血清蛋白质指纹图谱与人工神经网络模型在肺癌诊断中的应用  

Classification and diagnostic prediction of lung cancer using protein profiling of serum and bioinformatics

作　　者：韩明勇[1] 刘奇[1] 余捷凯[2] 郑树[2] 

机构地区：[1]山东大学附属省立医院肿瘤中心,济南250021 [2]浙江大学肿瘤研究所,杭州310009

出　　处：《山东大学学报（医学版）》2008年第6期604-607,共4页Journal of Shandong University:Health Sciences

基　　金：山东省科技公关项目资助课题(2007GG20002007)

摘　　要：目的筛选肺癌相关标志物并建立诊断肺癌的蛋白质谱模型。方法应用表面增强激光解吸电离飞行时间质谱（SELDI-TOF-MS）技术检测了86例肺癌、80例健康对照样本的血清蛋白质质谱，结合人工神经网络建立肺癌诊断模型。结果从肺癌组与健康对照组中筛选出了4个蛋白质荷比峰建立肺癌诊断模型，该诊断模型的特异性为100％（95％的置信区间为93．9％～100.0％），敏感性为93．6％（87．6％-96．4％），准确率为96．7％（88．1％。98．3％）。结论成功建立了肺癌诊断模型，该模型在肺癌的诊断中具有较高的敏感性和特异性。Objective To identify serum biomarkers that distinguish lung cancer from healthy individuals by protein fingerprint pattern. Methods 86 lung cancer patients and 80 healthy controls were determined by surface-enhanced laser desorption/ionization time-of-flight mass spectrometry （SELDI-TOF-MS）. Results 4 protein peaks were selected and used by artificial neural network （ANN） to establish a diagnostic model. The specificity of the diagnostic pattern was 100% and sensitivity of the pattern was 93.6%. Conclusions A diagnostic model of lung cancer was successfully established, which has high sensitivity and specificity.

关 键 词：肺肿瘤 表面增强激光解吸电离飞行时间质谱 生物信息学 诊断 蛋白组学 

分 类 号：R322.81[医药卫生—人体解剖和组织胚胎学]