Anticoagulant therapy in patients with congenital FXI deficiency.

The bleeding phenotype of factor XI (FXI) deficiency is unpredictable. Bleeding is usually mild and mostly occurs after injury. Although FXI deficiency renders antithrombotic protection, some patients might eventually develop thrombosis or atrial fibrillation, requiring anticoagulant therapy. There is almost no evidence on the bleeding risk in this scenario. Our retrospective study of 269 white FXI-deficient subjects (1995-2021) identified 15 cases requiring anticoagulation. They harbored 8 different F11 variants, mainly in heterozygosis (1 case was homozygote), and had mild to moderate deficiency (FXI:C: 20% to 70%). Two subjects (13.3%) had bleeding history before anticoagulation. Atrial fibrillation was the main indication (12/15; 80%). Fourteen patients started therapy with vitamin K antagonists (VKA), but 4 subjects were on direct oral anticoagulants (DOACs) at the end of follow-up. Over >1000 months of anticoagulation, 2 mild bleeding episodes in 2 patients (13.3%, 95% confidence interval: 3.7% to 37.9%) were recorded. No major/fatal events were reported. "Pre-post" bleeding localization and severity did not change despite treatment. On VKA, drug dosing and management were also standard, unaltered by FXI deficiency. We provide the largest description of anticoagulant use in FXI deficiency, and the first cases receiving DOACs. Although further studies are needed, our observations suggest that moderate FXI deficiency does not interfere with anticoagulant management nor bleeding risk.

Personalized Survival Prediction of Patients With Acute Myeloblastic Leukemia Using Gene Expression Profiling.

Acute Myeloid Leukemia (AML) is a heterogeneous neoplasm characterized by cytogenetic and molecular alterations that drive patient prognosis. Currently established risk stratification guidelines show a moderate predictive accuracy, and newer tools that integrate multiple molecular variables have proven to provide better results. In this report, we aimed to create a new machine learning model of AML survival using gene expression data. We used gene expression data from two publicly available cohorts in order to create and validate a random forest predictor of survival, which we named ST-123. The most important variables in the model were age and the expression of KDM5B and LAPTM4B, two genes previously associated with the biology and prognostication of myeloid neoplasms. This classifier achieved high concordance indexes in the training and validation sets (0.7228 and 0.6988, respectively), and predictions were particularly accurate in patients at the highest risk of death. Additionally, ST-123 provided significant prognostic improvements in patients with high-risk mutations. Our results indicate that survival of patients with AML can be predicted to a great extent by applying machine learning tools to transcriptomic data, and that such predictions are particularly precise among patients with high-risk mutations.