摘要
肺癌是当今世界各国最常见的恶性肿瘤,其发病率和死亡率呈不断上升趋势,对人类的健康和生命构成了极大威胁。在中国,肺癌每年大约导致40万例患者死亡,已成为发病率和死亡率最高的恶性肿瘤。研究显示I期肺癌术后10年生存率可达到92%。然而肺癌早期不易诊断,恶性程度高,一经病理确诊多数已属晚期,失去手术治疗的最佳时机,总的5年生存率仅为15%左右。因此,要降低肺癌患者的死亡率关键在于肺癌的早期发现、早期诊断和早期治疗。肺癌的发生是多因素、多基因和多阶段发展的复杂过程,由于传统的影像学检查和支气管镜等检查手段存在敏感性、特异性和适用度等方面的局限,近年来国内外学者对肺癌早期预警或诊断相关的分子标志和多种肿瘤生物标志的联合检测做了大量有益的探索,以期找到更合理、敏感性和特异性更高的分子联合标志。
肺癌的发生是环境因素和遗传因素共同作用的结果,因此在寻找肺癌早期预警或诊断的生物标志时,也可以从两方面着手,即反映机体先天具有或后天获得的对外源性物质产生反应能力的易感性标志；反映早期生物效应、结构和/或功能改变以及疾病的效应标志。遗传因素属于前者,其作用体现在同一环境暴露中个体肿瘤易感性的差异,归根到底由基因多态所代表的遗传背景决定。另一方面,在很多情况下,许多分子事件的发生早于明显恶性表型的出现,因此,运用分子生物学的方法检测肺癌发生过程中的早期分子事件,从而发现癌前病变或早期癌变也被认为是肺癌早期预警最具应用前景的手段。肿瘤发生的早期生物效应包括了DNA甲基化和端粒损伤在内的遗传学和表观遗传学改变。
数据挖掘(Data Mining),又称数据库知识发现(Knowledge Discovery from Database, KDD),它是从大量数据中提取并挖掘未知的、有价值的模式或规律等知识的复杂过程。它通常与计算机科学有关,并通过统计、在线分析处理、情报检索、机器学习、专家系统(依靠过去的经验法则)和模式识别等诸多方法来实现上述目标。数据挖掘与传统数据分析有着本质的区别。数据挖掘是在没有明确的假设的前提下挖掘信息和发现知识。同时,通过数据挖掘得到的信息具有先前未知、有效及可实用3个特征。数据挖掘中的决策树和人工神经网络技术(Artificial Neural Networks, ANN)能够对数据信息进行大规模并行处理和分布式存储,且具有良好的自适应性、自组织性及较强的学习功能、联想功能和容错功能。在肿瘤的诊断方面,不仅能够起到检测可疑病变和分类的作用,还能挖掘用于检测和分类的潜在特征标志,为肿瘤的诊断做出建设性贡献。
本研究检测对象外周血中CYP1A1, GSTM1, GSTT1, mEH, XRCC1基因多态性、p16和RASSF1A基因甲基化水平及端粒相对长度,探讨5种基因多态性与p16、RASSF1A基因甲基化和端粒相对长度的相关关系,在此基础上应用数据挖掘技术,检测这些分子指标对肺癌早期预警的相关性,抽取可用于肺癌预警的有效特征,构建较为适合的预测模型,探讨是否有助于提高肺癌早期预警或诊断的正确率及联合检测对肺癌辅助诊断的意义,以实现肺癌早期预警、诊断和分类的自动化,为高危人群的筛查和临床肺癌诊断提供有价值的参考资料。
目的
1.探讨肺癌患者外周血I相代谢酶基因CYP1A1,Ⅱ相代谢酶基因GSTM1、GSTT1、mEH,及DNA修复酶基因XRCC1的多态基因型与肺癌易感之间的关系,探讨抑癌基因p16、RASSF1A甲基化及端粒相对长度与肺癌发生的关系,筛选出与肺癌发生相关的有效分子生物标志,找出对肺癌早期预警意义最大的几项,为肺癌的早期预警提供基础资料。
2.将数据挖掘技术和上述分子标志相结合,构建可“自动”处理信息的智能预警模型,为肺癌智能预警系统的研制开辟一条新途径,提高肺癌早期预警的准确率。
材料与方法
1.以251例肺癌患者和256例健康体检者为研究对象。
2.采用等位基因特异性扩增法(allele-specific amplification, ASA)检测CYP1A1-exon7位点多态性,采用多重PCR法检测GSTM1、GSTT1基因多态性,采用聚合酶链反应-限制性片段长度多态性(polymerase chain reaction-restriction fragment length polymorphism, PCR-RFLP)方法分别检测CYP1A1-Mspl位点、mEH-exon3、mEH-exon4、XRCC1-194、XRCC1-280及XRCC1-399位点基因多态性。采用实时荧光定量甲基化特异PCR (real-time methylation specific PCR, qMSP)技术检测p16和RASSF1A基因甲基化水平,采用荧光定量PCR法检测端粒相对长度。
3.应用SPSS12.0统计分析软件,采用x2检验、t检验、秩和检验、Logistic回归分析等方法对基因多态、甲基化水平和端粒相对长度的结果进行一般统计学分析处理,探讨基因多态性、DNA甲基化及端粒相对长度变化与肺癌发生的关系,筛选可能用于肺癌早期判别模型的有效指标。
4.将每组样本按3：1的比例随机分为训练集和测试集,将CYP1A1-exon7、GSTM1、mEH-exon3、XRCC1-194和XRCC1-280位点基因多态性、p16基因和RASSF1A基因甲基化水平、端粒长度及吸烟情况作为输入参数,用Fisher判别分析、决策树C5.0和反向传播神经网络算法(Back-Propagation, BP算法)分别对训练集进行训练建立模型,用训练好的模型对相应的测试集进行盲法预测,验证判别模型的优劣,最终建立肺癌早期智能化预警模型。
结果
1. GSTM1基因缺失型,CYP1A1-exon7、mEH-exon3、XRCC1-194及XRCC 1-280基因位点纯和突变型在病例组与对照组中的分布频率差异均有统计学意义(P<0.05),GSTM1基因缺失者与GSTM1基因阳性者相比发生肺癌的危险性升高(ORadj=1.727,95%CI：1.211-2.463)；携带CYP1A1-exon7 Ile/val+val/val基因型的个体较携带CYP1A1-exon7 Ile/Ile基因型的个体发生肺癌的危险性升高(ORadj1.727,95%CI：1.203-2.477);mEH-exon3突变基因型携带者与野生纯合型的个体相比发生肺癌的危险性升高(ORadj1.758,95%CI：1.194-2.589)；携带XRCC1-194 Arg/Trp+Trp/Trp基因型的个体较携带XRCC1-194 Arg/Arg基因型的个体发生肺癌的危险性升高(ORadj=1.542,95%CI：1.083-2.196)；XRCC1-280His/His基因型携带者较XRCC1-280 Arg/Arg+Arg/His基因型携带者发生肺癌的危险性升高(ORadj=2.941,95%CI：1.427-6.060)。CYPIA1-Msp1、GSTT1、mEH-exon4及XRCC 1-399多态基因型在病例组与对照组中的分布频率差异均无统计学意义(P>0.05)。基于5种基因多态性建立肺癌判别模型,结果为Fisher判别分析、决策树及ANN对训练集和预测集的准确率分别为63.59%、63.25%；95.64%、82.61%：84.1%、80.77%,Fisher判别分析、决策树及ANN模型的ROC曲线下面积(AUC)分别为0.627、0.836、0.821。
2.肺癌组外周血p16基因和RASSF1A基因甲基化水平及端粒相对长度分别为0.59(0.16～4.50)、27.62(9.09～52.86)、0.93±0.32,与对照组相比差异具有统计学意义(P<0.05)；p16基因和RASSF1A基因启动子区甲基化水平增高及端粒相对长度缩短与肺癌发生危险性增加有关；性别、年龄、吸烟情况、肺癌分期和病理类型与p16基因、RASSFIA基因甲基化及端粒长度无关(P>0.05)。基于上述指标建立肺癌判别模型,结果为Fisher判别分析、决策树及ANN对训练集和预测集的准确率分别为66.34%、65.82%;77.26%、75.45%；72.15%、71.72%,3种模型的AUC分别为0.660、0.782、0.759。
3. XRCC1-280位点不同基因型之间p16甲基化水平有差异,CYP1A1-exon7、GSTM1、mEH-exon3和XRCC1-280位点不同基因型之间RASSFIA基因甲基化水平不同,CYP1A1-exon7和GSTM1基因突变型与野生型相比端粒相对长度差异。基于上述综合指标建立肺癌判别模型结果显示,Fisher判别分析、决策树及ANN对训练集和预测集的准确率分别为72.15%、70.59%；93.88%、93%;92.96%、89.62%,3种模型的AUC分别为0.722、0.929、0.894。决策树模型对临床早期(I+II期)肺癌的判别准确率为96.36%,ANN模型为89.09%。
结论
1.CYP1A1-exon7、GSTM1、mEH-exon3、XRCC1-194和XRCC1-280基因位点的变异、p16和RASSFIA基因甲基化水平异常增高、端粒相对长度缩短与肺癌患癌危险度增加有关,上述指标组成肺癌早期预警模型的分子标志群。
2.数据挖掘技术联合肺癌发生相关的多角度分子事件建立模型对肺癌的判别准确性优于单方面分子标志的检测。
3.本文建立的多个肿瘤分子标志联合决策树和ANN技术的肺癌早期预警模型对肺癌的判别优于传统的Fisher判别方式,比常规的统计学方法更适合于临床数据的分析,准确度较高,可以用于肺癌早期预警。
