Identification of gene expression signatures associated with neuroinflammation in discogenic sciatica using machine learning and experimental validation.

Background: Sciatica is a debilitating condition characterized by pain radiating along the sciatic nerve, often manifesting due to underlying neuroinflammatory processes. Understanding the molecular mechanisms linking neuroinflammation to sciatica is essential for developing targeted therapeutic interventions. Recent studies have suggested that specific neuroinflammatory genes may play a pivotal role in the pathophysiology of sciatica, offering a potential avenue for understanding this condition. Methods: This study aimed to elucidate the contributions of neuroinflammatory genes to the development of sciatica. We used publicly available datasets GSE124272 and GSE150408 from the Gene Expression Omnibus (GEO) database of the National Center for Biotechnology Information. By thoroughly analyzing the expression matrices, we identified differentially expressed genes (DEGs) linked to neuroinflammatory pathways. Functional annotation was performed using Gene Ontology (GO) analysis and Gene Set Enrichment Analysis (GSEA). To enhance predictive modeling, we employed Least Absolute Shrinkage and Selection Operator (LASSO) regression and Support Vector Machine Recursive Feature Elimination (SVM-RFE) methods to assess neuroinflammatory gene expression. Lastly, we employed quantita-tive real-time PCR (qRT-PCR) to validate our results. Results: The analysis revealed that the identified DEGs are significantly enriched in multiple biological pathways relevant to neuroinflammatory responses in patients with sciatica. Notably, LASSO regression and SVM techniques identified four key neuroinflammatory genes: Conclusion: Our findings substantiate the critical roles of