[1]谭善娟),余春华),王威),等.基于人工神经网络的肿瘤标志蛋白芯片在肺癌辅助诊断中的应用*[J].郑州大学学报(医学版),2012,(06):762.
 TAN Shanjuan,YU Chunhua,WANG Wei,et al.Application of tumor marker protein biochip combined with artificial neural network in diagnosis of lung cancer[J].JOURNAL OF ZHENGZHOU UNIVERSITY(MEDICAL SCIENCES),2012,(06):762.
点击复制

基于人工神经网络的肿瘤标志蛋白芯片在肺癌辅助诊断中的应用*
分享到:

《郑州大学学报(医学版)》[ISSN:1671-6825/CN:41-1340/R]

卷:
期数:
2012年06期
页码:
762
栏目:
论著
出版日期:
2012-11-20

文章信息/Info

Title:
Application of tumor marker protein biochip combined with artificial neural network in diagnosis of lung cancer
作者:
谭善娟1)余春华2)王威1)吴拥军1)#吴逸明1)
1)郑州大学公共卫生学院卫生毒理学教研室 郑州 450001;
2)郑州大学第五附属医院呼吸内科 郑州 450052
Author(s):
TAN Shanjuan1)YU Chunhua2)WANG Wei1)WU Yongjun1)WU Yiming1)
1)Department of Health Toxicology,College of Public Health,Zhengzhou University,Zhengzhou 450001

2)Department of Respiratory Medicine,the Fifth Affiliated Hospital,Zhengzhou University,Zhengzhou 450052
关键词:
肺癌人工神经网络肿瘤标志蛋白芯片诊断
Keywords:
lung cancerartificial neural networktumor markerprotein biochipdiagnosis
分类号:
R734
摘要:
目的:应用人工神经网络技术,联合肿瘤标志蛋白芯片对肺癌及肺良性疾病进行诊断,建立肿瘤标志蛋白芯片联合人工智能的辅助诊断模型。方法:收集有肿瘤标志蛋白芯片检测记录的肺癌和肺良性疾病患者共102例,其中肺癌50例,肺良性疾病52例。利用人工神经网络技术,对9项指标进行联合检测,建立基于人工神经网络的肿瘤标志蛋白芯片智能诊断模型。结果:人工神经网络模型、判别分析和蛋白芯片检测系统对肺良性疾病和肺癌识别的准确度分别为88.0%、64.0%和60.0%,人工神经网络模型的ROC曲线下面积0.878,准确度较好,而判别分析模型的ROC曲线下面积(0.635)和肿瘤标志联合检测的ROC曲线下面积(0.596)均<0.7,准确度较差。结论:人工神经网络联合多肿瘤标志蛋白芯片检测系统建立的模型可以很好地区分肺癌和肺良性疾病,对肺癌的诊断和鉴别诊断效果优于判别分析和蛋白芯片检测系统。
Abstract:
Aim:To establish two classification models of artificial neural networks(ANN) and Fisher discrimination analysis,and to compare the differences among two models and the multiple tumor marker protein biochip detective system in the diagnosis of lung cancer.Methods:The clinical data and multiple tumor marker protein biochip detective system records of 102 lung disease patients(50 cases of lung cancer and 52 cases of benign pulmonary diseases) were retrospectively reviewed,and then the models of ANN and Fisher discrimination analysis were developed.Results:The accuracy of ANN,Fisher discrimination analysis and multiple tumor marker protein biochip detective system was 88.0%,64.0% and 600%.The area under ROC curve of ANN(0.878) was higher than that of Fisher discrimination analysis(0.635) and multiple tumor marker protein biochip detective system(0.596).Conclusion:The effects of ANN model established by multiple tumor marker protein biochip detective system are better than those of Fisher discrimination analysis and multiple tumor marker protein biochip detective system in discrimination of lung cancer.

参考文献/References:

[1] Liang Z,Wang HF,Wu AZ,et al.Clinical value of multitumor markers protein biochip in the diagnosis of pulmonary carcinoma[J].Nan Fang Yi Ke Da Xue Xue Bao,2010,30(11):2516

[2]周建光,杨梅.多肿瘤标志物蛋白芯片检测在肿瘤诊断中的临床应用及研究进展[J].中国医学检验杂志,2010,11(3):165

[3]张矗,吴逸明,吴拥军,等.人工神经网络技术在纤维支气管镜诊断肺癌中的应用[J].郑州大学学报:医学版,2010,45(1):113

[4]Zhang Z,Yu YH,Xu FJ,et al.Combining multiple serum tumor markers improves detection of stage Ⅰ epithelial ovarian cancer[J].Gynecol Oncol,2007,107(3):526

[5]Anderson B,Hardin JM,Alexander DD,et al.Comparison of the predictive qualities of three prognostic models of colorectal cancer[J].Front Biosci(Elite Ed),2010,2:849