Lung cancer is one of the most frequent malignancies in the world nowadays, its morbidity and mortality are continuously rising, and it constitutes a grave threat to human health. In China, there are about 400,000 people died every year because of lung cancer which morbidity and mortality is the highest in malignant tumors. Studies show that 10-year survival of postoperation can arrive to 92% in patients with stage I lung cancer. However, it is very difficult to diagnose lung cancer at the early stage, and also because of its high grade malignancy, lung cancer patients are usually diagnosed in the advanced stage and lose the best opportunity of operation, so that the total 5-year survival rate is only about 15%. So early detection, early diagnosis and early treatment are vital for lung cancer patients to reduce their mortality. The occurrence of lung cancer is a complex process involved in many factors, lots of genes and multiple steps. As tranditional methods including imageology and bronchial tube, et al. have limits in susceptibility, specificity and adaptability, in recent years a lot of scholars have devoted themselves to exploring new molecular marker and to combined detection of multiply tumor markers in order to find more reasonable and sensitive association.
Lung cancer occurs because of both environmental factors and genetic factors. So we search for biomarkers of early warning or diagnosis of lung cancer from two aspects, that is biomarkers of susceptibility and effect. Genetic factors belong to the former which is reflected in the difference of tumour susceptibility and is determined by genetic polymorphism. On the other hand, in many cases many molecular events happen before obvious malignant phenotype, so detecting early molecular events during the occurrence of lung cancer to discover precancerosis or canceration of early phase is also one of the most promising approach. Early biological effects during tumorigenesis include changes of genetics and epigenetics such as DNA methylation and telomere damage.
Data Mining, also known as Knowledge Discovery from Database, is a complex process which to extract and to mine unknown and valuable knowledge such as model or regular pattern from mass of data. It is usually related with computer science, and to discovery knowledge through statistics, on-line analysis, information retrieval, machine learning, expert system (relying on past rule of thumb) and pattern recognition etc. There is essential difference between data mining and traditional data analysis. Data mining is to excavate information and discover knowledge without clear hypothesis. Meanwhile, information gained from data mining is unknown, effective and practical. Decision tree and artificial neural networks techniques can parallel process and save large-scale data information distributedly, and also take on well self-adaption, self-organization and strong learning, association and fault-tolerance function. In tumour diagnosis aspect data moning techniques can not only detect suspicious lesion and type but also mine potential pathognomonic markers that constructively contribute to tumour diagnosis.
In this study genetic polymorphisms of CYP1A1, GSTM1, GSTT1, mEH and XRCC1 genes, p16 and RASSF1A gene methylation, and telomere length were detected in peripheral blood of lung cancer patients and health people to explore their correlationship. Then data mining techniques were used to detect the relevance between these molecular index and early warning or diagnoisis of lung cancer, to extract effective feature and construct suited prediction model of lung cancer, and to explore wheather it can contribute to increase accuracy rate of lung cancer early diagnosis and the significance of united detection used in auxiliary diagnosis of lung cancer. So that to automaticly early warn, diagnose and classify lung cancer and to provide valuable information in screening high risk populations and clinical diagnosis of lung cancer.
