Diagnosis model of idiopathic thrombocytopenic purpura based on platelet differential proteome.
10.7534/j.issn.1009-2137.2013.01.027
- Author:
Pan ZHOU
1
;
Yin-Huan DING
;
Peng HE
;
Peng-Qiang WU
;
Wen-Jun LIU
;
Kai-Zheng WANG
Author Information
1. Department of Laboratorial Medicine, Affiliated Hospital of Luzhou Medical College, Luzhou, Sichuan Province, China.
- Publication Type:Journal Article
- MeSH:
Adult;
Case-Control Studies;
Humans;
Neural Networks (Computer);
Peptide Mapping;
Proteome;
analysis;
Proteomics;
Purpura, Thrombocytopenic, Idiopathic;
diagnosis;
genetics;
metabolism;
Spectrometry, Mass, Matrix-Assisted Laser Desorption-Ionization;
methods
- From:
Journal of Experimental Hematology
2013;21(1):130-134
- CountryChina
- Language:Chinese
-
Abstract:
This study was purposed to establish a new quick and simple diagnostic method with high sensitivity and good specificity for idiopathic thrombocytopenic purpura (ITP) and to evaluate its significance. 240 platelet lysates (from patients with ITP, leukemia, MDS, and healthy adults, each of 60 cases) were randomly assigned to training set (120 cases) or validation set (120 cases), all of them were detected by surface enhanced laser desorption ionization time of flight mass spectrometry (SELDI-TOF-MS), in order to identify the differentially expressed protein, the diagnostic model was established by means of artificial neural network (ANN), and was validated by blind test with SPSS 17.0. The results showed that 5 marked proteins significantly differentially expressed (P < 0.01), m/z of highly expressed proteins were 2234.30, 3476.36, and 7526.29, m/z of low expressed proteins were 4990.02 and 5152.39, respectively. The sensitivity and specificity of diagnostic model were 80.6% and 77.3% respectively. The area under the ROC curve consisting of the output value of artificial neura1 network was 0.837. Efficacy of the model was validated by means of blinded test. It is concluded that the ANN model is useful for clinical diagnosis of ITP on the basis of platelet protein fingerprint spectrum.
