Identification of CXCL16 as Diagnostic Biomarker Related to Obesity and Intervertebral Disc Degeneration based on Machine Learning

Abstract

Abstract Intervertebral disc degeneration (IDD) of the spine stands as the primary cause of neck and back pain. Obesity has been established as a significant risk factor for IDD. The objective of this study is to explore the molecular mechanisms attributable to the influence of obesity on IDD by identifying the overlapping causative genes associated with both conditions. The identification of specific diagnostic biomarker in obese patients with IDD would have crucial clinical implications.We obtained gene expression profiles of GSE70362 and GSE152991 from GEO, followed by their analysis using two machine learning algorithms, Lasso and SVM-RFE, which enabled the identification of CXCL16 as a shared diagnostic biomarker for obesity and IDD. Additionally, In addition, gene set variant analysis (GSVA) was used to explore the potential mechanism of CXCL16 in the disease, and CXCL16 was found to have an effect on disc degeneration by affecting fatty acid metabolism. Further, correlation analysis between CXCL16 and immune cells demonstrated that CXCL16 negatively regulated T helper 17 cells to induce IDD. Finally, independent external datasets (GSE124272 and GSE59034) were used to verify the diagnostic efficacy of CXCL16. In conclusions, a common diagnostic biomarker of obesity and IDD, CXCL16, was identified using a machine learning algorithm, providing a new perspective for exploring possible mechanisms of secondary IDD in obesity.