摘要
目的:研究食管癌癌变过程中血清低分子量蛋白的细微变化,探索食管癌发生的机制、寻找食管癌早期诊断的生物标志物和方法。方法:应用表面激光解析电离飞行时间质谱技术对食管癌患者和健康对照血清进行蛋白质谱指纹图谱检测,通过Biomarker Wizard软件筛选差异蛋白,使用人工神经网络软件建立食管癌早期诊断模型并用盲法验证其诊断效果;将食管癌早期和中晚期食管癌患者血清质谱图进行比对分析,寻找各期差异蛋白,并建立分期诊断模型。结果:发现食管癌和正常人差异蛋白5种,早期食管癌和中晚期食管癌差异蛋白3种。通过早期食管癌组和健康对照组建立早期诊断模型的灵敏度87.88%,特异度91.43%,准确度89.71%,经过盲法验证结果为灵敏度95.83%,特异度89.13%,准确度91.43%。建立的分期诊断模型中,早期食管癌和中晚期筛选的差异蛋白建立的分期诊断模型灵敏度75.76%,特异度79.17%,准确度77.19%。结论:表面增强激光解析离子化飞行时间质谱(SELDI-TOF-MS)联合人工神经网络技术操作较为简便,在食管癌的诊断和分期上具有可行性。
Objective：To explore the mechanism of esophageal cancer（EC）and find the biomarkers and methods of early diagnosis,the minor alterations of serum proteins in canceration were detected using mass spectrometry.Methods：The serum proteomic patterns of esophageal cancer and healthy control group were detected using the SELDI-TOF-MS（surface-enhanced laser desorption/ionization-time of flight-mass spectrometry） technology.Differences in protein peaks between patients with EC and controls were analysed using the Biomarker Pattern Software,and a primary early diagnosis model of EC was developed and validated with ANN（artificial neural network）.Analysing the protein peaks of between the early and advanced EC,the diagnosis model of staging esophageal cancer with differences in protein was established.Results：Between EC and controls,there were five differences in proteins,and three proteins in early and advanced esophageal cancer were found;The five proteins were selected to build the model of early diagnosis with a sensitivity of 87.88%,a specificity of 91.43%,and an accuracy of 89.71%.The blind test generated a sensitivity of 95.83%,a specificity of 89.13% and an accuracy of 91.43%.Three different proteins were used to established the model of staging diagnosis.The sensitivity was 75.76%,the specificity was 79.17%,and the accuracy was 77.19%.Conclusion：It was simple in operation and was feasible in the diagnosis and staging of esophageal cancer to combine SELDI-TOF-MS and artificial neural network.
