D-dimer levels and risk of recurrence following provoked venous thromboembolism: findings from the RIETE registry.

BACKGROUND: Patients with venous thromboembolism (VTE) secondary to transient risk factors may develop VTE recurrences after discontinuing anticoagulation. Identifying at-risk patients could help to guide the duration of therapy. METHODS: We used the RIETE database to assess the prognostic value of d-dimer testing after discontinuing anticoagulation to identify patients at increased risk for recurrences. Transient risk factors were classified as major (postoperative) or minor (pregnancy, oestrogen use, immobilization or recent travel). RESULTS: In December 2018, 1655 VTE patients with transient risk factors (major 460, minor 1195) underwent d-dimer measurements after discontinuing anticoagulation. Amongst patients with major risk factors, the recurrence rate was 5.74 (95% CI: 3.19-9.57) events per 100 patient-years in those with raised d-dimer levels and 2.68 (95% CI: 1.45-4.56) in those with normal levels. Amongst patients with minor risk factors, the rates were 7.79 (95% CI: 5.71-10.4) and 3.34 (95% CI: 2.39-4.53), respectively. Patients with major risk factors and raised d-dimer levels (n = 171) had a nonsignificantly higher rate of recurrences (hazard ratio [HR]: 2.14; 95% CI: 0.96-4.79) than those with normal levels. Patients with minor risk factors and raised d-dimer levels (n = 382) had a higher rate of recurrences (HR: 2.34; 95% CI: 1.51-3.63) than those with normal levels. On multivariate analysis, raised d-dimers (HR: 1.74; 95% CI: 1.09-2.77) were associated with an increased risk for recurrences in patients with minor risk factors, not in those with major risk factors. CONCLUSIONS: Patients with raised d-dimer levels after discontinuing anticoagulant therapy for VTE provoked by a minor transient risk factor were at an increased risk for recurrences.

Development of a predictive model of venous thromboembolism recurrence in anticoagulated cancer patients using machine learning.

INTRODUCTION: Patients with cancer and venous thromboembolism (VTE) show a high risk of VTE recurrence during anticoagulant treatment. This study aimed to develop a predictive model to assess the risk of VTE recurrence within 6 months at the moment of primary VTE diagnosis in these patients. MATERIALS AND METHODS: Using the EHRead® technology, based on Natural Language Processing (NLP) and machine learning (ML), the unstructured data in electronic health records from 9 Spanish hospitals between 2014 and 2018 were extracted. Both clinically- and ML-driven feature selection were performed to identify predictors for VTE recurrence. Logistic regression (LR), decision tree (DT), and random forest (RF) algorithms were used to train different prediction models, which were subsequently validated in a hold-out data set. RESULTS: A total of 16,407 anticoagulated cancer patients with diagnosis of VTE were identified (54.4 % male and median age 70). Deep vein thrombosis, pulmonary embolism and metastases were observed in 67.2 %, 26.6 %, and 47.7 % of the patients, respectively. During the study follow-up, 11.4 % of the patients developed a recurrent VTE, being more frequent in patients with lung cancer. Feature selection and model training based on ML identified primary pulmonary embolism, deep vein thrombosis, metastasis, adenocarcinoma, hemoglobin and serum creatinine levels, platelet and leukocyte count, family history of VTE, and patients' age as predictors of VTE recurrence within 6 months of VTE diagnosis. The LR model had an AUC-ROC (95 % CI) of 0.66 (0.61, 0.70), the DT of 0.69 (0.65, 0.72) and the RF of 0.68 (0.63, 0.72). CONCLUSIONS: This is the first ML-based predictive model designed to predict 6-months VTE recurrence in patients with cancer. These results hold great potential to assist clinicians to identify the high-risk patients and improve their clinical management.

Metabolic Syndrome Increases Risk of Venous Thromboembolism Recurrence after Acute Pulmonary Embolism.

Rationale: Metabolic syndrome (MetS), the clinical clustering of hypertension, dyslipidemia, insulin resistance, and abdominal obesity, has been associated with a prothrombotic and hypofibrinolytic state, although data linking MetS with venous thromboembolism (VTE) remain limited.Objectives: The aim of this study was to measure the prevalence of MetS in patients with pulmonary embolism (PE) across a large population and to examine its impact on VTE recurrence.Methods: This was a retrospective, population-based analysis using deidentified information from a large statewide database, the Indiana Network for Patient Care. All patients with an International Classification of Diseases-defined diagnosis of PE from 2004 to 2017 were included. We measured the frequency with which patients with PE carried a comorbid diagnosis of each MetS component. Multiple logistic regression analysis was performed with VTE recurrence as the dependent variable to test the independent effect of MetS diagnosis, with a statistical model using a directed acyclic graph to account for potential confounders and mediators. Kaplan-Meier curves were constructed to compare rates of VTE recurrence over time based on the presence or absence of MetS and its individual components.Results: A total of 72,936 patients were included in this analysis. The most common MetS component was hypertension with a prevalence of 59%, followed by hyperlipidemia (41%), diabetes mellitus (24%), and obesity (22%). Of these patients, 69% had at least one comorbid component of MetS. The overall incidence of VTE recurrence was 17%, increasing stepwise with each additional MetS component and ranging from 6% in patients with zero components to 37% in those with all four. Logistic regression analysis yielded an adjusted odds ratio of 3.03 (95% CI, 2.90-3.16) for the effect of composite diagnosis requiring at least three of the four components of MetS diagnosis on VTE recurrence.Conclusions: The presence of comorbid MetS in patients with PE is associated with significantly higher rates of VTE recurrence, supporting the importance of recognizing these risk factors and initiating appropriate therapies to reduce recurrence risk.

Treatment of cancer-associated venous thromboembolism: 12-month outcomes of the placebo versus rivaroxaban randomization of the SELECT-D Trial (SELECT-D: 12m).

BACKGROUND: The Anticoagulation Therapy in Selected Cancer Patients at Risk of Recurrence of Venous Thromboembolism (SELECT-D) trial demonstrated reduction in recurrent venous thromboembolism (VTE) but increased bleeding with rivaroxaban compared with dalteparin for treatment of acute VTE in cancer patients, at 6 months. Uncertainty remains around optimal duration of anticoagulation. OBJECTIVES: To assess VTE recurrence and bleeding, with anticoagulation or not, beyond 6 months. PATIENTS/METHODS: In SELECT-D, after 6 months of trial treatment for VTE, patients with active cancer and residual deep vein thrombosis (RDVT) or index pulmonary embolism (PE) were eligible for randomization to a further 6 months of rivaroxaban or placebo. Patients with no RDVT stopped anticoagulation. Primary outcome was VTE recurrence at 12 months. The second randomization closed prematurely because of low recruitment when 92 of the planned 300 patients were recruited. RESULTS: Ninety-two of 136 eligible patients were randomized to rivaroxaban or placebo. The cumulative VTE recurrence after 6 months from the second randomization was 14% with placebo and 4% with rivaroxaban (hazard ratio, 0.32; 95% confidence interval [CI], 0.06-1.58). The major and clinically relevant non-major bleeding rates were 0% and 0% with placebo; and 5% (95% CI, 1-18) and 4% (95% CI, 1-17) with rivaroxaban. In an exploratory analysis, 7 (15%) of 46 placebo patients with RDVT or an index PE experienced recurrent VTE compared to none in the 35 patients in the RDVT-negative cohort (P = .03). CONCLUSION: The SELECT-D trial was underpowered to detect a statistically significant reduction in recurrent VTE with extended anticoagulation. The absence of RDVT and/or index PE, defined a population at low risk of recurrence.