The construction of risk prediction models using GWAS data and its application to a type 2 diabetes prospective cohort

Daichi Shigemizu, Testuo Abe, Takashi Morizono, Todd A. Johnson, Keith A. Boroevich, Yoichiro Hirakawa, Toshiharu Ninomiya, Yutaka Kiyohara, Michiaki Kubo, Yusuke Nakamura, Shiro Maeda, Tatsuhiko Tsunoda

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

Recent genome-wide association studies (GWAS) have identified several novel single nucleotide polymorphisms (SNPs) associated with type 2 diabetes (T2D). Various models using clinical and/or genetic risk factors have been developed for T2D risk prediction. However, analysis considering algorithms for genetic risk factor detection and regression methods for model construction in combination with interactions of risk factors has not been investigated. Here, using genotype data of 7,360 Japanese individuals, we investigated risk prediction models, considering the algorithms, regression methods and interactions. The best model identified was based on a Bayes factor approach and the lasso method. Using nine SNPs and clinical factors, this method achieved an area under a receiver operating characteristic curve (AUC) of 0.8057 on an independent test set. With the addition of a pair of interaction factors, the model was further improved (p-value 0.0011, AUC 0.8085). Application of our model to prospective cohort data showed significantly better outcome in disease-free survival, according to the log-rank trend test comparing Kaplan-Meier survival curves (p-value2:09 × 10-11). While the major contribution was from clinical factors rather than the genetic factors, consideration of genetic risk factors contributed to an observable, though small, increase in predictive ability. This is the first report to apply risk prediction models constructed from GWAS data to a T2D prospective cohort. Our study shows our model to be effective in prospective prediction and has the potential to contribute to practical clinical use in T2D.

Original languageEnglish
Article numbere92549
JournalPloS one
Volume9
Issue number3
DOIs
Publication statusPublished - 20-03-2014

Fingerprint

Genome-Wide Association Study
Medical problems
noninsulin-dependent diabetes mellitus
Type 2 Diabetes Mellitus
Genes
prediction
Area Under Curve
Single Nucleotide Polymorphism
risk factors
Kaplan-Meier Estimate
Polymorphism
ROC Curve
single nucleotide polymorphism
Disease-Free Survival
Nucleotides
Genotype
genome-wide association study
methodology
testing
genotype

All Science Journal Classification (ASJC) codes

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

Shigemizu, D., Abe, T., Morizono, T., Johnson, T. A., Boroevich, K. A., Hirakawa, Y., ... Tsunoda, T. (2014). The construction of risk prediction models using GWAS data and its application to a type 2 diabetes prospective cohort. PloS one, 9(3), [e92549]. https://doi.org/10.1371/journal.pone.0092549
Shigemizu, Daichi ; Abe, Testuo ; Morizono, Takashi ; Johnson, Todd A. ; Boroevich, Keith A. ; Hirakawa, Yoichiro ; Ninomiya, Toshiharu ; Kiyohara, Yutaka ; Kubo, Michiaki ; Nakamura, Yusuke ; Maeda, Shiro ; Tsunoda, Tatsuhiko. / The construction of risk prediction models using GWAS data and its application to a type 2 diabetes prospective cohort. In: PloS one. 2014 ; Vol. 9, No. 3.
@article{71f5cbc3337549dc9b861bd49798093c,
title = "The construction of risk prediction models using GWAS data and its application to a type 2 diabetes prospective cohort",
abstract = "Recent genome-wide association studies (GWAS) have identified several novel single nucleotide polymorphisms (SNPs) associated with type 2 diabetes (T2D). Various models using clinical and/or genetic risk factors have been developed for T2D risk prediction. However, analysis considering algorithms for genetic risk factor detection and regression methods for model construction in combination with interactions of risk factors has not been investigated. Here, using genotype data of 7,360 Japanese individuals, we investigated risk prediction models, considering the algorithms, regression methods and interactions. The best model identified was based on a Bayes factor approach and the lasso method. Using nine SNPs and clinical factors, this method achieved an area under a receiver operating characteristic curve (AUC) of 0.8057 on an independent test set. With the addition of a pair of interaction factors, the model was further improved (p-value 0.0011, AUC 0.8085). Application of our model to prospective cohort data showed significantly better outcome in disease-free survival, according to the log-rank trend test comparing Kaplan-Meier survival curves (p-value2:09 × 10-11). While the major contribution was from clinical factors rather than the genetic factors, consideration of genetic risk factors contributed to an observable, though small, increase in predictive ability. This is the first report to apply risk prediction models constructed from GWAS data to a T2D prospective cohort. Our study shows our model to be effective in prospective prediction and has the potential to contribute to practical clinical use in T2D.",
author = "Daichi Shigemizu and Testuo Abe and Takashi Morizono and Johnson, {Todd A.} and Boroevich, {Keith A.} and Yoichiro Hirakawa and Toshiharu Ninomiya and Yutaka Kiyohara and Michiaki Kubo and Yusuke Nakamura and Shiro Maeda and Tatsuhiko Tsunoda",
year = "2014",
month = "3",
day = "20",
doi = "10.1371/journal.pone.0092549",
language = "English",
volume = "9",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "3",

