摘要
目的将有限的检验信息提炼为高效的诊治信息，从技术层面探索检验医学的临床实践新途径。方法以CA72—4，CA19-9和CEA三项血清标志物检验诊断大肠癌为例，依托实验室信息系统（LIS）与医院信息系统（HIS）的数据信息平台，利用人工神经网络（ANN）为数据挖掘工具和SPSS统计软件构建ROC数据集，以验后概率解释每一份胃肠肿瘤标志物检验报告。结果纳入研究的1206份胃肠道肿瘤标志物检验标本中大肠癌占12．365％；构建了CA19-9，CA72—4和CEA检验筛查和诊断大肠癌的ROC数据集；大肠癌组三项血清标志物浓度均显著高于健康对照组和其他疾病组（P〈0．01）；CA19-9，CA72—4，CEA和人工神经网络诊断模型预测值筛查大肠癌的ROC曲线下面积分别是0．624，0．692，0．721和0．785。而诊断大肠癌的ROC曲线下面积分别是0．607，0．762，0．687和0．795。赋予验后概率的检验报告客观地提供了检测结果的参考价值。结论ANN模型在多项检验项目分析中具有更高的诊断效率，构建ROC数据集并赋予验后概率的检验报告是检验医学临床实践切实可行的新途径。
Objective To make the limited laboratory information extraction for efficient diagnosis and treatment of information,and to explore a clinical new way for laboratory medicine from a technical level. Methods CA72-4,CA19-9 and CEA,the three blood serum makers were used to diagnose carcinoma of large intestlne,for example,relylng on laboratory information system （LIS） and hospital information system （HIS） data information platform,artificial neural network （ANN） was used for data digging tools,and by means of SPSS statistical software to build ROC data sets. Depend on posterior probability to comment gastrointestinal tumor markers in each inspection reports. Results In 1 206 samples,gastrointestinal tumor marker test specimens of colorectal cancer was accounted for 12.36% ,to build CA19-9,CA72-4 and CEA testing,seeking and diagnosis carcinoma of large intestine of ROC data sets;the three carcinoma of large intestine serum markers＇concentrations were significantly higher than the healthy control group and the other disease groups （P〈0. 01）. CA19-9,CA72-4,CEA and ANN diagnostic model for carcinoma of large intestine screening predictive value of area under the ROC curve were 0. 624,0. 692,0. 721 and 0. 785 ,respetively. While the diagnosis of carcinoma of large intestine in the area under the ROC curve were 0. 607,0. 762,0. 687 and 0. 795, respectively, survey report assigned test posterior probability objectively provide a reference value. Conclusion ANN model has a higher diagnostic efficiency analysis in a number of test items,to build ROC data sets ,and a inspection report satisfied with the ROC data sets,which has been given the posterior probabillty,is a feasible new way in clinical practice of laboratory medicine.
出处
《现代检验医学杂志》
CAS
2010年第2期39-42,共4页
Journal of Modern Laboratory Medicine
关键词
大肠癌
肿瘤标志物
验后概率
人工神经网络
检验医学
carcinoma of large intestine
tumor maker
test posterior probability
ANN
laboratory medicine
作者简介
郑旅芳（1982-），女，初级职称，研究方向：蛋白组学和实验诊断方向，Tel：15011289554。
通信作者：王开正。Tel：0830-3165730，E-mail：kaizhengw@yahoo．com．cn。
