Research Article
LASSO Model Better Predicted the Prognosis of DLBCL than Random Forest Model: A Retrospective Multicenter Analysis of HHLWG
Table 2
Multivariable analysis of OS based on LASSO and random forest.
| Variables | HR | 95% CI | |
| LASSO | | | | Age | 1.032 | 1.022-1.042 | <0.001 | WBC | 1.028 | 1.017-1.040 | <0.001 | HB | 0.988 | 0.983-0.993 | <0.001 | CNS involvement | 2.241 | 1.636-3.068 | <0.001 | Gender | 0.659 | 0.524-0.829 | <0.001 | Ann Arbor stage | 1.644 | 1.286-2.100 | <0.001 | Random forest | | | | Age | 1.031 | 1.021-1.041 | <0.001 | WBC | 1.031 | 1.020-1.041 | <0.001 | HB | 0.988 | 0.983-0.994 | <0.001 | CNS involvement | 1.992 | 1.462-2.715 | <0.001 | ALB | 0.984 | 0.969-0.999 | 0.038 | ECOG | 1.295 | 1.011-1.659 | 0.040 |
|
|