Objectives
1. To study the association between genetic polymorphism of metabolizing and DNA repairing enzymes and susceptibility to pulmonary cancer, to explore the association between p16, RASSF1A methylation and telomere length and occurrence of lung cancer. To screen out effective molecular biomarkers correlated with lung cancer and find the most significant index so as to come up with initial value for early warning or diagnosis of lung cancer.
2. Combining data mining techniques with above index to construct intelligentized model for diagnosis that can automaticly analyse information for increasing accuracy rate of early diagnosis of lung cancer.
Materials and methods
1.251 lung cancer patients and 256 health persons were chosen to be study subjects.
2. Using AS-PCR to detect genotype of CYP1A1-exon7, using multiplex PCR to detect genotype of GSTM1 and GSTT1, using PCR-RFLP to detect genotype of CYP1A1-Msp, mEH-exon3, mEH-exon4, XRCC1-194, XRCC1-280 and XRCC1-399. Using qMSP to detect methylation levels of p16 and RASSF1A, using RT-PCR to detect telomere length.
3. Using SPSS 12.0 statistic analysis software, using chi-square test, t test, rank sum test, Logistic regression to analyze the data, and to explore the association between the above index and lung cancer in order to screen out effective index used in early discrimination model of lung cancer.
4. Deviding the samples of each group into training set and testing set by 3:1, using Fisher discriminatory analysis, decision tree C5.0 and BP arithmetic to train the training set and build the model, then using the model to test the testing set by blind method in order to verify its odds, the intelligentized model was developed for early diagnosis of lung cancer.
Results
1. The frequencies of GSTM1-null, CYP1A1-exon7 mt/mt, mEH-exon3 mt/mt, XRCC1-194 Trp/Trp, XRCC1-280 His/His genotype in case group were significantly higher than those in control group (P<0.05), There was an increased risk of lung cancer for individuals carrying genotypes of GSTM1 (ORadj=1.727,95%CI: 1.211-2.463), CYP1A1-exon7 Ile/val+val/val (ORadj=1.727,95%CI:1.203-2.477), mEH-exon3 wt/mt+mt/mt(ORadj=1.758,95%CI:1.194-2.589), XRCC1-194 Arg/Trp +Trp/Trp (ORajd=1.542,95%CI:1.083-2.196) and XRCC1-280 His/His (ORadj=2.941, 95%CI:1.427-6.060) compared with subjects carrying genotypes of GSTM1 null, CYP1A1-exon7 Ile/Ile, mEH-exon3 wt/wt, XRCC1-194 Arg/Arg and XRCC1-280 Arg/Arg+Arg/His; There was no significant difference for CYP1A1-Msp1, GSTT1, mEH-exon4, XRCC1-399 genotype between the two groups (P>0.05). Building the model of lung cancer discrimination based on above index and The accuracy rate of Fisher, decision tree and ANN model for training set and testing set was (63.59%, 63.25%), (95.64%,82.61%), (84.1%,80.77%), respectively; AUC of the three models was 0.627 (Fisher),0.836 (decision tree),0.821 (ANN), repectively.
2. The level of p16, RASSF1A gene methylation and telomere length of peripheral blood in lung cancer group was 0.59 (0.16-4.50)、27.62 (9.09-52.86)、0.93±0.32, respectively, and there was significant difference between the case group and control group; The hypermethylation of p16 gene and RASSF1A gene and contraction in length of telomere was correlated with increasing risk of lung cancer; There was no significant association between sex, age, tobacco smoking, lung cancer stage, pathological types and hypermethylation of p16 gene, RASSF1A gene and telomere length (P>0.05). Building the model of lung cancer discrimination based on above index and the accuracy rate of Fisher, decision tree and ANN model for training set and testing set was (66.34%,65.82%); (77.26%,75.45%); (72.15%, 71.72%), respectively; AUC of the three models was 0.660(Fisher),0.782(decision tree),0.759(ANN), respectively.
3. The hepermethylation level of p16 gene was significantly variant in different genotypes of XRCC1-280; the hepermethylation level of RASSF1A gene was significantly variant in different genotypes of CYP1A1-exon7, GSTM1, mEH-exon3 and XRCC 1-280; the contraction in length of telomere was variant in different genotypes of CYP1A1-exon7 and GSTM1. Building the model of lung cancer discrimination based on above index and the accuracy rate of Fisher, decision tree and ANN model for training set and testing set was (72.15%,70.59%), (93.88%, 93%), (92.96%,89.62%), respectively; AUC of the three models was 0.722 (Fisher), 0.929 (decision tree),0.894 (ANN), respectively; the accuracy rate of decision tree and ANN model for clinical early stage (Ⅰ+Ⅱ) lung cancer was 96.36 and 89.09, respectively.
Conclusion
1. The genetic polymorphisms of CYP1A1-exon7, GSTM1, mEH-exon3, XRCC1-194 and XRCC1-280, the hypermethylation of p16 gene and RASSF1A gene and the contraction in length of telomere might contribute to the risk of developing lung caner; and the above index made up a tumour marker group for early diagnosis model of lung cancer.
2. The discriminative model of lung cancer based on multi-dimension molecular events related to the occurrence of lung cancer is superior to that based on unilateral molelular markers.
3. The diagnostic model of lung cancer based on multiple tumour markers and data mining techniques was superior to traditional discriminative pattern, and it was more suitable for analysis of clinical data than conventional statistics, and it could be used in early warning of lung cancer.
引文
[1]Yang L, Yang G, Zhou M, et al. Body mass index and mortality from lung cancer in smokers and nonsmokers:a nationally representative prospective study of 220,000 men in China. Int J Cancer,2009,125(9):2136-2143.
[2]Henschke CI, Yankelevitz DF, Libby DM, et al. Survival of patients with stage I lung cancer detected on CT screening. N Engl J Med,2006,355(17):1763-1771.
[3]Jemal A, Bray F, Center MM, et al. Global cancer statistics[J].CA Cancer J Clin.2011, 61(2):69-90.
[4]Jemal A, Siegel R, Ward E, et al. Cancer statistics,2009[J]. CA Cancer J Clin.2009, 59(4):225-249.
[5]Mascaux C, Peled N, Garg K, et al. Early detection and screening of lung cancer. Expert Rev Mol Diagn,2010,10(6):799-815.
[6]National Lung Screening Trial Research Team, Aberle DR, Berg CD, et al. The National Lung Screening Trial:overview and study design. Radiology,2011,258(1):243-253.
[7]Maziak D, Darling GE, Inculet RI, et al. A randomized controlled trial (RCT) of 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET) versus conventional imaging (CI) in staging potentially resectable non-small cell lung cancer (NSCLC). J Clin Oncol,2008,26(20 suppl):abstr 7502.
