Screening of Potential Biomarkers in the Peripheral Serum for Steroid-Induced Osteonecrosis of the Femoral Head Based on WGCNA and Machine Learning Algorithms

<div>Identification of potential biomarkers for SONFH based on machine learning algorithms. (a) Log (Lambda) value of the three genes in LASSO model. (b) The most proper log (Lambda) value in LASSO model. (c) ROC curve of the LASSO model based on three genes. (d) The optimum error rate of SVM model based on 16 characteristic genes. (e) ROC curve of the RF module based on top 10 genes. (f) Venn diagram shows the overlapping genes in LASSO, SVM, and RF module.</div>

Disease Markers

fig4

Figure 4

Figure 4: Screening of Potential Biomarkers in the Peripheral Serum for Steroid-Induced Osteonecrosis of the Femoral Head Based on WGCNA and Machine Learning Algorithms 

Figure 4 | Screening of Potential Biomarkers in the Peripheral Serum for Steroid-Induced Osteonecrosis of the Femoral Head Based on WGCNA and Machine Learning Algorithms 