论文部分内容阅读
目的建立蛋白质芯片技术检测血清蛋白质指纹图谱的方法,探讨基于人工神经网络的血清蛋白质指纹图谱模型在肝癌诊断中的应用价值。方法应用蛋白质指纹图谱分析仪(表面增强激光解析电离飞行时间质谱仪,SELDITOFMS),测定106例肝癌、肝硬化患者和健康人血清标本的蛋白质指纹图谱并结合人工神经网络方法进行数据的分析。将106例标本随机分成训练组70例(肝癌35例,肝硬化14例,健康人21例)和盲法测试组36例(肝癌17例,肝硬化8例,健康人11例)。利用从训练组得出的基于人工神经网络的血清蛋白质指纹图谱模型,对36例未知血清进行检测,并与甲胎蛋白(AFP)检测结果进行比较。结果应用该方法对肝癌进行诊断的准确率、敏感性和特异性分别为917%(33/36)、882%(15/17)和946%(18/19),明显高于AFP检测结果。结论基于人工神经网络的血清蛋白质指纹图谱模型在肝癌的诊断中较以往的传统方法具有更高的敏感性和特异性,值得进一步研究与应用。
Objective To establish a method of detecting protein profile of serum by protein chip technology and to explore the value of serum protein fingerprinting model based on artificial neural network in the diagnosis of liver cancer. Methods The protein fingerprints of 106 serum samples from patients with liver cancer, liver cirrhosis and healthy people were detected by protein fingerprinting analyzer (SELDI-TOF MS) and the data were analyzed by artificial neural network. 106 cases were randomly divided into training group of 70 cases (35 cases of liver cancer, 14 cases of cirrhosis, 21 healthy subjects) and 36 cases of blind test (17 cases of liver cancer, 8 cases of liver cirrhosis and 11 healthy subjects). Thirty-six unknown serum samples were tested using the serum protein fingerprinting model based on the artificial neural network derived from the training group and compared with the AFP test results. Results The accuracy, sensitivity and specificity of this method for the diagnosis of liver cancer were 917% (33/36), 882% (15/17) and 946% (18/19), respectively, which were significantly higher than those of AFP. Conclusion The serum protein fingerprinting model based on artificial neural network is more sensitive and specific than the traditional methods in the diagnosis of liver cancer and is worth further study and application.