Abstract 15698: Logistic and Machine Learning Approaches to Identify Predictors of Venous Thromboembolism in Covid-19 Patients

Abstract

Introduction: Venous thromboembolism (VTE) has a significantly higher incidence in COVID-19 patients when compared to other acute viral infections. The evidence on the risk factors of VTE in COVID-19 inhospital patients is still inconsistent. The information is of utmost importance, as a path to promote prevention, early diagnosis and treatment. Hypothesis: VTE predictors may be identified through logistic regression (LR) and machine learning (ML) approaches. Methods: This multicenter cohort study included consecutive COVID-19 adult patients from 16 hospitals, admitted between March and September, 2020. Deep venous thrombosis and pulmonary embolism were confirmed by objective imaging. LR analysis, tree-based boosting and bagging were used to investigate the association of variables upon hospital presentation with VTE. Results: Among 4,120 patients (median age 61 [interquartile range 48-72] years-old, 55.5% men, 39.3% admitted to intensive care unit), VTE was confirmed in 6.7%. In multivariate LR analysis, obesity (OR 1.50, 95%CI 1.11-2.02); being an ex-smoker (OR 1.44, 95%CI 1.03-2.01); surgery ≤ 90 days (OR 2.20, 95%CI 1.14-4.23); axillary temperature (OR 1.41, 95%CI 1.22-1.63); D-dimer ≥ 4 times above the upper limit of reference value (OR 2.16, 95%CI 1.26-3.67), lactate (OR 1.10, 95%CI 1.02-1.19), C-reactive protein levels (CRP, OR 1.09, 95% CI 1.01-1.18); and neutrophil count (OR 1.04, 95%CI 1.005-1.075) were independent predictors of VTE. Temperature at hospital presentation, SF ratio, neutrophil count, D-dimer, CRP and lactate levels were also identified as predictors by ML methods. Conclusions: By using ML and LR analysis, we showed that D-dimer, axillary temperature, neutrophil count, CPR and lactate levels are risk factors for VTE in COVID-19 patients. ML approaches were able to identify additional predictors. We suggest that patients presenting those risk factors at hospital admission should be more closely monitored for VTE development.