Molecular and clinical presentation of UBA1-mutated myelodysplastic syndromes.

Mutations in UBA1, which are disease-defining for VEXAS syndrome, have been reported in patients diagnosed with myelodysplastic syndromes (MDS). Here, we define the prevalence and clinical associations of UBA1 mutations in a representative cohort of patients with MDS. Digital droplet PCR profiling of a selected cohort of 375 male patients lacking MDS disease-defining mutations or established WHO disease classification identified 28 patients (7%) with UBA1 p.M41T/V/L mutations. Using targeted sequencing of UBA1 in a representative MDS cohort (n=2,027), we identified an additional 27 variants in 26 patients (1%), which we classified as likely/pathogenic (n=12) and unknown significance (n=15). Among the total 40 patients with likely/pathogenic variants (2%), all were male and 63% were classified by WHO2016 as MDS-MLD/SLD. Patients had a median of one additional myeloid gene mutation, often in TET2 (n=12), DNMT3A (n=10), ASXL1 (n=3), or SF3B1 (n=3). Retrospective clinical review where possible showed that 83% (28/34) UBA1-mutant cases had VEXAS-associated diagnoses or inflammatory clinical presentation. The prevalence of UBA1-mutations in MDS patients argues for systematic screening for UBA1 in the management of MDS.

Molecular Taxonomy of Myelodysplastic Syndromes and its Clinical Implications.

Myelodysplastic syndromes/neoplasms (MDS) are clonal hematologic disorders characterized by morphologic abnormalities of myeloid cells and peripheral cytopenias. While genetic abnormalities underlie the pathogenesis of these disorders and their heterogeneity, current classifications of MDS rely predominantly on morphology. We performed genomic profiling of 3,233 patients with MDS or related disorders to delineate molecular subtypes and define their clinical implications. Gene mutations, copy-number alterations (CNAs), and copy-neutral loss of heterozygosity (cnLOH) were derived from targeted sequencing of a 152-gene panel, with abnormalities identified in 91, 43, and 11% of patients, respectively. We characterized 16 molecular groups, encompassing 86% of patients, using information from 21 genes, 6 cytogenetic events, and LOH at the TP53 and TET2 loci. Two residual groups defined by negative findings (molecularly not-otherwise specified, absence of recurrent drivers) comprised 14% of patients. The groups varied in size from 0.5% to 14% of patients and were associated with distinct clinical phenotypes and outcomes. The median bone marrow blast percentage across groups ranged from 1.5 to 10%, and the median overall survival from 0.9 to 8.2 years. We validated 5 well-characterized entities, added further evidence to support 3 previously reported subsets, and described 8 novel groups. The prognostic influence of bone marrow blasts depended on the genetic subtypes. Within genetic subgroups, therapy-related MDS and myelodysplastic/myeloproliferative neoplasms (MDS/MPN) had comparable clinical and outcome profiles to primary MDS. In conclusion, genetically-derived subgroups of MDS are clinically relevant and may inform future classification schemas and translational therapeutic research.

Efficacy and safety of luspatercept versus epoetin alfa in erythropoiesis-stimulating agent-naive, transfusion-dependent, lower-risk myelodysplastic syndromes (COMMANDS): interim analysis of a phase 3, open-label, randomised controlled trial.

