Predictors of thrombosis and bleeding in 1613 myelofibrosis patients from the Spanish Registry of Myelofibrosis.

Available data have proved insufficient to develop consensus recommendations on the prevention of thrombosis and bleeding in myelofibrosis (MF). We evaluated the incidence and risk factors of vascular complications in 1613 patients from the Spanish Myelofibrosis Registry. Over a total of 6981 patient-years at risk, 6.4% of the study population had at least one thrombotic event after MF diagnosis, amounting to an incidence rate of 1.65 per 100 patient-years. Prior history of thrombosis, the JAK2 mutation, and the intermediate-2/high-risk International Prognostic Scoring System (IPSS) categories conferred an increased thrombotic risk after adjustment for the risk-modifying effect of anti-thrombotic and cytoreductive treatments. History of thrombosis and the JAK2 mutation allowed us to pinpoint a group of patients at higher risk of early thrombosis. No decreased incidence of thrombosis was observed while patients were on anti-thrombotic or cytoreductive treatment. An increased risk of venous thrombosis was found during treatment with immunomodulatory agents. A total of 5.3% of patients had at least one episode of major bleeding, resulting in an incidence rate of 1.5 events per 100 patient-years. Patients in the intermediate-2/high-risk IPSS categories treated with anti-coagulants had an almost sevenfold increased risk of major bleeding. These findings should prove useful for guiding decision-making in clinical practice.

Machine Learning Improves Risk Stratification in Myelofibrosis: An Analysis of the Spanish Registry of Myelofibrosis.

Myelofibrosis (MF) is a myeloproliferative neoplasm (MPN) with heterogeneous clinical course. Allogeneic hematopoietic cell transplantation remains the only curative therapy, but its morbidity and mortality require careful candidate selection. Therefore, accurate disease risk prognostication is critical for treatment decision-making. We obtained registry data from patients diagnosed with MF in 60 Spanish institutions (N = 1386). These were randomly divided into a training set (80%) and a test set (20%). A machine learning (ML) technique (random forest) was used to model overall survival (OS) and leukemia-free survival (LFS) in the training set, and the results were validated in the test set. We derived the AIPSS-MF (Artificial Intelligence Prognostic Scoring System for Myelofibrosis) model, which was based on 8 clinical variables at diagnosis and achieved high accuracy in predicting OS (training set c-index, 0.750; test set c-index, 0.744) and LFS (training set c-index, 0.697; test set c-index, 0.703). No improvement was obtained with the inclusion of MPN driver mutations in the model. We were unable to adequately assess the potential benefit of including adverse cytogenetics or high-risk mutations due to the lack of these data in many patients. AIPSS-MF was superior to the IPSS regardless of MF subtype and age range and outperformed the MYSEC-PM in patients with secondary MF. In conclusion, we have developed a prediction model based exclusively on clinical variables that provides individualized prognostic estimates in patients with primary and secondary MF. The use of AIPSS-MF in combination with predictive models that incorporate genetic information may improve disease risk stratification.

Clinico-biological characteristics of patients with myelofibrosis: an analysis of 1,000 cases from the Spanish Registry of Myelofibrosis. / Características clínico-biológicas de los pacientes con mielofibrosis: un análisis de 1.000 casos del Registro Español de Mielofibrosis.

BACKGROUND AND OBJECTIVE MYELOFIBROSIS: is an infrequent chronic myeloproliferative neoplasm. We aimed to describe the clinico-biological characteristics, treatment, and evolutive course of myelofibrosis patients in Spain. MATERIAL AND METHODS: A total of 1,000 patients from the Spanish Registry of Myelofibrosis diagnosed with primary (n=641) or secondary (n=359) myelofibrosis were analysed. RESULTS: Median age was 68 years. The frequency of constitutional symptoms, moderate to severe anaemia (Hb<10g/dL), and symptomatic splenomegaly was 35%, 36%, and 17%, respectively. The rate of thrombosis and haemorrhage was 1.96 and 1.6 events per 100 patient-years, respectively. The cumulative incidence of leukaemia at 10 years was 15%. The most frequent therapies for the anaemia were the erythropoiesis stimulating agents and danazol. From 2010, a progressive increase in the use of ruxolitinib was noticed. A total of 7.5% of patients were transplanted. During the observation period, 42% of patients died mainly due to the clinical deterioration caused by myelofibrosis or leukaemic transformation. The median survival of the series was 5.7 years. Four different risk categories were identified by the IPSS: median survival was not reached in the low risk group and was 8.8 years, 5.3 years, and 2.8 years in the intermediate-1, intermediate-2, and high-risk groups, respectively. CONCLUSIONS: Myelofibrosis is a disabling condition mainly affecting elderly people. Its treatment is mostly driven by symptom control. Despite its clinical heterogeneity, several prognostic models are useful to select candidates for transplantation.