Skip to main content
Fig. 6 | European Journal of Medical Research

Fig. 6

From: Immune-associated biomarkers identification for diagnosing carotid plaque progression with uremia through systematical bioinformatics and machine learning analysis

Fig. 6

Candidate diagnostic biomarker identification via machine learning algorithms. A Based on the Lasso regression algorithm, 7 genes corresponding to the lowest point of the curve were identified as the most accurate biomarkers for USCP with the diagnosis of uremia with USCP. B, C The random forest algorithm shows the error in USCP. Based on the random forest algorithm's importance score, we selected and ranked the top ten genes. D, E 8 genes were selected based on SVM-RFE with the lowest error and highest accuracy. F Based on the intersection of genes from three algorithms, three hub genes (FGR, LCP1, and C5AR1) were selected for the next step of nomogram construction and diagnostic value evaluation. SVM-RFE support vector machine-recursive feature elimination, FGR feline Gardner-Rasheed, LCP1 lymphocyte cytosolic protein 1, C5AR1 complement C5a receptor 1

Back to article page

European Journal of Medical Research

ISSN: 2047-783X

Contact us