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.
Hypercoagulability is a recognized feature in SARS-CoV-2 infection. There exists a need for a dedicated risk assessment model (RAM) that can risk-stratify hospitalized COVID-19 patients for venous thromboembolism (VTE) and guide anticoagulation. We aimed to build a simple clinical model to predict VTE in COVID-19 patients. This large-cohort, retrospective study included adult patients admitted to four hospitals with PCR-confirmed SARS-CoV-2 infection. Model training was performed on 3531 patients hospitalized between March and December 2020 and validated on 2508 patients hospitalized between January and September 2021. Diagnosis of VTE was defined as acute deep vein thrombosis (DVT) or pulmonary embolism (PE). The novel RAM was based on commonly available parameters at hospital admission. LASSO regression and logistic regression were performed, risk scores were assigned to the significant variables, and cutoffs were derived. Seven variables with assigned scores were delineated as: DVT History = 2; High D-Dimer (>500–2000 ng/mL) = 2; Very High D-Dimer (>2000 ng/mL) = 5; PE History = 2; Low Albumin (<3.5 g/dL) = 1; Systolic Blood Pressure <120 mmHg = 1, Tachycardia (heart rate >100 bpm) = 1. The model had a sensitivity of 83% and specificity of 53%. This simple, robust clinical tool can help individualize thromboprophylaxis for COVID-19 patients based on their VTE risk category.
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 in COVID-19 patients 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 prevention, early identification and management of VTE in hospitalized COVID-19 patients and improve clinical outcomes in these patients. Methods 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 random forest, multiple logistic regression, multiple linear regression, and decision trees were built on the primary outcome of in-hospital acute deep vein thrombosis and pulmonary embolism 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 area under the receiver operating characteristic curve and confusion matrix.Results The cohort included 3531 admissions, 3526 had discharge diagnosis, and 6.68% patients developed acute VTE (N=236). VTE group had a longer hospital and ICU LOS than 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% patients in VTE group required more advanced oxygen support, compared to 2.7% patients in 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 of in-hospital VTE in COVID-19 patients. Conclusions and Relevance Patients with COVID-19 have increased 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 clinical judgment on empirical dosages of anticoagulation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.