For patients with myelofibrosis undergoing allogeneic hematopoietic cell transplantation (allo-HCT), machine learning (ML) enhances risk stratification, according to a study published in Blood. Donal McLornan, MBBS, PhD, and colleagues examined different ML models to predict overall survival after transplant in 5,183 patients who underwent first allo-HCT. Th e cohort was divided into training (75%) and test (25%) sets for model validation. Ten variables were included in a Random Survival Forests (RSF) model—age, comorbidity index, performance status, blood blasts, hemoglobin, leukocytes, platelets, donor type, conditioning intensity, and graft-versus-host disease prophylaxis—and compared to that of other models. Th e RSF model outperformed all comparators and achieved better concordance across primary and post-essential thrombocythemia/polycythemia vera myelofibrosis subgroups. In both data sets, metrics confirmed the robustness and generalizability of the RSF model. Although all models were prognostic for non-relapse mortality, better curve separation was provided by the RSF model, which effectively identified a group at high risk, composed of 25% of patients.