BACKGROUND: Erythropoiesis-stimulating agents (ESAs) are the standard-of-care treatment for anaemia in most patients with lower-risk myelodysplastic syndromes but responses are limited and transient. Luspatercept promotes late-stage erythroid maturation and has shown durable clinical efficacy in patients with lower-risk myelodysplastic syndromes. In this study, we report the results of a prespecified interim analysis of luspatercept versus epoetin alfa for the treatment of anaemia due to lower-risk myelodysplastic syndromes in the phase 3 COMMANDS trial. METHODS: The phase 3, open-label, randomised controlled COMMANDS trial is being conducted at 142 sites in 26 countries. Eligible patients were aged 18 years or older, had a diagnosis of myelodysplastic syndromes of very low risk, low risk, or intermediate risk (per the Revised International Prognostic Scoring System), were ESA-naive, and required red blood cell transfusions (2-6 packed red blood cell units per 8 weeks for ≥8 weeks immediately before randomisation). Integrated response technology was used to randomly assign patients (1:1, block size 4) to luspatercept or epoetin alfa, stratified by baseline red blood cell transfusion burden (<4 units per 8 weeks vs ≥4 units per 8 weeks), endogenous serum erythropoietin concentration (≤200 U/L vs >200 to <500 U/L), and ring sideroblast status (positive vs negative). Luspatercept was administered subcutaneously once every 3 weeks starting at 1·0 mg/kg body weight with possible titration up to 1·75 mg/kg. Epoetin alfa was administered subcutaneously once a week starting at 450 IU/kg body weight with possible titration up to 1050 IU/kg (maximum permitted total dose of 80 000 IU). The primary endpoint was red blood cell transfusion independence for at least 12 weeks with a concurrent mean haemoglobin increase of at least 1·5 g/dL (weeks 1-24), assessed in the intention-to-treat population. Safety was assessed in patients who received at least one dose of study treatment. The COMMANDS trial was registered with ClinicalTrials.gov, NCT03682536 (active, not recruiting). FINDINGS: Between Jan 2, 2019 and Aug 31, 2022, 356 patients were randomly assigned to receive luspatercept (178 patients) or epoetin alfa (178 patients), comprising 198 (56%) men and 158 (44%) women (median age 74 years [IQR 69-80]). The interim efficacy analysis was done for 301 patients (147 in the luspatercept group and 154 in the epoetin alfa group) who completed 24 weeks of treatment or discontinued earlier. 86 (59%) of 147 patients in the luspatercept group and 48 (31%) of 154 patients in the epoetin alfa group reached the primary endpoint (common risk difference on response rate 26·6; 95% CI 15·8-37·4; p<0·0001). Median treatment exposure was longer for patients receiving luspatercept (42 weeks [IQR 20-73]) versus epoetin alfa (27 weeks [19-55]). The most frequently reported grade 3 or 4 treatment-emergent adverse events with luspatercept (≥3% patients) were hypertension, anaemia, dyspnoea, neutropenia, thrombocytopenia, pneumonia, COVID-19, myelodysplastic syndromes, and syncope; and with epoetin alfa were anaemia, pneumonia, neutropenia, hypertension, iron overload, COVID-19 pneumonia, and myelodysplastic syndromes. The most common suspected treatment-related adverse events in the luspatercept group (≥3% patients, with the most common event occurring in 5% patients) were fatigue, asthenia, nausea, dyspnoea, hypertension, and headache; and none (≥3% patients) in the epoetin alfa group. One death after diagnosis of acute myeloid leukaemia was considered to be related to luspatercept treatment (44 days on treatment). INTERPRETATION: In this interim analysis, luspatercept improved the rate at which red blood cell transfusion independence and increased haemoglobin were achieved compared with epoetin alfa in ESA-naive patients with lower-risk myelodysplastic syndromes. Long-term follow-up and additional data will be needed to confirm these results and further refine findings in other subgroups of patients with lower-risk myelodysplastic syndromes, including non-mutated SF3B1 or ring sideroblast-negative subgroups. FUNDING: Celgene and Acceleron Pharma.

SARS-CoV-2 infection and vaccination in patients with hairy-cell leukaemia.

Little is known of the course of COVID-19 and the antibody response to infection or vaccination in patients with hairy-cell leukaemia (HCL). Among a total of 58 HCL cases we studied in these regards, 37 unvaccinated patients, mostly enjoying a relatively long period free from anti-leukaemic treatment, developed COVID-19 between March 2020 and December 2021 with a usually favourable outcome (fatality rate: 5/37, 14%); however, active leukaemia, older age and more comorbidities were associated with a worse course. Postinfection (n = 11 cases) and postvaccination (n = 28) seroconversion consistently developed, except after recent anti-CD20 or venetoclax therapy, correlating with perivaccine B-cell count. Vaccination appeared to protect from severe COVID-19 in 11 patients with breakthrough infection.

