期刊文献+

老年肺癌早期诊断血清肿瘤标志物及其组合的Logistic模型筛选研究 被引量:1

Screening the serum tumor marker or markers combination for early diagnosis of elderly of lung cancer by using logistic models
暂未订购
导出
摘要 目的:评价不同血清肿瘤标志物对老年支气管肺癌的诊断价值,筛选最佳诊断效能标志物及标志物组合。方法:采用电化学发光免疫法检测所有对象血清中Fer、CEA、CA724、Cyfra211、NSE、CA125、CA199、CA153的表达水平;对肺癌组及对照组间有统计学差异的血清肿瘤标志物用Logistic逐步回归法建立函数诊断模型;并进行预测分类,筛选诊断效能最佳的单一标志物及标志物组合。结果:在肺癌及对照组之间,各单一指标检测均有显著性差异(P<0.05);其中Cyfra211为最佳单一指标;在组合模型诊断效价评定中,CEA+NSE+Cyfra211组合具有更好的临床价值。结论:应用Logistic逐步回归函数诊断模型可有效筛选灵敏度及特异度较好的血清肿瘤诊断标志物,可简便、快速、有效使用标志物及标志物组合对老年肺癌进行早期诊断。 Objective:To evaluate the diagnostic value of differential serum tumor markers for diagnosing elderly lung cancer and screening the excellent marker or markers combination.Methods:To detect serum tumor markers:Fer,CEA,CA724,Cyfra211,NSE,CA125,CA199,CA153 by using electrochemiluminescence immunoassay(ECLIA),and which were significant difference in expression levels between lung cancer group and control group would be established function diagnostic model by logistic stepwise methods,then forecast classification,screen the excellent marker or markers combination lastly.Results:There are significant difference in expression levels of single marker between lung cancer group and control group,Cyfra211was the best single index.A discriminate model which was composed of CEA+ NSE+Cyfra211 was considered the best model.Conclusion:Using the Logistic methods to construct discriminate models by serum tumor markers could conveniently,rapidly and effectively make differential diagnosis elderly lung cancer,and convenient for clinical diagnosis.
出处 《现代肿瘤医学》 CAS 2010年第11期2139-2142,共4页 Journal of Modern Oncology
关键词 肺癌 Logistic模型筛选 肿瘤标志物 诊断模型 lung cancer logistic regression tumor marker diagnostic model
  • 相关文献

参考文献8

二级参考文献53

  • 1张斌,华中生.一种改进的求解含等式约束凸二次规划问题的Lemke算法[J].中国科学技术大学学报,2004,34(6):668-677. 被引量:5
  • 2何文章,张宪彬.利用Logistic模型预测耐用消费品社会拥有量[J].数理统计与管理,1994,13(1):21-25. 被引量:22
  • 3刘勇洪,牛铮,王长耀.基于MODIS数据的决策树分类方法研究与应用[J].遥感学报,2005,9(4):405-412. 被引量:91
  • 4崔党群.生物统计学[M].北京:中国科学技术出版社,1994..
  • 5边肇祺 张学工.模式识别(第二版)[M].北京:清华大学出版社,2003.250-257.
  • 6Vapnik V. The nature of statistical learning theory, New York: Springer-Verlag, 1995: 10-15
  • 7Scholkopf B, Smola AJ. Learning with kernels:support vector machines, regularization, optimization and beyond. Cambridge: MIT Press, 2002:10-16
  • 8Campbell C. Kernel methods: a survey of current techniques. Neurocomputing, 2002; 48 (1-4)∶63
  • 9Campbell C. Algorithmic approaches to training support vector machinies:a survey. Proceedings of ESANN2000. D-Facto Publications, Belgium, 2000, 2000∶27
  • 10Platt J. Using analytic QP and sparseness to speed training of support vector machines. Advances in kernel methods-support vector learning. Cambridge: MIT Press,1999: 185

共引文献248

同被引文献16

引证文献1

二级引证文献13

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部