Figure 7 | Scientific Reports

Figure 7

From: Identification of diagnostic biomarkers for idiopathic pulmonary hypertension with metabolic syndrome by bioinformatics and machine learning

Figure 7

Machine learning. Drawn by R software program (version 3.40.6; R Foundation for Statistical Computing, Vienna, Austria, https://www.r-project.org/). (A,B) Genes are screened by the LASSO algorithm. In order to obtain the optimal model, the ten-fold cross-validation method is adopted. The lowest gene number n = 18 at the lowest point of the curve is best suited for LASSO. (C,D) Screen genes via random forest algorithm. The top 30 significant genes recognized from Random Forest. IncNodePurity rank the genes in accordance with their relative importance. (E) Venn plot of the intersection of two algorithms. (F) Nomogram for IPAH and MS diagnostics. (G) Nomogram's calibration curve, Close to the diagonal indicates high accuracy.

Back to article page