TY - JOUR T1 - Metabolomics-based multidimensional network biomarkers for diabetic retinopathy identification in patients with type 2 diabetes mellitus JF - BMJ Open Diabetes Research & Care JO - BMJ Open Diab Res Care DO - 10.1136/bmjdrc-2020-001443 VL - 9 IS - 1 SP - e001443 AU - Jingjing Zuo AU - Yuan Lan AU - Honglin Hu AU - Xiangqing Hou AU - Jushuang Li AU - Tao Wang AU - Hang Zhang AU - Nana Zhang AU - Chengnan Guo AU - Fang Peng AU - Shuzhen Zhao AU - Yaping Wei AU - Chaonan Jia AU - Chao Zheng AU - Guangyun Mao Y1 - 2021/02/01 UR - http://drc.bmj.com/content/9/1/e001443.abstract N2 - Introduction Despite advances in diabetic retinopathy (DR) medications, early identification is vitally important for DR administration and remains a major challenge. This study aims to develop a novel system of multidimensional network biomarkers (MDNBs) based on a widely targeted metabolomics approach to detect DR among patients with type 2 diabetes mellitus (T2DM) efficiently.Research design and methods In this propensity score matching-based case-control study, we used ultra-performance liquid chromatography-electrospray ionization-tandem mass spectrometry system for serum metabolites assessment of 69 pairs of patients with T2DM with DR (cases) and without DR (controls). Comprehensive analysis, including principal component analysis, orthogonal partial least squares discriminant analysis, generalized linear regression models and a 1000-times permutation test on metabolomics characteristics were conducted to detect candidate MDNBs depending on the discovery set. Receiver operating characteristic analysis was applied for the validation of capability and feasibility of MDNBs based on a separate validation set.Results We detected 613 features (318 in positive and 295 in negative ESI modes) in which 63 metabolites were highly relevant to the presence of DR. A panel of MDNBs containing linoleic acid, nicotinuric acid, ornithine and phenylacetylglutamine was determined based on the discovery set. Depending on the separate validation set, the area under the curve (95% CI), sensitivity and specificity of this MDNBs system were 0.92 (0.84 to 1.0), 96% and 78%, respectively.Conclusions This study demonstrates that metabolomics-based MDNBs are associated with the presence of DR and capable of distinguishing DR from T2DM efficiently. Our data also provide new insights into the mechanisms of DR and the potential value for new treatment targets development. Additional studies are needed to confirm our findings. ER -