , Paul McKeigue  5 , Jennifer H Barrett  3   4 , Costantino Pitzalis  6 , Anne Barton  2   8 , Matura Consortium  1   2   3   4   5   6   7   8 , Heather J Cordell  2
Affiliations

Prediction of treatment response in rheumatoid arthritis patients using genome-wide SNP data

Svetlana Cherlin et al. Genet Epidemiol. 2018 Dec.

Abstract

Although a number of treatments are available for rheumatoid arthritis (RA), each of them shows a significant nonresponse rate in patients. Therefore, predicting a priori the likelihood of treatment response would be of great patient benefit. Here, we conducted a comparison of a variety of statistical methods for predicting three measures of treatment response, between baseline and 3 or 6 months, using genome-wide SNP data from RA patients available from the MAximising Therapeutic Utility in Rheumatoid Arthritis (MATURA) consortium. Two different treatments and 11 different statistical methods were evaluated. We used 10-fold cross validation to assess predictive performance, with nested 10-fold cross validation used to tune the model hyperparameters when required. Overall, we found that SNPs added very little prediction information to that obtained using clinical characteristics only, such as baseline trait value. This observation can be explained by the lack of strong genetic effects and the relatively small sample sizes available; in analysis of simulated and real data, with larger effects and/or larger sample sizes, prediction performance was much improved. Overall, methods that were consistent with the genetic architecture of the trait were able to achieve better predictive ability than methods that were not. For treatment response in RA, methods that assumed a complex underlying genetic architecture achieved slightly better prediction performance than methods that assumed a simplified genetic architecture.

Keywords: cross validation; prediction; snp data; treatment response.

PubMed Disclaimer

Figures

Figure 1
Figure 1
Pearson correlation coefficient from the prediction analyses for the 11 methods for all the data sets [Color figure can be viewed at wileyonlinelibrary.com]
Figure 2
Figure 2
Calibration slope (a slope of 1 suggests perfect calibration) from the prediction analyses for the 11 methods for all the data sets [Color figure can be viewed at wileyonlinelibrary.com]
Figure 3
Figure 3
Prediction mean squared error (PMSE; lower values indicate better fit) from the prediction analyses for the 11 methods for all the data sets [Color figure can be viewed at wileyonlinelibrary.com]
Figure 4
Figure 4
Prediction with lasso for the SimSparse data set. The black dashed line is the equality line; the red dashed line is the best fit line [Color figure can be viewed at wileyonlinelibrary.com]
Figure 5
Figure 5
Area under the curve (AUC) from the prediction analyses for the 11 methods for all the data sets, after transforming the phenotype to a binary format [Color figure can be viewed at wileyonlinelibrary.com]
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Abraham, G. , Kowalczyk, A. , Zobel, J. , & Inouye, M. (2013). Performance and robustness of penalized and unpenalized methods for genetic prediction of complex human disease. Genetic Epidemiology, 37, 184–195. 10.1002/gepi.21698 - DOI - PubMed
    1. Anderson, C. A. , Pettersson, F. H. , Clarke, G. M. , Cardon, L. R. , Morris, A. P. , & Zondervan, K. T. (2010). Data quality control in genetic case‐control association studies. Annals of the Rheumatic Diseases, 5, 1564–1573. - PMC - PubMed
    1. Baker, J. F. , Conaghan, P. G. , Smolen, J. S. , Aletaha, D. , Shults, J. , Emery, P. , & Østergaard, M. (2014). Development and validation of modified disease activity scores in rheumatoid arthritis: Superior correlation with magnetic resonance imaging‐detected synovitis and radiographic progression. Arthritis & Rheumathology, 66, 794–802. 10.1002/art.38304 - DOI - PubMed
    1. Barrera, P. , vanderMaas, A. , vanEde, A. E. , Kiemeney, B. A. L. M. , Laan, R. F. J. M. , vandePutte, L. B. A. , & vanRiel, P. L. C. M. (2002). Drug survival, efficacy and toxicity of monotherapy with a fully human anti‐tumour necrosis factor‐α antibody compared with methotrexate in long‐standing rheumatoid arthritis. Rheumatology, 41, 530–439. 10.1093/rheumatology/41.4.430 - DOI - PubMed
    1. Barton, A. , & Pitzalis, C. (2017). Stratified medicine in rheumatoid arthritis ‐ the MATURA programme: Targeted treatment for patients. Rheumatology, 56, 1247–1250. 10.1093/rheumatology/kew369 - DOI - PMC - PubMed

Publication types