Objectives: The IPSS-M is a recently published score for risk stratification in myelodysplastic syndromes (MDS), based on clinical and molecular data. We aimed to evaluate its relevance on treatment choice in a real-life setting.Methods: We retrospectively collected clinical, cytogenetic and molecular data from 166 MDS patients. We calculated IPSS-R and IPSS-M scores and compared Overall Survival (OS) and Leukemia Free Survival (LFS). We also analyzed which patients would have been affected by the re-stratification in terms of clinical management.Results: We found that 86.1% of the patients had at least one genetic alteration. The most frequent mutated genes were SF3B1 (25.9%), DNMT3A (16.8%) and ASXL1 (14.4%). IPSS-M re-stratified 48.2% of the patients, of which 16.9% were downgraded and 31.3% were upgraded. IPSS-M improved outcome prediction, with a Harrell’s c-index of 0.680 vs 0.626 for OS and 0.801 vs 0.757 for LFS. In 22.2% of the cohort, the reclassification of the IPSS-M could potentially affect clinical management; 17.4% of the patients would be eligible for treatment intensification and 4.8% for treatment reduction.Conclusions: IPSS-M implementation in clinical practice could imply different treatment approaches in a significant number of patients. Our work validates IPSS-M in an external cohort and confirms its applicability in a real-life setting.

Background/Objectives: This study aimed to determine whether interim PET/CT (iPET) scans could identify follicular lymphoma (FL) patients at high risk of relapse following first-line therapy. Methods: A total of 117 FL patients who underwent iPET scans were included, with responses interpreted using the Deauville score (DS). Progression-free survival (PFS) was evaluated over a median follow-up of 34 months. Results: Overall, 34% of patients were classified as iPET (+), with significantly worse estimated 5-year PFS compared to iPET (−) patients (34% vs. 76%, hazard ratio 4.3, p < 0.001). Multivariate analysis confirmed iPET (+) as an independent predictor of PFS. Conclusions: Interim PET results are significant predictors of PFS in FL first-line therapy and could inform response-adapted treatment strategies.

Anti-CD38 monoclonal antibody (MoAB) therapy has significantly improved the prognosis of patients with multiple myeloma. However, not all patients sustain durable responses. We aimed to describe the natural history of patients relapsed or refractory (R/R) to CD38 MoAB therapy. We performed a single-center, retrospective analysis of the clinical characteristics and outcomes of 81 patients with multiple myeloma who progressed after treatment with daratumumab. Our cohort was heavily pretreated, with a median of two lines prior to daratumumab and only 17 patients received daratumumab as a first line. A total of 38.2% had received a previous autologous stem cell transplantation (ASCT), and 61.7% had received both an immunomodulatory drug (IMID) and a proteasome inhibitor (PI). The median overall survival (OS) was 21 months for the global cohort but it decreased to 14 months for triple-class refractory patients and 5 months for penta-refractory patients. Most of the patients (83.9%) received treatment after daratumumab progression, in many cases with second generation IMID or PI, but seven patients were treated with anti-BCMA therapy and three patients received CART therapy within a clinical trial. In conclusion, patients R/R to daratumumab represent an unmet clinical need with poor prognosis and in need of incorporation of new treatments.

Artificial intelligence (AI) is transforming morphological assessment in hematologic malignancies by enabling automated cell classification, detection of disease-specific features, and prediction of genetic alterations from blood and bone marrow smear images. Deep learning models have achieved expert-level performance in identifying malignant patterns, uncovering morphologic-molecular associations, and providing patient-level diagnoses through multiple instance learning approaches. This review summarizes recent advances in AI-driven morphological analysis across myeloid and lymphoid neoplasms, emphasizing their impact on diagnosis and disease classification. We further examine emerging evidence linking image-derived features, such as nuclear texture, cytoplasmic granularity, and spatial cell organization, to molecular and prognostic variables. In addition, we discuss enabling technologies, including virtual staining and interpretability methods, that support clinical integration. Finally, we address key challenges, including data heterogeneity, the need for prospective validation, and interdisciplinary collaboration. AI-powered, explainable morphological analysis has the potential to advance precision hematology and personalized patient management.

Background/Objectives: This study aimed to determine whether interim PET/CT (iP-ET) scans could identify follicular lymphoma (FL) patients at high risk of relapse fol-lowing first-line therapy. Additionally, the potential of cell-free DNA (cfDNA) analysis to complement iPET in predicting outcomes was explored. Methods: A total of 121 FL patients who underwent iPET scans were included, with responses interpreted using the Deauville score (DS). Progression-free survival (PFS) was evaluated over a median follow-up of 34 months. Interim cfDNA data were analyzed for 14 patients to assess its potential for detecting false-positive PET results. Results: Overall, 34% of patients were classified as iPET(+), with significantly worse estimated 5-year PFS compared to iPET(-) patients (29% vs. 72%, hazard ratio 4.31, p < 0.001). Multivariate analysis confirmed iPET(+) as an independent predictor of PFS. Rituximab maintenance was predictive of reduced progression within the iPET(+) group but not among iPET(-) patients. cfDNA analysis identified two false-positive iPET cases and showed potential to identify pa-tients with complete response at risk of early progression. Conclusions: Interim PET results are significant predictors of PFS in FL first-line therapy and could inform re-sponse-adapted treatment strategies. cfDNA analysis has the potential to complement PET/CT by improving specificity and identifying patients at risk of early progression, offering a more precise approach to managing FL.