[8]Xiong Z, Xiong G, Man Y, et al. Detection of lung cancer by oral examination. Med Hypotheses,2010,74(2):346-347.
[9]Amann A, Corradi M, Mazzone P, et al. Lung cancer biomarkers in exhaled breath. Expert Rev Mol Diagn,2011,11 (2):207-217.
[10]Pavlova I, Hume KR, Yazinski SA, et al. Multiphoton microscopy as a diagnostic imaging modality for lung cancer. Proc Soc Photo Opt Instrum Eng,2010,7569:756918.
[11]Amos CI, Xu W, Spitz MR. Is there a genetic basis for lung cancer susceptibility? Recent Results Cancer Res,1999,151:3-12.
[12]Schwartz AG. Lung cancer:family history matters. Chest,2006,130(4):936-937.
[13]Hung RJ, McKay JD, Gaborieau V, et al. A susceptibility locus for lung cancer maps to nicotinic acetylcholine receptor subunit genes on 15q25. Nature,2008,452(7187):633-637.
[14]Thorgeirsson TE, Geller F, Sulem P, et al. A variant associated with nicotine dependence, lung cancer and peripheral arterial disease. Nature,2008,452(7187):638-642.
[15]Landi MT, Chatterjee N, Yu K, et al. A genome-wide association study of lung cancer identifies a region of chromosome 5p15 associated with risk for adenocarcinoma. Am J Hum Genet,2009,85(5):679-691.
[16]Yoon KA, Park JH, Han J, et al. A genome-wide association study reveals susceptibi lity variants for non-smal 1 cell lung cancer in the Korean population. Hum Mol Genet,2010, 19(24):4948-4954.
[17]Schwartz AG, Wenzlaff AS, Bock CH, et al. Admixture mapping of lung cancer in 1812 African-Americans. Carcinogenesis,2011,32(3):312-317.
[18]Kohno T, Kunitoh H, Shimada Y, et al. Individuals susceptible to lung adenocarcinoma defined by combined HLA-DQA1 and TERT genotypes. Carcinogenesis,2010,31(5): 834-841.
[19]Li Y, Sheu C.C, Ye Y, et al. Genetic variants and risk of lung cancer in never smokers:a genome-wide association study. Lancet Oncol,2010,11(4):321-330.
[20]Wu C, Hu Z, Yu D, et al. Genetic variants on chromosome 15q25 associated with lung cancer risk in Chinese populations. Cancer Res,2009,69(12):5065-5072.
[21]Hao B, Miao X, Li Y, et al. A novel T-77C polymorphism in DNA repair gene XRCC1 contributes to diminished promoter activity and increased risk of non-small cell lung cancer. Oncogene,2006,25(25):3613-3620.
[22]Yu D, Zhang X, Liu J, et al. Characterization of functional excision repair cross-comple-mentation group 1 variants and their association with lung cancer risk and prognosis. Clin Cancer Res,2008,14(9):2878-2886.
[23]Yang M, Guo H, Wu C, et al. Functional FEN1 polymorphisms are associated with DNA damage levels and lung cancer risk. Hum Mutat,2009,30(9):1320-1328.
[24]Guo Y, Zhang X, Yang M, et al. Functional evaluation of missense variations in the human MAD1L1 and MAD2L1 genes and their impact on susceptibility to lung cancer. J Med Genet, 2010,47(9):616-622.
[25]Sun T, Gao Y, Tan W, et al. A six-nucleotide insertion-deletion polymorphism in the CASP8 promoter is associated with susceptibility to multiple cancers. Nat Genet,2007,39(5): 605-613.
[26]Holliday R. DNA methylation and epigenotypes. Biochemistry (Mosc),2005,70(5):500-504
[27]王娟,陈秀华.表观遗传学的研究进展及其在抗肿瘤领域的应用.世界临床药物.2008,29(11)：683-687.
[28]Urban S V, Benevolenskaya E, Kiss J, et al. Beyond genetics--the emerging role of epigenetics and its clinical aspects. Orv Hetil.2012; 153(6):214-21.
[29]Choo KB. Epigenetics in disease and cancer. Malays J Pathol.2011; 33(2):61-70.
[30]Feil R, Fraga MF. Epigenetics and the environment:emerging patterns and implications. Nat Rev Genet.2012; 13(2):97-109.
[31]Banno K, Kisu I, Yanokura M, et al. Epigenetics and genetics in endometrial cancer:new carcinogenic mechanisms and relationship with clinical practice. Epigenomics.2012; 4(2):147-62.
[32]Trimarchi MP, Mouangsavanh M, Huang TH. Cancer epigenetics:a perspective on the role of DNA methylation in acquired endocrine resistance. Chin J Cancer.2011; 30(11):749-56.
[33]Terry MB, Delgado-Cruzata L, Vin-Raviv N, Wu HC, Santella RM. DNA methylation in white blood cells:association with risk factors in epidemiologic studies[J]. Epigenetics.2011, 6(7):828-837.
[34]Kim JK, Samaranayake M, Pradhan S. Epigenetic mechanisms in mammals [J]. Cell Mol Life Sci.2009,66(4):596-612.
[35]Goffin J, Eisenhauer E. DNA methyltransferase inhibitors-state of the art[J]. Ann Oncol. 2002,13(11):1699-1716.
[36]Robertson KD, Jones PA. DNA methylation:past, present and future directions[J]. Carcinogenesis.2000,21(3):461-467.
[37]Belinsky SA, Liechty KC, Gentry FD, et al. Promoter hypermethylation of multiple genes in sputum precedes lung cancer incidence in a high-risk cohort. Cancer Res,2006,66(6): 3338-3344.
[38]Yi JM, Dhir M, Guzzetta AA, et al. DNA methylation biomarker candidates for early detection of colon cancer[J]. Tumour Biol.2012,33(2):363-372.
[39]Jang JS, Choi YY, Lee WK, et al.Telomere length and the risk of lung cancer[J].Cancer Sci.2008,99(7):1385-1389.
[40]Hosgood HD, Cawthon R, He X, et al. Genetic variation in telomere maintenance genes, telomere length, and lung cancer susceptibility[J]. Lung Cancer.2008,66(2):157-161.
[41]Ngan PS, Wong ML, Lam W, et al. Medical data mining using evolutionary computation[J]. Artif Intell Med,1999,16(1):73-96.
[42]Ye J, Li T, Xiong T, et al. Using uncorrelated discriminant analysis for tissue classification with gene expression data[J]. IEEE/ACM Trans Comput Biol Bioinform,2004, 1(4):181-190.