}

Shigemizu, D, Abe, T, Morizono, T, Johnson, TA, Boroevich, KA, Hirakawa, Y, Ninomiya, T, Kiyohara, Y, Kubo, M, Nakamura, Y, Maeda, S & Tsunoda, T 2014, 'The construction of risk prediction models using GWAS data and its application to a type 2 diabetes prospective cohort', PloS one, vol. 9, no. 3, e92549. https://doi.org/10.1371/journal.pone.0092549

The construction of risk prediction models using GWAS data and its application to a type 2 diabetes prospective cohort. / Shigemizu, Daichi; Abe, Testuo; Morizono, Takashi; Johnson, Todd A.; Boroevich, Keith A.; Hirakawa, Yoichiro; Ninomiya, Toshiharu; Kiyohara, Yutaka; Kubo, Michiaki; Nakamura, Yusuke; Maeda, Shiro; Tsunoda, Tatsuhiko.

In: PloS one, Vol. 9, No. 3, e92549, 20.03.2014.

Research output: Contribution to journalArticle

TY - JOUR

T1 - The construction of risk prediction models using GWAS data and its application to a type 2 diabetes prospective cohort

AU - Shigemizu, Daichi

AU - Abe, Testuo

AU - Morizono, Takashi

AU - Johnson, Todd A.

AU - Boroevich, Keith A.

AU - Hirakawa, Yoichiro

AU - Ninomiya, Toshiharu

AU - Kiyohara, Yutaka

AU - Kubo, Michiaki

AU - Nakamura, Yusuke

AU - Maeda, Shiro

AU - Tsunoda, Tatsuhiko

PY - 2014/3/20

Y1 - 2014/3/20

N2 - Recent genome-wide association studies (GWAS) have identified several novel single nucleotide polymorphisms (SNPs) associated with type 2 diabetes (T2D). Various models using clinical and/or genetic risk factors have been developed for T2D risk prediction. However, analysis considering algorithms for genetic risk factor detection and regression methods for model construction in combination with interactions of risk factors has not been investigated. Here, using genotype data of 7,360 Japanese individuals, we investigated risk prediction models, considering the algorithms, regression methods and interactions. The best model identified was based on a Bayes factor approach and the lasso method. Using nine SNPs and clinical factors, this method achieved an area under a receiver operating characteristic curve (AUC) of 0.8057 on an independent test set. With the addition of a pair of interaction factors, the model was further improved (p-value 0.0011, AUC 0.8085). Application of our model to prospective cohort data showed significantly better outcome in disease-free survival, according to the log-rank trend test comparing Kaplan-Meier survival curves (p-value2:09 × 10-11). While the major contribution was from clinical factors rather than the genetic factors, consideration of genetic risk factors contributed to an observable, though small, increase in predictive ability. This is the first report to apply risk prediction models constructed from GWAS data to a T2D prospective cohort. Our study shows our model to be effective in prospective prediction and has the potential to contribute to practical clinical use in T2D.

AB - Recent genome-wide association studies (GWAS) have identified several novel single nucleotide polymorphisms (SNPs) associated with type 2 diabetes (T2D). Various models using clinical and/or genetic risk factors have been developed for T2D risk prediction. However, analysis considering algorithms for genetic risk factor detection and regression methods for model construction in combination with interactions of risk factors has not been investigated. Here, using genotype data of 7,360 Japanese individuals, we investigated risk prediction models, considering the algorithms, regression methods and interactions. The best model identified was based on a Bayes factor approach and the lasso method. Using nine SNPs and clinical factors, this method achieved an area under a receiver operating characteristic curve (AUC) of 0.8057 on an independent test set. With the addition of a pair of interaction factors, the model was further improved (p-value 0.0011, AUC 0.8085). Application of our model to prospective cohort data showed significantly better outcome in disease-free survival, according to the log-rank trend test comparing Kaplan-Meier survival curves (p-value2:09 × 10-11). While the major contribution was from clinical factors rather than the genetic factors, consideration of genetic risk factors contributed to an observable, though small, increase in predictive ability. This is the first report to apply risk prediction models constructed from GWAS data to a T2D prospective cohort. Our study shows our model to be effective in prospective prediction and has the potential to contribute to practical clinical use in T2D.

UR - http://www.scopus.com/inward/record.url?scp=84898629887&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84898629887&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0092549

DO - 10.1371/journal.pone.0092549

M3 - Article

C2 - 24651836

AN - SCOPUS:84898629887

VL - 9

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 3

M1 - e92549

ER -