Integrating AIPSS‐MF and molecular predictors: A comparative analysis of prognostic models for myelofibrosis

[...]the potential improvement of our ML model's prognostic accuracy by incorporating molecular data on additional somatic mutations could not be adequately evaluated because a significant proportion of patients did not have this information available at that time. For OS prediction, the ML model considering VAF proved superior to those based solely on the presence/absence of mutations or the total mutation count per gene (Supporting Information S1: Table ). In parallel, the primary model for LFS prediction was based on the VAF of 20 genes (c-index, 0.702; Supporting Information S1: Table ) and showed slight improvement when mutational data of the CALR gene or U2AF1 Q157 mutation was incorporated. [...]although we mitigated the absence of an external dataset by cross-validating our findings, the intrinsic limitations of internal validation loom.