[43]Veenman CJ, Reinders MJ. The nearest subclass classifier:a compromise between the nearest mean and nearest neighbor classifier[J]. IEEE Trans Pattern Anal Mach Intell,2005, 27(9):1417-1429.
[44]Dayhoff JE, DeLeo JM. Artificial neural networks:opening the black box[J]. Cancer,2001, 91(8 Suppl):1615-1635.
[45]Getz G, Gal H, Kela I, et al. Coupled two-way clustering analysis of breast cancer and colon cancer gene expression data[J]. Bioinformatics,2003,19(9):1079-1089.
[46]Zollanvari A, Cunningham MJ, Braga-Neto U, et al. Analysis and modeling of time-course gene-expression profiles from nanomaterial-exposed primary human epidermal keratinocytes[J]. BMC Bioinformatics,2009,10(Suppl 11):S10.
[47]冯敏.数据挖掘技术及其在医学上的应用[J].中国利·技信息.2008(12)：192-193.
[48]Monica D I, Luca M, Grossi E, et al. Artificial Neural Networks Allow the Use of Simultaneous Measurements of Alzheimer Disease Markers for Early Detection of the Disease[J]. J Trasl Med.2005,3:30.
[49]陈明.医学数据挖掘综述.医学信息.2008,21(1)：19-21.
[50]朱凌云,吴宝明.医学数据挖据的技术、方法及应用.生物医学工程学杂志,2003,20(3)：559-562.
[51]Matsuki Y, Nakamura K, Watanabe H, et al. Usefulness of an Artificial Neural Network for Differentiating Benign from Malignant Pulmonary Nodules on High-resolution CT: Evaluation with Receiver operating Characteristic Analysis. AJR Am J Roentgenol.2002, 178(3):657-663.
[52]胡灵芝.数据挖掘方法及其在医学领域中的应用.辽宁中医药大学学报.2010,12(7)：51-52.
[53]Yongjun Wu, Yiming Wu, Jing Wang, et al. An optimal tumor marker group-coupled artificial neural network for diagnosis of lung cancer[J]. Expert Systems with Applications. 2011(38):11329-11334.
[54]Yongjun Wu, Na Wang, Hongsheng Zhang, et al. Application of artificial neural networks in the diagnosis of lung cancer by computed tomography[J]. ICNC 2010.2010,147-153.
[55]冯斐斐,聂广金,吴拥军,等.基于6项肿瘤标志联合检测的3种分类模型判别肺癌的对比分析[J].卫生研究.2009,38(4)：429-432.
[56]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)：3312-3314.
[57]杨美琴,郁琳琳,余捷凯,等.人工神经网络肿瘤标志物模型的建立及应用研究[J].中华检验医学杂志.2005,28(5)：492-494.
[58]Aggarwal C, Langer CJ. Older age, poor performance status and major comorbidities:how to treat high-risk patients with advanced nonsmall cell lung cancer. Curr Opin Oncol.2012; 24(2):130-136.
[59]Begum S. Molecular changes in smoking-related lung cancer. Expert Rev Mol Diagn.2012; 12(1):93-106.
[60]Bailey-Wilson JE, Amos CI, Pinney SM, et al. A major lung cancer susceptibility locus maps to chromosome 6q23-25. Am J Hum Genet,2004,75(3):460-474.
[61]周新文,石云,周宜开.CYP1A1基因多态性与肺癌个体易感性研究[J].环境与职业医学.2002；19(6)：355-357.
[62]Lam TK, Ruczinski I, Helzlsouer K, et al. Copy number variants of GSTM1 and GSTT1 in relation to lung cancer risk in a prospective cohort study. Ann Epidemiol.2009; 19(8):546-552.
[63]Sreeja L, Syamala V, Hariharan S, et al. Possible risk modification by CYP1A1, GSTM1 and GSTT1 gene polymorphisms in lung cancer susceptibility in a South Indian population. J Hum Genet.2005; 50(12):618-627.
[64]曹燕燕,边建超.环氧化物水解酶基因多态与疾病遗传易感性研究进展.中华流行病学杂志.2004；25(4)：355-358.
[65]Lihong Yin, Yuepu Pu, Tingyun Liu, et al. Genetic polymorphisms of NAD(P)H quinine oxidoreduetase, CYP1A1 and microsomal epoxide hydrolase and lung cancer risk in Nanjing, China. Lung Cancer.2001; 33:133-141.
[66]尹立红,浦跃朴,林嫔嫔,等.肺癌易感性与NQO1、CYP1A1、mEH基因多态性的关系.环境与职业医学.2003；20(1)：22-25.
[67]Erkisi Z, Yaylim-Eraltan I, Turna A, et al. Polymorphisms in the microsomal epoxide hydrolase gene:role in lung cancer susceptibility and prognosis. Tumori. 2010;96(5):756-763.
[68]Thompson LH, West MG. XRCC1 keeps DNA from getting stranded[J]. Mutat Res.2000; 459(1):1-18.
[69]冷皓凡.数据挖掘技术在医学研究中的应用.实用临床医学,2009,10(4)：131-132.
[70]于长春.决策树模型在2型糖尿病患者脑梗死风险预测中的应用[J].中国卫生统计.2011,28(6)：683-684
[71]刘鑫,赵家刚,刘絮子.人工神经网络之BP模型算法实现[J].科技信息.2011,30285-30286.
[72]Jaiswal AK, Gonzalez FJ, Nebert DW. Human dioxin-inducible cytochrome P1-450: complementary DNA and amino acid sequence. Science.1985; 228(4695):80-83.
[73]Bartsch H, Rojas M, Nair U, et al. Genetic cancer susceptibility and DNA adducts:studies in smokers, tobacco chewers, and coke oven workers. Cancer Detect Prev.1999; 23(6):445-453.
[74]Bartsch H, Nair U, Risch A, et al. Genetic polymorphism of CYP genes, alone or in combination, as a risk modifier of tobacco-related cancers. Cancer Epidemiol Biomarkers Prev.2000; 9(1):3-28.
[75]Bufalo NE, Leite JL, Guilhen AC, et al. Smoking and susceptibility to thyroid cancer:an inverse association with CYP1A1 allelic variants. Endocr Relat Cancer.2006; 13(4):1185-1193.
[76]Song N, Tan W, Xing D, et al. CYP 1A1 polymorphism and risk of lung cancer in relation to tobacco smoking:a case-control study in China. Carcinogenesis.2001; 22(1):11-16.