SARS-CoV-2 infection in patients with chronic lymphocytic leukemia: The Italian Hematology Alliance on COVID-19 cohort.

COVID-19, the disease caused by SARS-CoV-2, is still afflicting thousands of people across the globe. Few studies on COVID-19 in chronic lymphocytic leukemia (CLL) are available. Here, we analyzed data from the CLL cohort of the Italian Hematology Alliance on COVID-19 (NCT04352556), which included 256 CLL patients enrolled between 25 February 2020 and 1 February 2021. Median age was 70 years (range 38-94) with male preponderance (60.1%). Approximately half of patients (n = 127) had received at least one line of therapy for CLL, including 108 (83.7%) who were on active treatment at the time of COVID-19 or received their last therapy within 12 months. Most patients (230/256, 89.9%) were symptomatic at COVID-19 diagnosis and the majority required hospitalization (n = 176). Overall, after a median follow-up of 42 days (IQR 24-96), case fatality rate was 30.1%, and it was 37.5% and 24.4% in the first (25 February 2020-22 June 2020) and second wave (23 June 2020-1 February 2021), respectively (p = 0.03). At multivariate analysis, male sex (HR 1.82, 95% CI 1.03-3.24, p = 0.04), age over than 70 years (HR 2.23, 95% CI 1.23-4.05, p = 0.01), any treatment for CLL given in the last 12 months (HR 1.72, 95% CI 1.04-2.84, p = 0.04) and COVID-19 severity (severe: HR 5.66, 95% CI 2.62-12.33, p < 0.0001; critical: HR 15.99, 95% CI 6.93-36.90, p < 0.0001) were independently associated with poor survival. In summary, we report a dismal COVID-related outcome in a significant fraction of CLL patients, that can be nicely predicted by clinical parameters.

Antitumour activity of trabectedin in myelodysplastic/myeloproliferative neoplasms.

BACKGROUND: Juvenile myelomonocytic leukaemia (JMML) and chronic myelomonocytic leukaemia (CMML) are myelodysplastic myeloproliferative (MDS/MPN) neoplasms with unfavourable prognosis and without effective chemotherapy treatment. Trabectedin is a DNA minor groove binder acting as a modulator of transcription and interfering with DNA repair mechanisms; it causes selective depletion of cells of the myelomonocytic lineage. We hypothesised that trabectedin might have an antitumour effect on MDS/MPN. METHODS: Malignant CD14+ monocytes and CD34+ haematopoietic progenitor cells were isolated from peripheral blood/bone marrow mononuclear cells. The inhibition of CFU-GM colonies and the apoptotic effect on CD14+ and CD34+ induced by trabectedin were evaluated. Trabectedin's effects were also investigated in vitro on THP-1, and in vitro and in vivo on MV-4-11 cell lines. RESULTS: On CMML/JMML cells, obtained from 20 patients with CMML and 13 patients with JMML, trabectedin - at concentration pharmacologically reasonable, 1-5 nM - strongly induced apoptosis and inhibition of growth of haematopoietic progenitors (CFU-GM). In these leukaemic cells, trabectedin downregulated the expression of genes belonging to the Rho GTPases pathway (RAS superfamily) having a critical role in cell growth and cytoskeletal dynamics. Its selective activity on myelomonocytic malignant cells was confirmed also on in vitro THP-1 cell line and on in vitro and in vivo MV-4-11 cell line models. CONCLUSIONS: Trabectedin could be good candidate for clinical studies in JMML/CMML patients.

A practical algorithm for acute myeloid leukaemia diagnosis following the updated 2022 classifications.

