不同分类技术联合肿瘤标志在诊断和预测肺癌方面的研究

Diagnosis and prediction of lung cancer through different classification techniques with tumor markers

目的 探讨何种统计分类模型适于建立多肿瘤标志肺癌预测诊断模型。方法 采用放射免疫分析法（RIA）、双抗体夹心酶联免疫吸附试验法（ELISA）、分光光度法（SP）、高效液相色谱法（HPLC）及原子吸收分光光度法（AAS）分别测定肺癌患者、肺良性疾病患者和健康对照者血清中的癌胚抗原（CEA）、糖链抗原-125（CA125）、胃泌素（gastrin）、神经元特异性烯醇化酶（NSE）、β2-微球蛋白（β2-MG）、可溶性白细胞介素-6受体（sIL-6R）、唾液酸（sialicacid，SA）、一氧化氮（NO）、Cu、Zn、Ca及尿样中的伪尿核苷／肌苷（pseud／trop）含量，并分别建立logistic回归分析、决策树分析以及人工神经网络的数据挖掘分类预测模型。结果 logistic回归分析、决策树分析和人工神经网络模型联合12项肿瘤标志诊断肺癌的总敏感性分别为94．00％、100．00％、100．00％；特异度分别为100．00％、98．89％、100．00％；总准确性分别为94．29％、95．00％、90．00％。结论 12项肿瘤标志的3种分类模型对肺癌分类预测和诊断结果均比较理想，尤其是C5．0决策树模型和人工神经网络模型更适于解决职业性肺癌的预测和辅助诊断。

Objective To study which classification model was most suitable for establishing a multi-tumor markers lung cancer prediction model, through established logistic regression model, decision trees model and artificial neural network model. Methods RIA analysis, ELISA, spectrophotometry, highperformance liquid chromatography （HPLC） and atomic absorption spectrometry were used to measure the serum CEA , CA125, gastrin, NSE, β2-MG, sIL-6 receptors, sialic acid, nitric oxide, Cu, Zn, Ca and the pseudo-urine nucleoside of urine samples in lung cancer patients, benign lung disease patients and healthy controls. The lung cancer diagnosis models were established by logistic regression analysis, decision tree analysis and artificial neural network training. Results The diagnosis sensitivities of the logistic regression analysis, decision tree analysis and artificial neural network model with 12 tumor markers in lung cancer were 94.00%, 100.00% and 100.00%; the specificity were 100.00%, 98.89% and 100.00%; the total accurate 94.29%, 95.00% and 90.00%, respectively. Conclusion The results of three classification models with 12 tumor markers in diagnosis of lung cancer are ideal. Especially the C5.0 decision tree model and the artificial neural network model are more suitable for the prediction and diagnosis of the lung cancer.