Predictors of venous thromboembolism in COVID-19 patients: results of the COVID-19 Brazilian Registry

Abstract

Previous studies that assessed risk factors for venous thromboembolism (VTE) in COVID-19 patients have shown inconsistent results. Our aim was to investigate VTE predictors by both logistic regression (LR) and machine learning (ML) approaches, due to their potential complementarity. This cohort study of a large Brazilian COVID-19 Registry included 4120 COVID-19 adult patients from 16 hospitals. Symptomatic VTE was confirmed by objective imaging. LR analysis, tree-based boosting, and bagging were used to investigate the association of variables upon hospital presentation with VTE. Among 4,120 patients (55.5% men, 39.3% critical patients), 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. Atrial fibrillation, peripheral oxygen saturation/inspired oxygen fraction (SF) ratio and prophylactic use of anticoagulants were protective. Temperature at admission, SF ratio, neutrophil count, D-dimer, CRP and lactate levels were also identified as predictors by ML methods. By using ML and LR analyses, we showed that D-dimer, axillary temperature, neutrophil count, CRP and lactate levels are risk factors for VTE in COVID-19 patients. Supplementary Information The online version contains supplementary material available at 10.1007/s11739-022-03002-z.

COVID-19 and Pulmonary Thrombosis—An Unresolved Clinical Puzzle: A Single-Center Cohort Study

“…A Brazilian cohort ( n = 4120) reported twice as high in-hospital mortality in patients diagnosed with VTE. In contrast, we found no association between PT and mortality, similar as others [ 17 , 32 ]. This might be explained by a high frequency of small peripheral thrombi, which might not cause further respiratory deterioration.…”

Machine learning-based predictive models for patients with venous thromboembolism: A Systematic Review

“…splitting the dataset into training and testing subsets 49 as well as not clear reporting on individual test set 27,29,30,34,38,39,41,51 . Performance metrics are not consistently reported, making the head-to-head comparison of these studies challenging.…”

“…Nevertheless, if it is not performed properly data leakage can happen. In every case an unseen part of the dataset must be kept for internal validation purposes and this was not clear in many [28][29][30]34,[38][39][40][41]51,53,54,[56][57][58]61,62,64,77,84,89,126,127 of the reviewed studies. This review highlighted a significant problem in AI-related research, namely the lack of standardized reporting methods.…”

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

“…23 Obesity, D-dimer, blood lactate, CRP, and neutrophil count were also found to be independent predictors of venous thrombosis in an analysis of the COVID-19 Brazilian Registry. 24 The evidence that genetic predisposition may influence the clinical outcome of COVID-19 goes hand in hand with the results of a large genome-wide association study, which identified as many as 27 genes potentially associated with SARS-CoV-2-related hospitalization, many of which were related to coagulation pathways or inflammation and, most notably, associated with coagulation factor VIII and clinical phenotypes of VTE. 25 Interestingly, another preprint cross-trait analysis published by Huang et al found that VTE shared as many as eight and eleven genetic loci with severe SARS-CoV-2 infection and hospitalization for COVID-19, including genes participating to blood coagulation (e.g., ADAMTS-13 [a disintegrin and metalloproteinase with a thrombospondin type 1 motif, member 13] and FV).…”