Disease classification of complex and heterogenous diseases, such as acute myeloid leukaemia (AML), is continuously updated to define diagnoses, appropriate treatments, and assist research and education. Recent availability of molecular profiling techniques further benefits the classification of AML. The World Health Organization (WHO) classification of haematolymphoid tumours and the International Consensus Classification of myeloid neoplasms and acute leukaemia from 2022 are two updated versions of the WHO 2016 classification. As a consequence, the European LeukemiaNet 2022 recommendations on the diagnosis and management of AML in adults have been also updated. The current review provides a practical interpretation of these guidelines to facilitate the diagnosis of AML and discusses genetic testing, disease genetic heterogeneity, and FLT3 mutations. We propose a practical algorithm for the speedy diagnosis of AML. Future classifications may need to incorporate gene mutation combinations to enable personalised treatment regimens in the management of patients with AML.

Using real-world evidence in haematology.

Most new drug approvals are based on data from large randomized clinical trials (RCTs). However, there are sometimes contradictory conclusions from seemingly similar trials and generalizability of conclusions from these trials is limited. These considerations explain, in part, the gap between conclusions from data of RCTs and those from registries termed real world data (RWD). Recently, real-world evidence (RWE) from RWD processed by artificial intelligence has received increasing attention. We describe the potential of using RWD in haematology concluding RWE from RWD may complement data from RCTs to support regulatory decisions.

Personalized Timing for Allogeneic Stem-Cell Transplantation in Hematologic Neoplasms: A Target Trial Emulation Approach Using Multistate Modeling and Microsimulation.

PURPOSE: Decision about the optimal timing of a treatment procedure in patients with hematologic neoplasms is critical, especially for cellular therapies (most including allogeneic hematopoietic stem-cell transplantation [HSCT]). In the absence of evidence from randomized trials, real-world observational data become beneficial to study the effect of the treatment timing. In this study, a framework to estimate the expected outcome after an intervention in a time-to-event scenario is developed, with the aim of optimizing the timing in a personalized manner. METHODS: Retrospective real-world data are leveraged to emulate a target trial for treatment timing using multistate modeling and microsimulation. This case study focuses on myelodysplastic syndromes, serving as a prototype for rare cancers characterized by a heterogeneous clinical course and complex genomic background. A cohort of 7,118 patients treated according to conventional available treatments/evidence across Europe and United States is analyzed. The primary clinical objective is to determine the ideal timing for HSCT, the only curative option for these patients. RESULTS: This analysis enabled us to identify the most appropriate time frames for HSCT on the basis of each patient's unique profile, defined by a combination relevant patients' characteristics. CONCLUSION: The developed methodology offers a structured framework to address a relevant clinical issue in the field of hematology. It makes several valuable contributions: (1) novel insights into how to develop decision models to identify the most favorable HSCT timing, (2) evidence to inform clinical decisions in a real-world context, and (3) the incorporation of complex information into decision making. This framework can be applied to provide medical insights for clinical issues that cannot be adequately addressed through randomized clinical trials.

MOSAIC: An Artificial Intelligence-Based Framework for Multimodal Analysis, Classification, and Personalized Prognostic Assessment in Rare Cancers.

PURPOSE: Rare cancers constitute over 20% of human neoplasms, often affecting patients with unmet medical needs. The development of effective classification and prognostication systems is crucial to improve the decision-making process and drive innovative treatment strategies. We have created and implemented MOSAIC, an artificial intelligence (AI)-based framework designed for multimodal analysis, classification, and personalized prognostic assessment in rare cancers. Clinical validation was performed on myelodysplastic syndrome (MDS), a rare hematologic cancer with clinical and genomic heterogeneities. METHODS: We analyzed 4,427 patients with MDS divided into training and validation cohorts. Deep learning methods were applied to integrate and impute clinical/genomic features. Clustering was performed by combining Uniform Manifold Approximation and Projection for Dimension Reduction + Hierarchical Density-Based Spatial Clustering of Applications with Noise (UMAP + HDBSCAN) methods, compared with the conventional Hierarchical Dirichlet Process (HDP). Linear and AI-based nonlinear approaches were compared for survival prediction. Explainable AI (Shapley Additive Explanations approach [SHAP]) and federated learning were used to improve the interpretation and the performance of the clinical models, integrating them into distributed infrastructure. RESULTS: UMAP + HDBSCAN clustering obtained a more granular patient stratification, achieving a higher average silhouette coefficient (0.16) with respect to HDP (0.01) and higher balanced accuracy in cluster classification by Random Forest (92.7% ± 1.3% and 85.8% ± 0.8%). AI methods for survival prediction outperform conventional statistical techniques and the reference prognostic tool for MDS. Nonlinear Gradient Boosting Survival stands in the internal (Concordance-Index [C-Index], 0.77; SD, 0.01) and external validation (C-Index, 0.74; SD, 0.02). SHAP analysis revealed that similar features drove patients' subgroups and outcomes in both training and validation cohorts. Federated implementation improved the accuracy of developed models. CONCLUSION: MOSAIC provides an explainable and robust framework to optimize classification and prognostic assessment of rare cancers. AI-based approaches demonstrated superior accuracy in capturing genomic similarities and providing individual prognostic information compared with conventional statistical methods. Its federated implementation ensures broad clinical application, guaranteeing high performance and data protection.

