Skip to main content
Fig. 6 | Lipids in Health and Disease

Fig. 6

From: Role of arachidonic acid metabolism in intervertebral disc degeneration: identification of potential biomarkers and therapeutic targets via multi-omics analysis and artificial intelligence strategies

Fig. 6

Development of the early diagnosis model for IVDD. A ROC curves of SVM and RF models. B The impact of the number of decision trees on the error rate. The x-axis represents the number of decision trees, and the y-axis indicates the error rate. The error rate stabilized at approximately 500 decision trees. C Results of the RF classifier's Gini coefficient approach. Genetic variation is on the x-axis, and the significance index is on the y-axis. D, E Gene selection process using SVM-RFE and tenfold cross-validation in the GSE70362 and GSE176205 datasets. The highest model accuracy was achieved when 29 genes were selected. F UpSet plot showcasing the characteristic genes in LASSO, RF, DEGs, and SVM-RFE. G ROC curve values for the five hub genes in the GSE70362 and GSE176205 datasets. H–L Representative bar graphs reveal the expression differences in ALOX5, AKR1C3, CYP2B6, EPHX2, and PLB1 between mild IVDD (n = 17) and severe IVDD (n = 16)

Back to article page

Lipids in Health and Disease

ISSN: 1476-511X