Identification of serum biomarkers for rheumatoid arthritis using protein fingerprint / 中华风湿病学杂志

ABSTRACT

Objective To identify serum biomarkers for rheumatoid arthritis(RA)by protein finger- print pattern. Methods One hundred and forty-one serum samples of 90 RA patients, 20 systemic lupus ery- thematosus(SLE)patients, and 31 healthy individuals were randomly divided into training set(n=93, 60 RA patients, 13 SLE patients and 20 healthy individuals)and test set(n=48, 30 RA patients, 7 SLE patients and 11 healthy individuals). They were detected by surface enhanced laser desorption/ionization-time of flight- mass spectrometry(SELDI-TOF-MS). The protein fingerprint pattern obtained from SELDI-TOF was trained by a multi-layer artificial neural network(ANN)to establish a diagnostic model. Results The detective mod- el obtained by ANN was used to detect the 48 unknown serum samples. The sensitivity and specificity for RA detection was 90% and 90.9% respectively. Conclusion In comparison with traditional methods, SELDI- TOF-MS could identify new serum biomarkers in RA. Combined with ANN, it provides high sensitivity and specificity for RA diagnosis.