期刊文献+

应用Logistic回归和ROC曲线综合评价肿瘤标志物联合检测对肺癌的诊断价值 被引量:11

Diagnostic value of combined detection of tumor markers in lung cancer analyzed with ROC curve and logistic regression
下载PDF
导出
摘要 目的探讨Logistic回归和ROC曲线综合分析血清癌胚抗原(CEA)、鳞状细胞癌抗原(SCC-Ag)和铁蛋白(SF)对肺癌的诊断价值。方法分别检测100例肺癌患者和30例健康者血清中的CEA、SCC-Ag和SF水平,通过Logistic回归建立回归模型,用ROC曲线分析3种肿瘤标志物对肺癌的诊断的意义。结果肺癌组CEA、SCC-Ag和SF水平均明显高于健康对照组(P<0.01),腺癌组CEA水平最高,鳞癌组SCC-Ag水平最高,肺癌患者3种肿瘤标志物水平与TNM分期密切相关,Ⅲ+Ⅳ期明显高于Ⅰ+Ⅱ期,差异有统计学意义(P<0.05);CEA和SCC-Ag在转移组阳性率比无转移组高(分别为P<0.01;P<0.05),而SF在两组间阳性率比较差异无统计学意义(P>0.05)。建立回归模型Y=1/[1+EXP(2.261 X1+3.459 X2+4.267 X3-1.082)],新变量Y的AUC高于3种单一肿瘤标志物的AUC。结论血清CEA、SCC-Ag和SF对肺癌具有较高的诊断价值,综合运用logistic回归和ROC曲线分析可提高肺癌诊断的准确性。 [ Objective ] To investigate the diagnostic value of combined detection of tumor markers in lung cancer analyzed with ROC curve and logistic regression. [ Methods ] Serum CEA, SCC-Ag and SF were measured in 100 patients with lung cancer and 30 heahhy subjects. Logistic regression and ROC curve were applied to analyze the data and evaluate the diagnostic values. [ Results ] The concentrations of serum CEA, SCC-Ag and SF in patients with lung cancer were significantly higher than those in the healthy group. The serum level of CEA was the highest in patients with adenocarcinoma. SCC-Ag was the highest in squamous cell lung cancer. The concentrations of three tumor markers correlated strongly with tumor stage, and the serum levels of markers in patients with stage Ⅲ and Ⅳ were significantly higher than in those with stage Ⅰ and Ⅱ . The difference was statistically significant (P 〈 0.05 - 0.01); the positive rate of CEA and SCC-Ag of metastais group was evidently higher than the rate of non-metastasis (respectively, P 〈 0.01; P 〈 0.05), but there was no significant difference for SF between the two groups (P 〉 0.05). According to regression equation Y = 1/[1 + EXP (2.261 X1 + 3.459 X2 + 4.267 X3 - 1.082)], the AUC of variable Y was higher than any of the three tumor markers. [ Conclusions ] Combined detection CEA, SCC-Ag and SF could improve the diagnostic sensitivity and accuracy significantly. Applications of logistic regression and ROC curve in- crease diagnostic accuracy in lung cancer.
出处 《中国现代医学杂志》 CAS 北大核心 2015年第19期47-50,共4页 China Journal of Modern Medicine
基金 广西卫生厅基金课题(No:Z2012354)
关键词 肺癌 癌胚抗原 鳞状细胞癌抗原 铁蛋白 lung cancer CEA SCC-Ag SF
  • 相关文献

参考文献11

二级参考文献37

共引文献49

同被引文献96

引证文献11

二级引证文献91

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