The Use of Machine Learning to Create a Risk Score to Predict Survival in Patients with Hepatocellular Carcinoma: A TCGA Cohort Analysis

Figure 2

(a) Classification Tree Analysis was performed with the 15 most important genes derived from NNA. CTA provided three genes that were most predictable of survival along with cutoff values. (b) Based on the individual cutoff values and their predictability for survival or death, a score of either 0 (higher percentage of survival) or 1 (higher percentage of death) was given.