Toward a more patient-centered drug development process in clinical trials for patients with myelodysplastic syndromes/neoplasms (MDS): Practical considerations from the International Consortium for MDS (icMDS).

Notable treatment advances have been made in recent years for patients with myelodysplastic syndromes/neoplasms (MDS), and several new drugs are under development. For example, the emerging availability of oral MDS therapies holds the promise of improving patients' health-related quality of life (HRQoL). Within this rapidly evolving landscape, the inclusion of HRQoL and other patient-reported outcomes (PROs) is critical to inform the benefit/risk assessment of new therapies or to assess whether patients live longer and better, for what will likely remain a largely incurable disease. We provide practical considerations to support investigators in generating high-quality PRO data in future MDS trials. We first describe several challenges that are to be thoughtfully considered when designing an MDS-focused clinical trial with a PRO endpoint. We then discuss aspects related to the design of the study, including PRO assessment strategies. We also discuss statistical approaches illustrating the potential value of time-to-event analyses and their implications within the estimand framework. Finally, based on a literature review of MDS randomized controlled trials with a PRO endpoint, we note the PRO items that deserve special attention when reporting future MDS trial results. We hope these practical considerations will facilitate the generation of rigorous PRO data that can robustly inform MDS patient care and support treatment decision-making for this patient population.

Clinical and Genomic-Based Decision Support System to Define the Optimal Timing of Allogeneic Hematopoietic Stem-Cell Transplantation in Patients With Myelodysplastic Syndromes.

PURPOSE: Allogeneic hematopoietic stem-cell transplantation (HSCT) is the only potentially curative treatment for patients with myelodysplastic syndromes (MDS). Several issues must be considered when evaluating the benefits and risks of HSCT for patients with MDS, with the timing of transplantation being a crucial question. Here, we aimed to develop and validate a decision support system to define the optimal timing of HSCT for patients with MDS on the basis of clinical and genomic information as provided by the Molecular International Prognostic Scoring System (IPSS-M). PATIENTS AND METHODS: We studied a retrospective population of 7,118 patients, stratified into training and validation cohorts. A decision strategy was built to estimate the average survival over an 8-year time horizon (restricted mean survival time [RMST]) for each combination of clinical and genomic covariates and to determine the optimal transplantation policy by comparing different strategies. RESULTS: Under an IPSS-M based policy, patients with either low and moderate-low risk benefited from a delayed transplantation policy, whereas in those belonging to moderately high-, high- and very high-risk categories, immediate transplantation was associated with a prolonged life expectancy (RMST). Modeling decision analysis on IPSS-M versus conventional Revised IPSS (IPSS-R) changed the transplantation policy in a significant proportion of patients (15% of patient candidate to be immediately transplanted under an IPSS-R-based policy would benefit from a delayed strategy by IPSS-M, whereas 19% of candidates to delayed transplantation by IPSS-R would benefit from immediate HSCT by IPSS-M), resulting in a significant gain-in-life expectancy under an IPSS-M-based policy (P = .001). CONCLUSION: These results provide evidence for the clinical relevance of including genomic features into the transplantation decision making process, allowing personalizing the hazards and effectiveness of HSCT in patients with MDS.

