Skip to main content

Table 3 Multivariable models for CR, OS and RFS

From: AML risk stratification models utilizing ELN-2017 guidelines and additional prognostic factors: a SWOG report

Models AUCs or C-statistics
MNCs VLBs
Complete Response (CR, AUC) Discovery Validation Discovery Validation
ELN2017 0.66 0.73 0.66 0.67
AGE + ELN2017 0.71 0.72 0.71 0.72
AGE + PS + GATA2 + BAALC (MNCs) 0.77a 0.67 N/A N/A
AGE + PS + MN1 + GATA2 (VLBs) N/A N/A 0.72a 0.70
Overall Survival (OS, C Statistic) Discovery Validation Discovery Validation
ELN2017 0.60 0.68 0.59 0.68
AGE + ELN2017 0.72 0.70 0.71 0.71
AGE + ELN2017 + ERG1 + EVI1 + JAG1 + JAG1aELN (MNCs) 0.73a 0.69 N/A N/A
AGE + ELN2017 + EVI1 + ERG1 + CCNA1 (VLBs) N/A N/A 0.71a 0.73
Relapse-Free Survival (RFS, C Statistic) Discovery Validation Discovery Validation
ELN2017b 0.60 0.54 0.61 0.54
AGE + ELN2017b 0.67 0.63 0.66 0.62
AGE + ELN2017b + EVI1 + CCNA1 (MNCs) 0.69a 0.65 N/A N/A
AGE + ELN2017b + EVI1 + CCNA1 (VLBs) N/A N/A 0.72a 0.65
  1. aAUCs or C-statistics for the integrated models come from cross-validation. 1/5 of the discovery data were used to build a model, and the remaining 4/5 of the data were fit to this model, resulting in five C-statistics or AUCs. The mean of the five is presented in the table
  2. bDue to small sample size, ELN2017 in the RFS models was categorized into adverse vs. not adverse (including intermediate, favorable, and unknown)