Venous thromboembolism in COVID-19 patients and prediction model: a multicenter cohort study

Abstract

Background Patients with COVID-19 infection are commonly reported to have an increased risk of venous thrombosis. The choice of anti-thrombotic agents and doses are currently being studied in randomized controlled trials and retrospective studies. There exists a need for individualized risk stratification of venous thromboembolism (VTE) to assist clinicians in decision-making on anticoagulation. We sought to identify the risk factors of VTE in COVID-19 patients, which could help physicians in the prevention, early identification, and management of VTE in hospitalized COVID-19 patients and improve clinical outcomes in these patients. Method This is a multicenter, retrospective database of four main health systems in Southeast Michigan, United States. We compiled comprehensive data for adult COVID-19 patients who were admitted between 1st March 2020 and 31st December 2020. Four models, including the random forest, multiple logistic regression, multilinear regression, and decision trees, were built on the primary outcome of in-hospital acute deep vein thrombosis (DVT) and pulmonary embolism (PE) and tested for performance. The study also reported hospital length of stay (LOS) and intensive care unit (ICU) LOS in the VTE and the non-VTE patients. Four models were assessed using the area under the receiver operating characteristic curve and confusion matrix. Results The cohort included 3531 admissions, 3526 had discharge diagnoses, and 6.68% of patients developed acute VTE (N = 236). VTE group had a longer hospital and ICU LOS than the non-VTE group (hospital LOS 12.2 days vs. 8.8 days, p < 0.001; ICU LOS 3.8 days vs. 1.9 days, p < 0.001). 9.8% of patients in the VTE group required more advanced oxygen support, compared to 2.7% of patients in the non-VTE group (p < 0.001). Among all four models, the random forest model had the best performance. The model suggested that blood pressure, electrolytes, renal function, hepatic enzymes, and inflammatory markers were predictors for in-hospital VTE in COVID-19 patients. Conclusions Patients with COVID-19 have a high risk for VTE, and patients who developed VTE had a prolonged hospital and ICU stay. This random forest prediction model for VTE in COVID-19 patients identifies predictors which could aid physicians in making a clinical judgment on empirical dosages of anticoagulation.

Association of Clinical and Laboratory Findings in COVID-19 Patients with Thromboembolic Complications

“…Regarding the small sample size, further analyses on larger sample sizes are required to determine the predictors of thrombosis in COVID-19. Interestingly, based on logistic and linear regression models in a multicenter large cohort study on 3531 patients, CRP and LDH were unable to predict thromboembolism in COVID-19, which is in accordance with the present study (20).…”

“…The variables, including mean age, mean day of hospitalization, PaO 2 saturation, levels of CRP and ESR, and lymphocyte count, showed no significant differences between the thrombotic and non-thrombotic groups. Parallel to this finding, Lee et al also reported no significant difference in oxygen saturation between thrombotic and nonthrombotic COVID-19 patients (20). Riyahi et al conducted a multicenter study on 413 COVID-19 patients and found pulmonary embolism in 25% of hospitalized patients (11).…”

“…In a cohort study by Lee et al, the CRP level was suggested as an indicator of VTE in COVID-19 patients. They also reported that hospitalization length, lymphocyte count, and platelet count were associated with VTE in COVID-19 patients (20). The contradictions between the studies might be due to the different sample sizes.…”

SARS-COV-ATE risk assessment model for arterial thromboembolism in COVID-19

“…This is a retrospective, multi-institutional (one quaternary care and three community hospitals) cohort study of patients older than 18 years old admitted with polymerase chain reaction proven SARS-CoV-2 infection between March 1, 2020, and September 5, 2021. Data were analyzed from the Southeast Michigan COVID-19 Consortium Registry Database, a multi-institutional database of four main health systems in southeast Michigan, United States, including Henry Ford Health System, Beaumont Health System, Trinity Health System, and Wayne State University 15 , 16 . Data from Trinity and Henry Ford Health were used for this particular study.…”

Strength of Anticoagulation in Moderate to Severe COVID-19 Illness: In Medio Stat Virtus?

“…30 Similarly, Lee et al also evidenced that a multivariable model including both clinical and laboratory parameters (i.e., blood pressure, creatinine, electrolytes, hepatic enzymes and inflammatory biomarkers) predicted in-hospital VTE in COVID-19 patients with 0.83 AUC, 0.68 sensitivity, and 0.82 specificity, respectively. 31 Even the use of protocols including anticoagulant escalation based on D-dimer values enables to reduce the risk of death compared with standard thromboprophylaxis, 32 thus reinforcing the concept that a “personalized” treatment may be perhaps better than recommending a “standard” anticoagulant strategy.…”