[6]吴拥军,吴逸明,张振中,等.基于人工神经网络的“最优标志物群”在肺癌诊断中的应用研究[J].实用肿瘤杂志,2002,17(5):317

[7]周晓蕾,冯斐斐,张昭,等.人工神经网络模型在肺癌与胃癌或肠癌中的鉴别分析[J].实用医学杂志,2011,27(18):3312

[8]冯斐斐,吴拥军,聂广金,等.基于“优化肿瘤标志群”建立的人工神经网络模型对肺癌辅助诊断的作用[J].肿瘤防治研究,2011,38(6):709

[9]刘春艳,贾鹏,刘文君.应用表面增强激光解吸电离飞行时间质谱筛选急性特发性血小板减少性紫癜患儿血清生物标志物[J].实用儿科临床杂志,2011,26(15):1172

[10]张谦,单岩,王家祥,等.基于人工神经网络的血清蛋白质指纹图谱模型在先天性巨结肠患儿诊断中的应用[J].实用儿科临床杂志,2008,23(17):1382

相似文献/References:

[1]张矗),吴逸明)#,吴拥军),等.人工神经网络技术在纤维支气管镜诊断肺癌中的应用[J].郑州大学学报(医学版),2010,(01):113.
 ZHANG Chu),WU Yiming),WU Yongjun),et al.Application of artificial neural network in the diagnosis of lung cancer by bronchofibroscope[J].JOURNAL OF ZHENGZHOU UNIVERSITY(MEDICAL SCIENCES),2010,(06):113.
[2]王玉珍,吴逸明,李伟辉,等.热休克蛋白70hom基因+2 437(T/C)位点基因多态性与肺癌的关系*[J].郑州大学学报(医学版),2010,(02):219.
 WANG Yuzhen,WU Yiming,LI Weihui,et al.Heat shock protein 70hom gene+2 437(T/C) polymorphism and susceptibility to lung cancer in Chinese Han population[J].JOURNAL OF ZHENGZHOU UNIVERSITY(MEDICAL SCIENCES),2010,(06):219.
[3]刘艳华),王玲),王彦平),等.膳食因素与肺癌关系的病例对照研究[J].郑州大学学报(医学版),2009,(06):1260.
 LIU Yanhua),WANG Ling),WANG Yanping),et al.A casecontrol study on relationship between dietary intake and relative factors and lung cancer[J].JOURNAL OF ZHENGZHOU UNIVERSITY(MEDICAL SCIENCES),2009,(06):1260.
[4]马会军),李耀军),牛松涛),等.非小细胞肺癌40例介入治疗体会[J].郑州大学学报(医学版),2009,(05):1106.
[5]张菊娥)△,郭茂峰),张贵星),等.肺癌患者全血自由基代谢及其酶类测定*[J].郑州大学学报(医学版),2009,(04):766.
 ZHANG Jue),GUO Maofeng),ZHANG Guixing),et al.Detection of free radical metabolism and its protective enzymes of lung carcinoma patients[J].JOURNAL OF ZHENGZHOU UNIVERSITY(MEDICAL SCIENCES),2009,(06):766.
[6]刘天舟,张琳,王庆芳,等.血清CEA、NSE、SCCAg和CYFRA211联合检测对肺癌诊断的价值[J].郑州大学学报(医学版),2010,(05):809.
 LIU Tianzhou),ZHANG Lin),WANG Qingfang),et al.Diagnostic value of combined determination of serum CEA,NSE,SCCAg and CYFRA211 for lung cancer[J].JOURNAL OF ZHENGZHOU UNIVERSITY(MEDICAL SCIENCES),2010,(06):809.
[7]齐宇)△,李鑫),杨鲲鹏),等.支气管肺泡灌洗液中CYFRA211、NSE和CEA联合检测对肺癌的诊断价值[J].郑州大学学报(医学版),2010,(04):618.
 [J].JOURNAL OF ZHENGZHOU UNIVERSITY(MEDICAL SCIENCES),2010,(06):618.
[8]杜晓光,吕栋,谢新立,等.原发性肺癌合并骨转移242例骨痛分析[J].郑州大学学报(医学版),2010,(04):670.
 [J].JOURNAL OF ZHENGZHOU UNIVERSITY(MEDICAL SCIENCES),2010,(06):670.
[9]郑红伟),俞鹏辉),陈勇),等. 中晚期肺癌20例螺旋CT三期动态增强扫描观察[J].郑州大学学报(医学版),2011,(02):276.
 [J].JOURNAL OF ZHENGZHOU UNIVERSITY(MEDICAL SCIENCES),2011,(06):276.
[10]任振泰),崔静),李甸源)#,等. 多西紫杉醇对A549细胞的放射增敏作用[J].郑州大学学报(医学版),2011,(02):315.
 [J].JOURNAL OF ZHENGZHOU UNIVERSITY(MEDICAL SCIENCES),2011,(06):315.

备注/Memo

备注/Memo:
*国家自然科学基金资助项目30972457;河南省医学科技攻关计划基金资助项目2011020082
#通讯作者,男,1968年1月生,博士,教授,研究方向:肺癌的病因学、预防、早期诊断和综合治疗,Email:wuyongjun@zzu.edu.cn
更新日期/Last Update: 2013-07-03