Aim Asymptomatic deep vein thrombosis (DVT) diagnosed with compression ultrasound (CUS) is a common endpoint in trials assessing the efficacy of anticoagulants to prevent venous thromboembolism (VTE), but the relationship of asymptomatic thrombus to mortality remains uncertain. Methods In the APEX trial (ClinicalTrials.gov: NCT01583218), 7,513 acutely ill hospitalized medical patients were randomly assigned to extended-duration betrixaban (35–42 days) or enoxaparin (10 ± 4 days). Asymptomatic DVT was assessed once with CUS between day 32 and 47, and mortality was assessed through 77 days. Results A total of 309 asymptomatic DVTs were detected through CUS. Of these, 133 (4.27%) subjects were in the betrixaban group, and 176 (5.55%) subjects were in the enoxaparin group (relative risk = 0.77, 95% confidence interval [CI] = 0.62–0.97, p = 0.025, number needed to treat = 79). With respect to all-cause mortality due to cardiovascular diseases, non-cardiovascular diseases and unknown causes, the number of the deaths was 5 (1.67%), 4 (1.34%) and 1 (0.33%) in the asymptomatic DVT group and 25 (0.42%), 33 (0.56%) and 11 (0.19%) in the no DVT group, respectively. Subjects with an asymptomatic DVT had an almost threefold increase in the risk of all-cause mortality compared with subjects without DVT (hazard ratio = 2.87, 95% CI = 1.48–5.57, p = 0.001). A positive linear trend was observed between greater thrombus burden and mortality during the follow-up (p = 0.019). Conclusion Asymptomatic DVT was associated with approximately threefold increased risk of short-term all-cause mortality in patients hospitalized with an acute medical illness within the prior 77 days. A positive linear trend was observed between greater thrombus burden and mortality during the follow-up.

Background The identification of acutely ill patients at high risk for venous thromboembolism (VTE) may be determined clinically or by use of integer‐based scoring systems. These scores demonstrated modest performance in external data sets. Objectives To evaluate the performance of machine learning models compared to the IMPROVE score. Methods The APEX trial randomized 7513 acutely medically ill patients to extended duration betrixaban vs. enoxaparin. Including 68 variables, a super learner model (ML) was built to predict VTE by combining estimates from 5 families of candidate models. A “reduced” model (rML) was also developed using 16 variables that were thought, a priori, to be associated with VTE. The IMPROVE score was calculated for each patient. Model performance was assessed by discrimination and calibration to predict a composite VTE end point. The frequency of predicted risks of VTE were plotted and divided into tertiles. VTE risks were compared across tertiles. Results The ML and rML algorithms outperformed the IMPROVE score in predicting VTE (c‐statistic: 0.69, 0.68 and 0.59, respectively). The Hosmer‐Lemeshow goodness‐of‐fit P‐value was 0.06 for ML, 0.44 for rML, and <0.001 for the IMPROVE score. The observed event rate in the lowest tertile was 2.5%, 4.8% in tertile 2, and 11.4% in the highest tertile. Patients in the highest tertile of VTE risk had a 5‐fold increase in odds of VTE compared to the lowest tertile. Conclusion The super learner algorithms improved discrimination and calibration compared to the IMPROVE score for predicting VTE in acute medically ill patients.

No abstract