Skip to main content
. 2022 Aug 9;36(10):2384–2395. doi: 10.1038/s41375-022-01662-6

Fig. 6. The establishment and validation of risk nomogram in the BeatAML data set.

Fig. 6

A Univariate independent prognostic analysis. B Multivariate independent prognostic analysis based on variables at the diagnosis stage. C 4-factor nomogram containing the paired IPRP risk score. D The prognostic prediction accuracy in the BeatAML training set (n = 152). E The prognostic prediction accuracy in the BeatAML test set (n = 72). The colored curves correspond to different follow-up time points in the survival data with ROC-AUC values. The black diagonal line corresponds to the random classifier (ROC-AUC = 0.5). *p < 0.05, permutation test.