Study M118

Study name

Zheng H 2017

Title

Predictive diagnosis of major depression using NMR-based metabolomics and least-squares support vector machine

Overall design

The aim of this study was to develop an integrated analytical method of NMR-based metabolomics and least squares-support vector machine (LS-SVM) for predictive diagnosis of the major depressive disorder (MDD). The metabolite profiles in clinical plasma samples obtained from first-episode depressive patients (depression group, n = 72) and healthy subjects (control group, n = 54) were analyzed by NMR spectroscopy. Then, LS-SVM models with different kernels were trained and tested using 80% and 20% of samples, respectively.

Study Type

Type1;

Data available

Unavailable

Organism

Human;

Categories of depression

Depressive disorder; Depression; Depression;

Criteria for depression

DSM-IV diagnosed MDD, HAMD-17 > 17

Sample size

126

Tissue

Peripheral; Blood; Plasma;

Platform

NMR; NMR: Bruker Avance III 600 MHz NMR spectrometer (Bruker BioSpin);

PMID

27931880

DOI

10.1016/j.cca.2016.11.039

Citation

Zheng H, Zheng P, Zhao L, et al. Predictive diagnosis of major depression using NMR-based metabolomics and least-squares support vector machine. Clin Chim Acta 2017;464:223-7.

Metabolite

Adipic acid;

Pyruvic acid;

Beta-D-Glucose;

alpha-D-Glucose;

Lipid;

Formic acid;

VLDL/LDL;

Polyunsaturated fatty acid;

Lipids and acetoacetate;

Sugars + Amino acids;