Impact of statistical models on the prediction of type 2 diabetes using non-targeted metabolomics profiling

Yengo, Loic, Arredouani, Abdelilah, Marre, Michel, Roussel, Ronan, Vaxillaire, Martine, Falchi, Mario, Haoudi, Abdelali, Tichet, Jean, Balkau, Beverley, Bonnefond, Amelie and Froguel, Philippe (2016) Impact of statistical models on the prediction of type 2 diabetes using non-targeted metabolomics profiling. Molecular Metabolism, 5 10: 918-925. doi:10.1016/j.molmet.2016.08.011


Author Yengo, Loic
Arredouani, Abdelilah
Marre, Michel
Roussel, Ronan
Vaxillaire, Martine
Falchi, Mario
Haoudi, Abdelali
Tichet, Jean
Balkau, Beverley
Bonnefond, Amelie
Froguel, Philippe
Title Impact of statistical models on the prediction of type 2 diabetes using non-targeted metabolomics profiling
Journal name Molecular Metabolism   Check publisher's open access policy
ISSN 2212-8778
Publication date 2016-10-01
Sub-type Article (original research)
DOI 10.1016/j.molmet.2016.08.011
Open Access Status DOI
Volume 5
Issue 10
Start page 918
End page 925
Total pages 8
Place of publication Amsterdam, Netherlands
Publisher Elsevier BV
Collection year 2017
Language eng
Formatted abstract
Objective: Characterizing specific metabolites in sub-clinical phases preceding the onset of type 2 diabetes to enable efficient preventive and personalized interventions.

Research design and methods: We developed predictive models of type 2 diabetes using two strategies. One strategy focused on the probability of incidence only and was based on logistic regression (MRS1); the other strategy accounted for the age at diagnosis of diabetes and was based on Cox regression (MRS2). We assessed 293 metabolites using non-targeted metabolomics in fasting plasma samples of 1,044 participants (including 231 incident cases over 9 years) used as training population; and fasting serum samples of 128 participants (64 incident cases versus 64 controls) used as validation population. We applied a LASSO-based variable selection aiming at maximizing the out-of-sample area under the receiver operating characteristic curve (AROC) and integrated AROC.

Results: Sixteen and 17 metabolites were selected for MRS1 and MRS2, respectively, with AROC = 90% and 73% in the training and validation populations, respectively for MRS1. MRS2 had a similar performance and was significantly associated with a younger age of onset of type 2 diabetes (β = −3.44 years per MRS2 SD in the training population, p = 1.56 × 10−7; β = −4.73 years per MRS2 SD in the validation population, p = 4.04 × 10−3).

Conclusions:
Overall, this study illustrates that metabolomics improves prediction of type 2 diabetes incidence of 4.5% on top of known clinical and biological markers, reaching 90% in total AROC, which is considered the threshold for clinical validity, suggesting it may be used in targeting interventions to prevent type 2 diabetes.
Keyword High dimensional regression
LASSO
Metabolomics
Risk prediction
Type 2 diabetes
Q-Index Code C1
Q-Index Status Provisional Code
Institutional Status Non-UQ

Document type: Journal Article
Sub-type: Article (original research)
Collection: Institute for Molecular Bioscience - Publications
 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in Thomson Reuters Web of Science Article
Scopus Citation Count Cited 0 times in Scopus Article
Google Scholar Search Google Scholar
Created: Sat, 04 Mar 2017, 01:00:43 EST by Web Cron on behalf of Learning and Research Services (UQ Library)