Objective To establish effective and early experimental index for the detection of primary hepatic carcinoma ( PHC). Methods The samples of 435 serum were tested by surface enhanced laser desorption ionization time of flight mass spectrometry (SELDI-TOF-MS) and matched Cold Chip. Samples were randomly assigned into two subsets, the training set and the testing set. The training set was used for identifying the statistically significant peaks as well as for developing artificial neural network (ANN) model. And the testing set was used for blind test to validate the diagnostic efficiency of ANN model. Results Seven marker proteins differentially expressed were found. The prediction of PHC using the blind method of ANN model showed that the sensitivity and specificity were 84.00% and 81.25% respectively, the area under (AUC) of receiver operating characteristic curve (ROC curve) was 0.847, negative predictive value( NPV) was 94.20% , positive predictive value (PPV) was 58.33% , accuracy( ACC) was 81.90%. Conclusions There are different proteins significantly expressed in the serum of PHC, the ANN model based on it can provide a new method of differential diagnosis of PHC and has important referential value.%目的 建立早期有效检测原发性肝癌的实验指标.方法 利用表面增强激光解析电离飞行时间质谱(SELDI-TOF-MS)技术及其配套的金芯片(Gold Chip)检测435份血清蛋白质谱数据,并将其分为训练集和验证集两组.训练集用于筛选原发性肝癌的差异蛋白标志物并建立ANN诊断模型,验证集用于模型诊断效度的盲法验证.结果 共发现7个有明显表达差异的标志蛋白.用其建立ANN诊断模型对原发性肝癌进行盲法验证,诊断的灵敏度和特异度分别为84.00％和81.25％,受试者工作特征曲线(ROC曲线)下面积(AUC)为0.847,阴性预测值94.20％,阳性预测值58.33％,准确度为81.90％.结论 原发性肝癌患者血清具有明显表达差异的特征蛋白,据其建立的人工神经网络模型可为原发性肝癌的诊断提供新方法,有重要的参考价值.
展开▼