Emerging Insights into Molecular Mechanisms of Inflammation in Myelodysplastic Syndromes.

Inflammation impacts human hematopoiesis across physiologic and pathologic conditions, as signals derived from the bone marrow microenvironment, such as pro-inflammatory cytokines and chemokines, have been shown to alter hematopoietic stem cell (HSCs) homeostasis. Dysregulated inflammation can skew HSC fate-related decisions, leading to aberrant hematopoiesis and potentially contributing to the pathogenesis of hematological disorders such as myelodysplastic syndromes (MDS). Recently, emerging studies have used single-cell sequencing and muti-omic approaches to investigate HSC cellular heterogeneity and gene expression in normal hematopoiesis as well as in myeloid malignancies. This review summarizes recent reports mechanistically dissecting the role of inflammatory signaling and innate immune response activation due to MDS progression. Furthermore, we highlight the growing importance of using multi-omic techniques, such as single-cell profiling and deconvolution methods, to unravel MDSs' heterogeneity. These approaches have provided valuable insights into the patterns of clonal evolution that drive MDS progression and have elucidated the impact of inflammation on the composition of the bone marrow immune microenvironment in MDS.

Opportunities and Challenges of Synthetic Data Generation in Oncology.

Widespread interest in artificial intelligence (AI) in health care has focused mainly on deductive systems that analyze available real-world data to discover patterns not otherwise visible. Generative adversarial network, a new type of inductive AI, has recently evolved to generate high-fidelity virtual synthetic data (SD) trained on relatively limited real-world information. The AI system is fed with a collection of real data, and it learns to generate new augmented data while maintaining the general characteristics of the original data set. The use of SD to enhance clinical research and protect patient privacy has drawn a lot of interest in medicine and in the complex field of oncology. This article summarizes the main characteristics of this innovative technology and critically discusses how it can be used to accelerate data access for secondary purposes, providing an overview of the opportunities and challenges of SD generation for clinical cancer research and health care.

Applicability of 2022 classifications of acute myeloid leukemia in the real-world setting.

The increasing knowledge of molecular genetics of acute myeloid leukemia (AML) necessitated the update of previous diagnostic and prognostic schemes, which resulted in the development of the World Health Organization (WHO), the International Consensus Classification (ICC), and the new European LeukemiaNet (ELN) recommendations in 2022. We aimed to provide a real-world application of the new models, unravel differences and similarities, and test their implementation in clinical AML diagnosis. A total of 1001 patients diagnosed with AML were reclassified based on the new schemes. The overall diagnostic changes between the WHO 2016 and the WHO 2022 and ICC classifications were 22.8% and 23.7%, respectively, with a 13.1% difference in patients' distribution between ICC and WHO 2022. The 2022 ICC "not otherwise specified" and WHO "defined by differentiation" AML category sizes shrank when compared with that in WHO 2016 (24.1% and 26.8% respectively, vs 38.7%), particularly because of an expansion of the myelodysplasia (MDS)-related group. Of 397 patients with a MDS-related AML according to the ICC, 55.9% were defined by the presence of a MDS-related karyotype. The overall restratification between ELN 2017 and ELN 2022 was 12.9%. The 2022 AML classifications led to a significant improvement of diagnostic schemes. In the real-world setting, conventional cytogenetics, usually rapidly available and less expensive than molecular characterization, stratified 56% of secondary AML, still maintaining a powerful diagnostic role. Considering the similarities between WHO and ICC diagnostic schemes, a tentative scheme to generate a unified model is desirable.

Synthetic Data Generation by Artificial Intelligence to Accelerate Research and Precision Medicine in Hematology.

