4项肿瘤标志物联合检测预测小细胞肺癌及非小细胞肺癌分型的研究

Value of combined detection of tumor markers for the prediction of small cell and non- small cell lung cancer

为了探讨癌胚抗原 (CEA)、糖类抗原 12 5 (CA12 5 )、胃泌素、神经元特异性烯醇化酶 (NSE)在肺癌组织分型的价值 ,应用放射免疫分析法测定了 2 1例小细胞肺癌 (SCL C)、30例非小细胞肺癌 (NSCL C)患者血清中 CEA、CA12 5、胃泌素、NSE水平 ,观察了这些患者血清中该 4项肿瘤标志物水平在不同的组织分型中的变化 ,并观察了吸烟对该 4项肿瘤标志物水平的影响。在此基础上分别采用了线性学习机法、PRIMA法及 KNN最近邻域法进行判别处理 ,尝试了这 3种模式识别方法在肺癌组织分型的应用价值。结果表明 :小细胞肺癌患者血清中胃泌素、NSE水平显著高于非小细胞肺癌患者 ,而 CEA、CA12 5水平却明显低于非小细胞肺癌患者。吸烟仅对 CEA及 CA12 5水平有显著影响 ,而对胃泌素及 NSE水平影响不显著。 3种方法在判别 SCL C与 NSCL C中其准确度均在 85 %以上。因此 ,该 4项肿瘤标志物联合检测并运用模式识别方法可以辅助预测小细胞肺癌与非小细胞肺癌 。

To evaluate the value of detection of4tumor markers(CEA,CA12 5 ,gastrin,and NSE) forhistological types in patients with lung cancer and to improve the predicted efficiency of tumor markers for distinguishing between small cell lung cancer(SCL C) and non- small cell lung cancer(NSCL C) ,these4 tum or m arkers in serum were determ ined in 5 1patients (2 1cases with SCL C,30 cases with NSCL C) with confirmed primary diagnosis of lung cancer of different histology by radioimmunoassay.L inear learning machine method,PRIMA method and KNN method were used to classify SCL C and NSCL C. The levels of gastrin and NSE in SCL C were apparently higher than those of gastrin and NSE in NSCL C,butthe levels of CEA and CA12 5 in SCL C were significantly lower than those in NSCL C. Smoking had an effect on the levels of CEA and CA12 5 ,but had little effecton those of gastrin and NSE.The total accuracy of the three methods was over 85 % in distinguishing SCL C from NSCL C.So com bined detection of the four tumor markers in serum m ight be useful in the prediction of histological types in patients with lung cancer.