[77]Shaffi SM, Shah MA, Bhat IA, et al. CYP1A1 polymorphisms and risk of lung cancer in the ethnic Kashmiri population [J]. Asian Pac J Cancer Prev.2009; 10(4):651-656.
[78]Wright CM, Larsen JE, Colosimo ML, et al. Genetic association study of CYP1A1 polymerphisms identifies risk haplotypes in nonsmall cell lung cancer[J]. Eur Respir J.2010; 35(1):152-159.
[79]Lee KM, Kang D, Clapper ML, et al. CYP1A1, GSTM1, and GSTT1 polymorphisms, smoking, and lung cancer risk in a pooled analysis among Asian populations [J]. Cancer Epidemiol Biomarkers Prev.2008; 17(5):1120-1126.
[80]Taioli E, Benhamou S, Boffetta P, et al. Polymorphisms in CYP1A1, GSTM1 GSTT1 and lung cancer below the age of 45 years[J]. Int J Epidemiology,2003,32(1):60-63.
[81]Hung R J, Boffetta P, Brockmoller J, et al. CYP1 A1 and GSTM1 genetic polymorphisms and lung cancer risk in Caucasian non-smokers:a pooled analysis[J]. Carcinogenesis,2003, 24(5):875-882.
[82]胡毅玲,张桥.细胞色素P4501AI基因多态性与肺癌遗传易感性的研究.中华医学遗传学杂志.1999；16：16-29.
[83]瞿永华,石永波,钟礼杰,等.非吸烟女性肺癌患者细胞色素P4501AI和GSTM1的基因型.肿瘤.1998；18：80-83.
[84]Honma HN, De Capitani EM, Perroud MW Jr, et al. Influence of p53 codon 72 exon 4, GSTM1, GSTT1 and GSTP1*B polymorphisms in lung cancer risk in a Brazilian population. Lung Cancer.2008; 61(2):152-162.
[85]梁戈玉,浦跃朴,尹立红.基因多态性在肺癌发生中交互作用.中国公共卫生.2007；23(8)：902-903.
[86]Kuljukka-Rabb T, Nylund L, Vaaranrinta R, et al. The effect of relevant genotypes on PAH exposure-related biomarkers. Carcinogenesis. J Expo Anal Environ Epidemiol.2002; 12(1):81-91.
[87]Erkisi Z, Yaylim-Eraltan I, Turna A, et al. Polymorphisms in the microsomal epoxide hydrolase gene:role in lung cancer susceptibility and prognosis. Tumori.2010; 96(5):756-763.
[88]Lin TS, Huang HH, Fan YH, et al. Genetic polymorphism and gene expression of microsomal epoxide hydrolase in non-small cell lung cancer. Oncol Rep.2007; 17(3): 565-572.
[89]Gsur A, Zidek T, Schnattinger K, et al. Association of microsomal epoxide hydrolase polymorphisms and lung cancer risk. Br J Cancer.2003; 89(4):702-706.
[90]Shen MR, Jones IM, Mohrenweiser H. Nonconservative amino acid substitution variants exist at polymorphic frequency in DNA repair genes in healthy humans. Cancer Res,1998, 58:604-608.
[91]Lamerdin JE, Montgomery MA, Stilwagen SA, et al. Genomic sequence comparison of the human and mouse XRCC1 DNA repair gene regions. Genomics,1995,25:547-554.
[92]David-Beabes GL, London SJ. Genetic polymorphism of XRCC1 and lung cancer risk among African-Americans and Caucasians. Lung Cancer,2001,34:333-339.
[93]金明娟,陈坤,张扬,等XRCC1单核苷酸多态性与结直肠癌风险的关系.癌症,2007,26：274-279.
[94]曾小云,余红平,仇小强,等XRCC1基因多态性与肝细胞癌的病例对照研究Chin J Dis Control Prev,2010.14：760-763.
[95]张文娟,吴逸明,吴拥军.DNA修复基因XRCC1多态与肺癌易感性.中国公共卫生,2005,21：561-563.
[96]Hong YC, Lee KH, Kim WC, et al. Polymorphisms of XRCC1 gene, alcohol consumption and colorectal cancer. Int J Cancer,2005,116:428-432.
[97]Pachouri SS, Sobti RC, Kaur P, et al. Contrasting impact of DNA repair gene XRCC1 polymorphisms Arg399Glu and Arg194Trp on the risk of lung cancer in the north-India population. DNA Cell Biol,2007,26:186-191.
[98]Ratnasinghe D, Yao SX, Tangrea JA, et al. Polymorphisms of the DNA repair gene XRCC1 and lung cancer risk. Cancer Epidemiol Biomarkers Prev,2001,10:119-123.
[99]Divine K, Gilliland FD, Crowell RE, et al. The XRCC1399 glutamine allele is a risk factor for adenocarcinoma of the lung. Mutat Res,2001,461:273-278.
[100]Zhang X, Mao X, Liang G, et al. Polymorphism in DNA base excision repair genes ADPRT and XRCC1 and risk of lung cancer[J]. Cancer Res,2005,65(3):722-726.
[101]Yin J, Vogel U, Ma Y, et al. The DNA repair gene XRCC1 and genetic susceptibility of lung cancer in a northeastern Chinese population. Lung Cancer,2007,56:153-160.
[102]Schneider J, Classen V, Bernges U, et al. XRCC1 polymorphism and lung cancer risk in relation to tobacco smoking. Int J Mol Med,2005,16:709-716.
[103]David-Beabes GL, London SJ. Genetic polymorphism of XRCC1 and lung cancer risk among African-Americans and Caucasians. Lung Cancer,2001,34:333-339.
[104]Hung RJ, Brennau P, Canzian F, et al. Large-scale investigation of base excision repair genetic polymorphisms and lung cancer risk in a multicenter-study. J Nat Cancer Inst,2005, 97:567-571.
[105]Wang JJ, Zheng Y, Sun L, et al. CYP1A1 Ile462Val polymorphism and susceptibility to lung cancer:a meta-analysis based on 32 studies. Eur J Cancer Prev.2011; 20(6):445-452.
[106]Zhan P, Wang Q, Qian Q, et al. CYP1A1 MspI and exon7 gene polymorphisms and lung cancer risk:An updated meta-analysis and review. J Exp Clin Cancer Res.2011; 30(1):99. [Epub ahead of print]
[107]Gervasini G, San Jose C, Carrillo JA, et al. GST polymorphisms interact with dietary factors to modulate lung cancer risk:study in a high-incidence area. Cabanillas A. Nutr Cancer. 2010;62(6):750-758.
