ABSTRACT
BACKGROUND: Primary immune thrombocytopenic purpura (pITP) is defined as isolated autoimmune thrombocytopenia with idiopathic low platelet count, normal bone marrow, and unexplained causes of thrombocytopenia. Currently there is no definite criterion for ITP diagnosis. METHODS: We conducted proteomic screen of patients with pITP, secondary immune thrombocytopenia (sITP), and healthy controls using surface-enhanced laser desorption/ionization time-of-flight mass spectrometry (SELDI-TOF-MS). The proteomic profiles were obtained from platelet lysate samples of 82 healthy adult controls, 64 pITP, and 70 sITP patients, from which we screened marker proteins with significant differences, and constructed a diagnosis model using the artificial neural network (ANN) technique. RESULTS: We identified 6 marker proteins in the platelet lysates of pITP patients. This diagnosis method differentiated pITP patients from sITP effectively with a sensitivity of 96.9% (31/32), a specificity of 71.0% (54/76), and the area under the ROC curve of 0.864 in the training set, and a sensitivity of 87.5% (28/32), a specificity of 69.7% (53/76), and a positive predictive value of 75.0% (81/108) in the test set. CONCLUSION: The artificial neural network model based on platelet protein profiling established a potential pITP diagnosis platform.
