Treatment-specific prognostic performance of ELN 2022, ELN 2024, and Beat AML 2024: a real-world AML validation study

• For AML patients treated with less-intensive therapy, ELN 2024 and Beat AML 2024 best identify a favorable group. • Allogeneic stem-cell transplant improves survival, but patients classified as adverse-risk by any system still have poor outcomes. Real-world validation of ELN 2022, ELN 2024, and Beat AML 2024 across different therapies is needed. We evaluated 426 AML patients (median age 68; 60% male) treated from 2016–2025. ELN 2024 (55% ,24%, 20%), ELN 2022 (20%, 20%, 60%), and Beat AML 2024 (21%, 38%, 41%) assigned patients to favorable, intermediate, and adverse risk with variation. Less intensive treatment (LIT) had lower CR odds than (intensive chemotherapy (IC). For CR prediction, ELN 2022 (AUC 0.763) and Beat AML 2024 (0.759) outperformed ELN 2024 (0.718). With 49.8 months median follow-up, median OS was 15.7 months. Each system stratified mOS (all p<0.001); overall c-index favored ELN 2022 (0.640) and Beat AML 2024 (0.635) over ELN 2024 (0.601). In IC-treated patients, ELN 2022 (0.680) and Beat AML 2024 (0.664) exceeded ELN 2024 (0.601); in LIT-treated patients, ELN 2024 and Beat AML 2024 identified a favorable group with better mOS, whereas ELN 2022 failed to discriminate between favorable and intermediate risk. Allo-HCT improved mOS; in time-dependent analysis, adverse risk by Beat AML 2024 (HR 4.0), ELN 2024 (HR 3.0), and ELN 2022 (HR 2.5) remained independently unfavorable. Overall, Beat AML 2024 was the most informative in IC, and ELN 2024/Beat AML 2024 better identified favorable patients in LIT.