[108]Schneider J, Classen V, Helmig S. XRCC1 polymorphism and lung cancer risk. Expert Rev Mol Diagn.2008; 8(6):761-780.
[109]Petty TL. Screening strategies for early detection of lung cancer:the time is now. JAMA, 2000,284(15):1977-1980.
[110]Amornsiripanitch N, Hong S, Campa MJ, et al. Complement factor H autoantibodies are associated with early stage NSCLC. Clin Cancer Res,2010,16(12):3226-3231.
[111]Agarwal M, Brahmanday G, Bajaj SK, et al. Revisiting the prognostic value of preoperative (18)F-fluoro-2-deoxyglucose ((18)F-FDG) positron emission tomo-graphy (PET) in early-stage (Ⅰ & Ⅱ) non-small cell lung cancers (NSCLC). Eur J Nucl Med Mol Imaging, 2010,37(4):691-698.
[112]Ikeda S, Tsuboi E, Ono R, et al. Flexible bronchofiberscope. Jpn J Clin Oncol,2010,40(9): 55-64.
[113]Nobuhisa I, Yataro D, Wataru Y, et al. ADAM8 as a novel serological and histochemical marker for lung cancer[J]. Clin Cancer Res,2004,10:8363-8370.
[114]张红升.人工神经网络技术在肺癌CT诊断中的应用[D].郑州：郑州大学公共卫生学院,2007.
[115]冯斐斐,聂广金,吴拥军,等.基于6项肿瘤标志联合检测的3种分类模型判别肺癌的对比分析.卫生研究.2009,38(4)：429-432.
[116]林向阳,数据挖掘中的决策树算法比较研究.中国科技信息.2010,2：94-95.
[117]李芳,李一嫒,王冲.不确定数据的决策树分类算法[J].计算机应用.2009；(11)：3092-3095.
[118]Patel JL, Goyal RK. Applications of artificial neural networks in medical science[J]. Curr Clin Pharmacol,2007,2(3):217-226.
[119]Leighty RE, Runfeldtmj, Berndtd J, et al. Use of artificial neural networks to determine cognitive impairment and therapeutic effectiveness in Alzheimer's transgenic mice[J]. J Neurosci Methods,2008,167:358-366.
[120]白雪峰.基于人工神经网络技术的肿瘤标志群在肝癌辅助诊断中的应用.郑州.郑州大学公共卫生学院.2010.
[121]董超雄,肖晓旦,陈先来.判别分析与决策树在医院信息系统中的应用比较研究[J].现代图书情报技术,2006,12：72-77.
[122]Luk JM, Lam BY, Lee NPY, et al. Artificial neural networks and decision tree model analysis of liver cancer proteomes[J]. Biochem Biophys Res Commun,2007,361:68-73.
[123]Jiawei Han, Micheline Kamber. Data Mining Concepts and Techniques[M]. Morgan Kaufmann Publishers,2000:94.
[124]Kantardzic M. Data Mining Concepts, Models, Methods, and Algorithms[M]. IEEE Press, 2002:76.
[125]刘昆,刘业政.基于决策树的医疗数据分析[J].计算机工程,2002,28(2)：41-43.
[126]姜成志,叶明凤,顾泽元.基于决策树学习的智能机器人控制方法[J].计算机工程与设计,2002,23(10)：24-26.
[127]梁华金,申深,陈海雯.基于决策树的选案分析模型设计[J].现代计算机,2002,6(141)：21-23.
[128]孙长嵩,董西国,张健沛.一个基于粗糙集和决策树的最简分类规则集生成算法[J].哈尔滨工程大学学报,2002,23(5)：87-91.
[129]孙贵香,袁肇凯.人工神经网络在中医证候研究中的应用[J].中华中医药学刊,2007,25(7)：1450-1452.
[130]黄粤,高颖,马斌.中医证候研究常用数据挖掘方法述评.中医药学报.2010,38(3)：6-10.
[131]吴秀艳,王天芳,赵燕,等.数理分析方法在证候研究中的运用探析[J].江苏中医药,2007,39(7)：53-55.
[132]刘桂芝.血浆RASSF1A和p16基因高甲基化对非小细胞肺癌的诊断价值[D].郑州.郑州大学公共卫生学院.2007.
[133]Banno K, Kisu I, Yanokura M, et al. Epigenetics and genetics in endometrial cancer:new carcinogenic mechanisms and relationship with clinical practice. Epigenomics.2012; 4(2):147-162.
[134]Schnekenburger M, Diederich M. Epigenetics Offer New Horizons for Colorectal Cancer Prevention. Curr Colorectal Cancer Rep.2012; 8(1):66-81.
[135]Crea F, Nobili S, Paolicchi E, et al. Epigenetics and chemoresistance in colorectal cancer:an opportunity for treatment tailoring and novel therapeutic strategies. Drug Resist Updat.2011; 14(6):280-296.
[136]Weber W. Cancer epigenetics. Prog Mol Biol Transl Sci.2010; 95:299-349.
[137]Schmiemann V, Bocking A, Kazimirek M, Onofre AS, Gabbert HE, Kappes R, Gerharz CD, Grote HJ. Methylation assay for the diagnosis of lung cancer on bronchial aspirates:a cohort study[J]. Clin Cancer Res.2005,11(21):7728-7734.
[138]Daskalos A, Nikolaidis G, Xinarianos G, Savvari P, Cassidy A, Zakopoulou R, Kotsinas A, Gorgoulis V, Field JK, Liloglou T. Hypomethylation of retrotransposable elements correlates with genomic instability in non-small cell lung cancer[J]. Int J Cancer.2009,124(1):81-87.
[139]Kimmins S, Sassone-Corsi P. Chromatin remodelling and epigenetic features of germ cells[J]. Nature.2005,434(7033):583-589
[140]Koutsimpelas D, Pongsapich W, Heinrich U, Mann S, Mann WJ, Brieger J. Promoter methylation of MGMT, MLH1 and RASSF1A tumor suppressor genes in head and neck squamous cell carcinoma:pharmacological genome demethylation reduces proliferation of head and neck squamous carcinoma cells[J]. Oncol Rep.2012,27(4):1135-1141.
[141]Harte AL, da Silva NF, Miller MA, et al. Telomere length attrition, a marker of biological senescence, is inversely correlated with triglycerides and cholesterol in South asian males with type 2 diabetes mellitus. Exp Diabetes Res.2012; 2012:895185.
