摘要
目的 :通过肿瘤标志物联合检测 ,同时采用模式识别技术 ,评价血清癌胚抗原 (CEA)、糖类抗原 12 5(CA12 5 )、促胃液素 (Gastrin)、神经元特异性烯醇化酶 (NSE)水平对肺癌组织分型中的临床价值。方法 :用放射免疫法测定了 5 1例肺癌患者血清CEA、CA12 5、促胃液素、NSE水平 ,采用线性学习机法、Fisher判别分析法及K NN法等3种模式识别技术 ,探讨了该 4项肿瘤标志物在肺癌组织分型中的应用价值。结果 :小细胞肺癌 (SCLC)患者促胃液素、NSE水平明显高于非小细胞肺癌 (NSCLC)患者 ,而CEA、CA12 5水平却低于非小细胞肺癌患者。在判别SCLC与NSCLC类型中 ,3种模式识别技术总的符合率分别为 81.5 %、87.5 %、10 0 %。结论 :该 4项肿瘤标志物联合检测在肺癌组织分型方面可为临床提供有价值的参考资料 ,同时表明模式识别技术在组织分型中有一定的应用价值。
Aim: Lung cancer is classified into small cell lung cancer (SCLC) and non small cell lung cancer (NSCLC). SCLC is different from NSCLC in treatment and prognosis, and the treatment scheme changes with different histological type. It is important to make certain histological type for deciding treatment scheme, but it is difficult for physician, especially in rural area. For early clinical diagnosis of lung cancer, various tumor markers have been investigated, but for measurement of single marker, its sensitivity and specificity are hard to satisfy to clinical request for early and distinguishing diagnosis. From the point of view, combined determination proved to be more powerful than single. To improve the rate of correct classification of SCLC and NSCLC, four tumor markers were combined to be determined, and pattern recognition was used to distinguish NSCLC from SCLC. Methods: A panel of four markers, including CEA, CA125, gastrin, NSE was determined in 51 patients with confirmed primary diagnosis of lung cancer of different histology by radioimmunoassay (30 patients with NSCLC and 21 patients with SCLC). t test was used as statistical disposal. Pattern recognition was used as discriminant analysis, including linear learning machine, Fisher discriminant analysis and KNN. Results: The levels of gastrin and NSE in SCLC were apparently higher than those of gastrin and NSE in NSCLC, but levels of CEA and CA125 in SCLC were significantly lower than those in NSCLC. Three approaches of pattern recognition were used to classify between SCLC and NSCLC. The results showed that combined determination of the four tumor markers may be useful in the histological type diagnosis of lung cancer before operation, and the total accurate rates were 81.5%, 87.5%, 100%, respectively, in distinguishing SCLC from NSCLC. Conclusions: Pattern recognition is an important statistical method, especially in discriminant analysis. Combined determination of tumor markers can provide reference value for histological type of lung cancer.
出处
《河南医科大学学报》
2000年第3期214-217,共4页
Journal of Henan Medical University
基金
河南省自然科学基金资助项目!991170 2 15
关键词
肺肿瘤
肿瘤标志物
模式识别技术
carcinoembryonic antigen(CEA)
neuron specific enolase(NSE)
carbohydrate antigen125(CA125)
gastrin
small cell lung cancer
non small cell lung
cancer
histological type
pattern recognition
