Development and External Validation of a Transcriptome-Based Multivariable Prediction Model for Treatment-Free Remission in Chronic Myeloid Leukemia

The authors aimed to develop and validate a transcriptome-based prediction model for treatment-free remission (TFR) in chronic myeloid leukemia (CML) patients after discontinuing tyrosine kinase inhibitors. They identified a 50-gene signature that effectively discriminates between patients who achieve sustained TFR and those who relapse, demonstrating robust predictive performance in both training and external validation cohorts. Additionally, the study provides insights into the biological processes associated with TFR, highlighting differences in immune cell composition and signaling pathways between high and low TFR-signature groups.