COVID-19, as a disease involving the endothelium of multiple organs, is characterized by high mortality rates among hospitalized patients. Patients with hematological malignancies are particularly at risk of an unfavorable course of COVID-19. The endothelial activation and stress index (EASIX) score has been used as a simple predictor of overall survival (OS) in specific groups of hematological cancer patients. EASIX, as a biomarker of endothelial dysfunction, might play a prognostic role in patients with COVID-19. Here, we performed a comprehensive retrospective analysis of the EASIX score in 523 hospitalized COVID-19 patients with or without coexisting hematological cancer. Hematological cancer COVID-19 patients had higher EASIX scores compared to the overall population with COVID-19. In hematological patients, EASIX was a strong predictor of the occurrence of sepsis during COVID-19. Our findings demonstrated EASIX as a strong predictor of intensive care unit admission, in-hospital mortality, the occurrence of acute renal failure and the need for hemodialysis, both in hematological and non-hematological COVID-19 patients. Patients with a high EASIX score on COVID-19 diagnosis had significantly inferior OS compared to patients with low EASIX. We showed for the first time that EASIX might serve as a simple, universal prognostic tool of OS in both hematological and non-hematological COVID-19 patients.

With the incorporation of effective therapies for myelofibrosis (MF), accurately predicting outcomes after allogeneic hematopoietic cell transplantation (allo-HCT) is crucial for determining the optimal timing for this procedure. Using data from 5183 patients with MF who underwent first allo-HCT between 2005 and 2020 at European Society for Blood and Marrow Transplantation centers, we examined different machine learning (ML) models to predict overall survival after transplant. The cohort was divided into a training set (75%) and a test set (25%) for model validation. A random survival forests (RSF) model was developed based on 10 variables: patient age, comorbidity index, performance status, blood blasts, hemoglobin, leukocytes, platelets, donor type, conditioning intensity, and graft-versus-host disease prophylaxis. Its performance was compared with a 4-level Cox regression–based score and other ML-based models derived from the same data set, and with the Center for International Blood and Marrow Transplant Research score. The RSF outperformed all comparators, achieving better concordance indices across both primary and postessential thrombocythemia/polycythemia vera MF subgroups. The robustness and generalizability of the RSF model was confirmed by Akaike information criterion and time-dependent receiver operating characteristic area under the curve metrics in both sets. Although all models were prognostic for nonrelapse mortality, the RSF provided better curve separation, effectively identifying a high-risk group comprising 25% of patients. In conclusion, ML enhances risk stratification in patients with MF undergoing allo-HCT, paving the way for personalized medicine. A web application (https://gemfin.click/ebmt) based on the RSF model offers a practical tool to identify patients at high risk for poor transplantation outcomes, supporting informed treatment decisions and advancing individualized care.

In patients with myelodysplastic syndrome (MDS), higher revised International Prognostic Scoring System (IPSS-R) scores at transplant are associated with worse transplant outcome and, thus, lowering IPSS-R scores by therapeutic intervention before transplantation may seem beneficial. However, there is no evidence, to date, to support this approach. In a retrospective analysis, a total of 1482 patients with MDS with sufficient data to calculate IPSS-R score at diagnosis and at time of transplantation were selected from the European Society for Blood and Marrow Transplantation transplant registry and analyzed for transplant outcome in a multivariable Cox model including IPSS-R score at diagnosis, treatment intervention, change in IPSS-R score before transplant, and several patient and transplant variables. Transplant outcome was unaffected by IPSS-R score change in untreated patients and moderately superior in patients treated with chemotherapy with improved IPSS-R score at transplant. Improved IPSS-R score after hypomethylating agents (HMAs) or other therapies showed no beneficial effect. However, when IPSS-R score progressed after chemotherapy, HMAs, or other therapies, transplant outcome was worse than without any prior treatment. Similar results were found when reduction or increase in bone marrow (BM) blasts between diagnosis and transplantation was considered. The results show a limited benefit of IPSS-R score downstaging or reduction of BM blasts after chemotherapy and no benefit for HMAs or other treatments and thus question the role of prior therapy in patients with MDS scheduled for transplantation. The model-based survival estimates should help inform decision-making for both doctors and patients.

For patients with myelodysplastic neoplasm/syndrome (MDS), allogeneic hematopoietic cell transplantation (allo-HCT) represents the only potentially curative treatment, capable of eradicating disease-related mutant hematopoietic cells and establishing normal donor hematopoiesis. Biologic-assignment clinical trials have indicated that in eligible patients, allo-HCT is associated with superior clinical outcomes compared with nontransplant therapy. However, this therapeutic option is only available to a subset of patients, and the outcome is influenced by multiple factors inherent to the patient, the MDS subtype, and the allo-HCT procedure itself. In 2017, the European Society for Blood and Marrow Transplantation (EBMT) published recommendations for allo-HCT in MDS to guide practical decision making. In the contemporary era, genomic profiling has become routine clinical practice in many centers, and the most recent classification systems include MDS entities that are defined by genetic abnormalities. In particular, the molecular International Prognostic Scoring System offers more precise prognostication across all clinical end points and currently represents the standard tool for estimating patient survival in the absence of disease-modifying treatment. Evidence from multiple sources increasingly indicates that allo-HCT should be considered at the time of diagnosis in all eligible patients with MDS. Therefore, genomic profiling for somatic mutations and testing for germ line predisposition variants are integral to determining a patient’s eligibility for transplantation. Although all patients with higher-risk MDS are potential candidates for immediate transplantation, a subset of those with lower-risk MDS may also derive benefit from this procedure at an earlier disease stage. Comprehensive recommendations on behalf of an expert international panel for clinical practice and future clinical studies of relevance are presented.