Skip to main content
. 2019 Jul 21;2019:7239780. doi: 10.1155/2019/7239780

Figure 2.

Figure 2

Predictive importance of the input variables. As demonstrated in the ANN model, AST, PLT, WBC, CHE, LSM, ALT, and gender were the most important predictors of liver cirrhosis reverse by sensitive analysis. AST was the most crucial node with the weight coefficient of 0.296 in our model.