PURPOSE: Synthetic data are artificial data generated without including any real patient information by an algorithm trained to learn the characteristics of a real source data set and became widely used to accelerate research in life sciences. We aimed to (1) apply generative artificial intelligence to build synthetic data in different hematologic neoplasms; (2) develop a synthetic validation framework to assess data fidelity and privacy preservability; and (3) test the capability of synthetic data to accelerate clinical/translational research in hematology. METHODS: A conditional generative adversarial network architecture was implemented to generate synthetic data. Use cases were myelodysplastic syndromes (MDS) and AML: 7,133 patients were included. A fully explainable validation framework was created to assess fidelity and privacy preservability of synthetic data. RESULTS: We generated MDS/AML synthetic cohorts (including information on clinical features, genomics, treatment, and outcomes) with high fidelity and privacy performances. This technology allowed resolution of lack/incomplete information and data augmentation. We then assessed the potential value of synthetic data on accelerating research in hematology. Starting from 944 patients with MDS available since 2014, we generated a 300% augmented synthetic cohort and anticipated the development of molecular classification and molecular scoring system obtained many years later from 2,043 to 2,957 real patients, respectively. Moreover, starting from 187 MDS treated with luspatercept into a clinical trial, we generated a synthetic cohort that recapitulated all the clinical end points of the study. Finally, we developed a website to enable clinicians generating high-quality synthetic data from an existing biobank of real patients. CONCLUSION: Synthetic data mimic real clinical-genomic features and outcomes, and anonymize patient information. The implementation of this technology allows to increase the scientific use and value of real data, thus accelerating precision medicine in hematology and the conduction of clinical trials.

Real-World Validation of Molecular International Prognostic Scoring System for Myelodysplastic Syndromes.

PURPOSE: Myelodysplastic syndromes (MDS) are heterogeneous myeloid neoplasms in which a risk-adapted treatment strategy is needed. Recently, a new clinical-molecular prognostic model, the Molecular International Prognostic Scoring System (IPSS-M) was proposed to improve the prediction of clinical outcome of the currently available tool (Revised International Prognostic Scoring System [IPSS-R]). We aimed to provide an extensive validation of IPSS-M. METHODS: A total of 2,876 patients with primary MDS from the GenoMed4All consortium were retrospectively analyzed. RESULTS: IPSS-M improved prognostic discrimination across all clinical end points with respect to IPSS-R (concordance was 0.81 v 0.74 for overall survival and 0.89 v 0.76 for leukemia-free survival, respectively). This was true even in those patients without detectable gene mutations. Compared with the IPSS-R based stratification, the IPSS-M risk group changed in 46% of patients (23.6% and 22.4% of subjects were upstaged and downstaged, respectively).In patients treated with hematopoietic stem cell transplantation (HSCT), IPSS-M significantly improved the prediction of the risk of disease relapse and the probability of post-transplantation survival versus IPSS-R (concordance was 0.76 v 0.60 for overall survival and 0.89 v 0.70 for probability of relapse, respectively). In high-risk patients treated with hypomethylating agents (HMA), IPSS-M failed to stratify individual probability of response; response duration and probability of survival were inversely related to IPSS-M risk.Finally, we tested the accuracy in predicting IPSS-M when molecular information was missed and we defined a minimum set of 15 relevant genes associated with high performance of the score. CONCLUSION: IPSS-M improves MDS prognostication and might result in a more effective selection of candidates to HSCT. Additional factors other than gene mutations can be involved in determining HMA sensitivity. The definition of a minimum set of relevant genes may facilitate the clinical implementation of the score.

Generative Adversarial Networks in Brain Imaging: A Narrative Review.

Artificial intelligence (AI) is expected to have a major effect on radiology as it demonstrated remarkable progress in many clinical tasks, mostly regarding the detection, segmentation, classification, monitoring, and prediction of diseases. Generative Adversarial Networks have been proposed as one of the most exciting applications of deep learning in radiology. GANs are a new approach to deep learning that leverages adversarial learning to tackle a wide array of computer vision challenges. Brain radiology was one of the first fields where GANs found their application. In neuroradiology, indeed, GANs open unexplored scenarios, allowing new processes such as image-to-image and cross-modality synthesis, image reconstruction, image segmentation, image synthesis, data augmentation, disease progression models, and brain decoding. In this narrative review, we will provide an introduction to GANs in brain imaging, discussing the clinical potential of GANs, future clinical applications, as well as pitfalls that radiologists should be aware of.