Lanino, Luca

Myelodysplastic syndromes with isolated deletion of chromosome 5q [MDS-del(5q)] constitute a distinct biological entity traditionally associated with favorable outcomes, although up to one quarter of patients progress to acute myeloid leukemia (AML). Existing prognostic models, developed in heterogeneous MDS populations, may not adequately capture risk within this subgroup. We assembled an international cohort of 682 patients with MDS-del(5q) to evaluate the performance of the IPSS-R and IPSS-M, identify prognostic variables, and develop a disease-specific prognostic tool, the IPSS-del(5q). Most patients were classified as lower-risk by IPSS-R (94.4%) and IPSS-M (85.5%), yet both systems showed limited discriminatory ability (C-indices ≈0.5). Independent adverse prognostic factors included age ≥70 years, male sex, anemia (hemoglobin ≤10 g/dL), thrombocytopenia (platelets ≤100×10⁹/L), the presence of one additional chromosomal abnormality, ≥2 gene mutations, SF3B1 mutations, and high-risk TP53 status. Six variables were included in the IPSS-del(5q), stratifying patients into standard-risk (74.3%) and high-risk (25.7%) groups with significantly different LFS (69.2 vs. 32.0 months; p<0.01). Moreover, this model reclassified 19.1% of lower-risk IPSS-R and 14.6% of lower-risk IPSS-M patients into the high-risk IPSS-del(5q) group. However, its discriminative power remained modest, with a C-index of 0.60. Overall, this study provides the most comprehensive prognostic evaluation of MDS-del(5q) to date, demonstrates the limited discriminatory capacity of existing MDS scores in this entity, and underscores the need to develop refined disease-specific prognostic approaches for this MDS subtype.

PURPOSE Chronic myelomonocytic leukemia (CMML) is a rare myeloid neoplasm characterized by clinical heterogeneity and is associated with poor outcomes. To date, limited molecular information has been incorporated into disease classification and risk stratification. We aimed to integrate genomic features into the clinical decision-making process for CMML. PATIENTS AND METHODS We analyzed a retrospective cohort of 3013 patients with CMML (training set) and a prospective population of 516 patients (validation set). Using an innovative framework for multimodal data analysis, we developed molecular-based disease taxonomy and prognostication. RESULTS Unsupervised clustering identified nine entities with distinct genomic features and outcomes ( P < .001), including splicing machinery, transcription factors, signal transduction and tyrosine kinase pathways aberrations, and high-risk molecular signatures. Notably, 15% of patients showed molecular/clinical overlap with other myeloid neoplasms. We integrated molecular and clinical information to build the international CMML Prognostic Scoring System (iCPSS), incorporating mutations in nine genes together with hematologic parameters and cytogenetic abnormalities. The iCPSS identified five groups with distinct probability of overall and leukemia-free survival in both training and validation cohorts ( P < .001), outperforming existing prognostic models. Importantly, 55% of patients were reassigned to higher or lower risk groups by the iCPSS. Decision analysis demonstrated that iCPSS could refine the optimal timing of allogeneic transplantation at the individual level; compared with conventional prognostic tools, iCPSS-based decision modeling changed transplantation strategy in 31% of cases, resulting in a significant gain-in-life expectancy for eligible patient population ( P < .001). A federated learning platform was implemented to enable continuous, privacy-preserving model update across multiple centers. CONCLUSION Molecular information improves CMML classification and prognostication, supports more effective clinical decision making, and potentially refines the design of clinical trials.