血清蛋白质谱模型对胃癌早期诊断的应用研究

摘要

Objective;To establish serum proteomic pattern for the early diagnosis of gastric cancer. Methods: PBS II/C type protein spectrometer and CM10 protein chip were performed to detect mass spectrogram of patients with gastric cancer and contrast persons for serum protein signature analysis to build and test ANN model. Results: Four specific protein peaks ( M/Z as 2502. 3 ±3.2,3085.5 ±2.8,4130.6 ±2.1,8691.4 ±1.7) which were chosen to develop the artificial neural network diagnostic model had significant difference in gastric cancer compared with the control group . The sensitivity, specificity, negative predictive value, positive predictive value were 95% ,98.33% , 98. 33% ,95% ,97.5%. Conclusion: Serum proteomic pattern established by this study was valuable to the early diagnosis of gastric cancer.%目的:建立用于胃癌早期诊断的血清蛋白质谱模型.方法:采用PBSⅡ/C型蛋白质指纹图谱仪及CM10芯片筛选胃癌差异表达蛋白,通过人工神经网络(ANN)建立并验证胃癌的血清蛋白质谱模型.结果:发现4个质荷比峰(M/Z为2502.3±3.2、3085.5±2.8、4130.6±2.1、8691.4±1.7)在胃癌组与对照组比较中具有显著差异,组成的胃癌人工神经网络诊断模型,对胃癌诊断的灵敏度、特异度、阴阳性预测值、准确度分别为95％,98.33％,98.33％,95％,97.5％.结论:本研究建立的血清蛋白质谱模型对胃癌的早期诊断具有一定的价值,值得深入研究.