Autoantibodies to phospholipid-binding plasma proteins in patients with thrombosis and phospholipid-reactive antibodies

Anti-phospholipid (aPL) antibodies are defined as antibodies detected in systems employing phospholipids (PL). This general definition is misleading as it comprises a large group of autoimmune phospholipid-reactive antibodies that are directed against specific phospholipid-binding plasma proteins, such as beta(2)-glycoprotein I (beta(2)GPI) and prothrombin. Definition of phospholipid-reacting antibodies according to the plasma protein against which they are directed appears more appropriate and could be useful in understanding clinical events and pathogenic mechanisms. Using ELISA systems we have studied the presence of antibodies directed against specific phospholipid-binding proteins in a series of 22 patients with thrombosis and phospholipid-reactive antibodies of the IgG isotype. High levels of anti-beta(2)GPI IgG were detected in all 22 patients. Normal values were calculated on the basis of OD values at 405 nm (OD405) obtained for 22 age- and sex-matched healthy subjects (cut off value = 0.401). Levels of anti-beta(2)GPI antibodies were linearly correlated with those of cardiolipin-reactive (aCL) antibodies. Eleven out of 22 patients (50%) had values of anti-prothrombin antibodies exceeding the cut-off value of 0.250. No relationship was found between the levels of anti-beta(2)GPI and anti-prothrombin antibodies. Tests for antibodies against two natural inhibitors of blood coagulation, protein C and protein S, revealed elevated levels of anti-protein C IgG and anti-protein S IgG in 4 and 12 patients, respectively. A highly significant correlation between anti-protein C IgG and anti-protein S IgG values as well as between antibody titers against the two studied natural coagulation inhibitors and anti-prothrombin IgG was found. When comparing patients positive for aCL and presence or absence of a previous thrombotic episode (aCL+/T+ vs aCL+/T-), the positivity of anti-beta(2)GPI IgG was found to be statistically associated with thrombosis. Conversely, among patients with previous thromboembolism with or without aCL (aCL+/T+ vs aCL-/T+) the positivity of anti-beta(2)GPI IgG was strictly associated with the positivity of aCL, thus identifying the aPL antibody syndrome. These data demonstrate that anti-beta(2)GPI antibodies are a marker of ''autoimmune'' thrombosis. Anti-prothrombin antibodies are not a marker of thrombosis and are closely associated with antibodies to protein C and protein S.