Risk of Venous Thrombosis in Antithrombin Deficiency: A Systematic Review and Bayesian Meta-analysis

Abstract

Antithrombin deficiency is a strong risk factor for venous thromboembolism (VTE), but the absolute risk of the first and recurrent VTE is unclear. The objective of this paper is to establish the absolute risks of the first and recurrent VTE and mortality in individuals with antithrombin deficiency. The databases Embase, Medline Ovid, Web of Science, the Cochrane Library, and Google Scholar were systematically searched for case-control and cohort studies. Bayesian random-effects meta-analysis was used to calculate odds ratios (ORs), absolute risks, and probabilities of ORs being above thresholds. Thirty-five publications were included in the systematic review and meta-analysis. Based on 19 studies, OR estimates for the first VTE showed a strongly increased risk for antithrombin deficient individuals, OR 14.0; 95% credible interval (CrI), 5.5 to 29.0. Based on 10 studies, meta-analysis showed that the annual VTE risk was significantly higher in antithrombin-deficient than in non-antithrombin-deficient individuals: 1.2% (95% CrI, 0.8-1.7) versus 0.07% (95% CrI, 0.01-0.14). In prospective studies, the annual VTE risk in antithrombin deficient individuals was as high as 2.3%; 95% CrI, 0.2-6.5%. Data on antithrombin deficiency subtypes are very limited for reliable risk-differentiation. The OR for recurrent VTE based on 10 studies was 2.1; 95% CrI, 0.2 to 4.0. The annual recurrence risk without long-term anticoagulant therapy based on 4 studies was 8.8% (95% CrI, 4.6-14.1) for antithrombin-deficient and 4.3% (95% CrI, 1.5-7.9) for non-antithrombin-deficient VTE patients. The probability of the recurrence risk being higher in antithrombin-deficient patients was 95%. The authors conclude that antithrombin deficient individuals have a high annual VTE risk, and a high annual recurrence risk. Antithrombin deficient patients with VTE require long-term anticoagulant therapy.