Abstract
Abstract We report on our progress towards developing a test for early breast cancer detection using metabolite profiling methods. Using a combination of nuclear magnetic resonance (NMR) and multivariate statistical methods principal component analysis (PCA), partial least squares-discriminant analysis (PLS-DA) and orthogonal signal correction-partial least squares-discriminant analysis (O-PLS-DA) to analyzed the metabolite profiles of 142 breast cancer patients and 272 healthy control from four different sites. PCA and PLS-DA analysis was able to distinguish cancer patients from controls. From the analysis of the corresponding loading plots, 17 metabolites that were altered in concentration between cancer and controls were identified and tested individually and collectively using all samples. From a variable selection analysis, nine metabolite markers were shortlisted from analysis of samples from two of the locations using 10-fold cross validation. A PLS-DA model built using these markers with leave one out cross validation provided a sensitivity of 84% and a specificity of 98% (AUROC >0.95). Strikingly, when this model was used to test samples from the other two locations we achieved a sensitivity of 82% and specificity of 93% (AUROC >90%). Analysis of the samples after randomly assigning them into testing and training sets also performed well (AUROC >0.90). While additional work needs to be carried out on a broader range of normals and cancer patients, to the best of our knowledge, this is the first multisite study to identify and prevalidate a prediction model for early detection of breast cancer based on a metabolic profile. In particular, the combination of NMR and advanced multivariate analysis is a powerful approach for the early detection of breast cancer. This talk is also presented as Poster B20. Citation Information: Cancer Prev Res 2010;3(12 Suppl):PR-06.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
