Search

The International Prognostic Score of thrombosis in Essential Thrombocythemia (IPSET-thrombosis) and its revised version have been proposed to guide thrombosis prevention strategies. We evaluated both classifications to prognosticate thrombosis in 1366 contemporary essential thrombocythemia (ET) patients prospectively followed from the Spanish Registry of ET. The cumulative incidence of thrombosis at 10 years, taking death as a competing risk, was 11.4%. The risk of thrombosis was significantly higher in the high-risk IPSET-thrombosis and high-risk revised IPSET-thrombosis, but no differences were observed among the lower risk categories. Patients allocated in high-risk IPSET-thrombosis (subdistribution hazard ratios [SHR], 3.7 [95% confidence interval, CI, 1.6-8.7]) and high-risk revised IPSET-thrombosis (SHR, 3.2 [95% CI, 1.4-7.45]) showed an increased risk of arterial thrombosis, whereas both scoring systems failed to predict venous thrombosis. The incidence rate of thrombosis in intermediate risk revised IPSET-thrombosis (aged >60 years, JAK2-negative, and no history of thrombosis) was very low regardless of the treatment administered (0.9% and 0% per year with and without cytoreduction, respectively). Dynamic application of the revised IPSET-thrombosis showed a low rate of thrombosis when patients without history of prior thrombosis switched to a higher risk category after reaching 60 years of age. In conclusion, IPSET-thrombosis scores are useful for identifying patients at high risk of arterial thrombosis, whereas they fail to predict venous thrombosis. Controlled studies are needed to determine the appropriate treatment of ET patients assigned to the non-high-risk categories.

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.