Skip to main content
Fig. 2 | Journal of Translational Medicine

Fig. 2

From: Clinical applications of machine learning in the survival prediction and classification of sepsis: coagulation and heparin usage matter

Fig. 2

Identification of the subgroup phenotype with k-means clustering. The K value was optimized by compromising between the elbow method (A) and the silhouette coefficient method (B); C. The 3D PCA plot visualizes the 4 clusters; D. Survival curves; E. SIC score; F. SOFA score. * P < 0.05, ****P < 0.0001 analyzed by log-rank test of Mantel or Gehan-Breslow Wilcoxon test with the higher P value presented

Back to article page