[142]Zekry D, Krause KH, Irminger-Finger I, et al. Telomere length, comorbidity, functional, nutritional and cognitive status as predictors of 5 years post hospital discharge survival in the oldest old. J Nutr Health Aging.2012; 16(3):225-230.
[143]Longhese MP, Anbalagan S, Martina M, et al. The role of shelterin in maintaining telomere integrity. Front Biosci.2012; 17:1715-1728.
[144]Hoffmann J, Spyridopoulos I. Telomere length in cardiovascular disease:new challenges in measuring this marker of cardiovascular aging. Future Cardiol.2011; 7(6):789-803.
[145]Shen M, Cawthon R, Rothman N, et al. A prospective study of telomere length measured by monochrome multiplex quantitative PCR and risk of lung cancer. Lung Cancer.2011; 73(2):133-137.
[146]Jang JS, Choi YY, Lee WK, et al. Telomere length and the risk of lung cancer. Cancer Sci. 2008; 99(7):1385-1389.
[147]Comandini A, Marzano V, Curradi G, et al. Markers of anti-oxidant response in tobacco smoke exposed subjects:a data-mining review. Pulm Pharmacol Ther. 2010; 23(6):482-492.
[148]Dalan D. Clinical data mining and research in the allergy office. Curr Opin Allergy Clin Immunol.2010; 10(3):171-177.
[149]Hsu HS, Chen TP, Hung CH, et al. Characterization of a multiple epigenetic marker panel for lung cancer detection and risk assessment in plasma[J]. Cancer.2007,110(9): 2019-2026.
[150]Shenker N, Flanagan JM. Intragenic DNA methylation:implications of this epigenetic mechanism for cancer research. Br J Cancer.2012; 106(2):248-253.
[151]Egger G, Wielscher M, Pulverer W, et al. DNA methylation testing and marker validation using PCR:diagnostic applications. Expert Rev Mol Diagn.2012; 12(1):75-92.
[152]Lu F, Zhang HT. DNA methylation and nonsmall cell lung cancer. Anat Rec (Hoboken).2011; 294(11):1787-1795.
[153]Gonzalez-Ramirez I, Garcia-Cuellar C, Sanchez-Perez Y, et al. DNA methylation in oral squamous cell carcinoma:molecular mechanisms and clinical implications. Oral Dis.2011; 17(8):771-778.
[154]Terry MB, Delgado-Cruzata L, Vin-Raviv N, et al. DNA methylation in white blood cells: association with risk factors in epidemiologic studies. Epigenetics.2011; 6(7):828-837.
[155]Lewandowska J, Bartoszek A. DNA methylation in cancer development, diagnosis and therapy--multiple opportunities for genotoxic agents to act as methylome disruptors or remediators. Mutagenesis.2011; 26(4):475-487.
[156]Chen ZX, Riggs AD. DNA methylation and demethylation in mammals. J Biol Chem.2011; 286(21):18347-18353.
[157]Senner CE. The role of DNA methylation in mammalian development. Reprod Biomed Online.2011; 22(6):529-535.
[158]Watanabe Y, Maekawa M. Methylation of DNA in cancer. Adv Clin Chem.2010; 52: 145-167.
[159]Draht MX, Riedl RR, Niessen H, et al. Promoter CpG island methylation markers in colorectal cancer:the road ahead. Epigenomics.2012; 4(2):179-194.
[160]Ricketts CJ, Morris MR, Gentle D, et al. Genome-wide CpG island methylation analysis implicates novel genes in the pathogenesis of renal cell carcinoma. Epigenetics.2012; 7(3):278-290.
[161]Yokoyama S, Kitamoto S, Yamada N, et al. The application of methylation specific electrophoresis (MSE) to DNA methylation analysis of the 5'CpG island of mucin in cancer cells. BMC Cancer.2012; 12:67.
[162]Marx J. A challenge to p16 gene as a major tumor suppressor. Science.1994; 264(5167):1846.
[163]Hu YH, Zhang CY, Tian Z, et al. Aberrant protein expression and promoter methylation of p 16 gene are correlated with malignant transformation of salivary pleomorphic adenoma. Arch Pathol Lab Med.2011; 135(7):882-889.
[164]Hong SM, Choi J, Ryu K, et al. Promoter hypermethylation of the p16 gene and loss of its protein expression is correlated with tumor progression in extrahepatic bile duct carcinomas. Arch Pathol Lab Med.2006; 130(1):33-38.
[165]He XS, Rong YH, Su Q, et al. Expression of p16 gene and Rb protein in gastric carcinoma and their clinicopathological significance. World J Gastroenterol.2005; 11(15):2218-2223.
[166]Nemtsova MV, Zemliakova VV, Kuznetsova EV, et al. Correlation of pl6/INK4a gene damages and protein expression in the tumor tissue of sporadic breast cancer. Arkh Patol. 2008; 70(4):6-9.
[167]Mokrowiecka A, Wierzchniewska-Lawska A, Smolarz B, et al. p16 gene mutations in Barrett's esophagus in gastric metaplasia-intestinal metaplasia-dysplasia-adenocarcinoma sequence. Adv Med Sci.2012:1-6.
[168]Rayess H, Wang MB, Srivatsan ES. Cellular senescence and tumor suppressor gene p16. Int J Cancer.2012; 130(8):1715-1725.
[169]Verdoodt B, Sommerer F, Palisaar RJ, et al. Inverse association of p16 INK4a and p14 ARF methylation of the CDKN2a locus in different Gleason scores of prostate cancer. Prostate Cancer Prostatic Dis.2011; 14(4):295-301.
[170]Guan RJ, Fu Y, Holt PR, et al. Association of K-ras mutations with p16 methylation in human colon cancer. Gastroenterology.1999; 116(5):1063-1071.
[171]Calmon MF, Colombo J, Carvalho F, et al. Methylation profile of genes CDKN2A (p14 and p16), DAPK1, CDH1, and ADAM23 in head and neck cancer. Cancer Genet Cytogenet. 2007;173(1):31-37.
[172]Wakabayashi T, Natsume A, Hatano H, et al. p16 promoter methylation in the serum as a basis for the molecular diagnosis of gliomas. Neurosurgery.2009; 64(3):455-461.
[173]Vidaurreta M, Maestro ML, Sanz-Casla MT, et al. Inactivation of p16 by CpG hypermethylation in renal cell carcinoma. Urol Oncol.2008; 26(3):239-245.
[174]Shin KC, Lee KH, Lee CH, et al. MAGE A1-A6 RT-PCR and MAGE A3 and p16 methylation analysis in induced sputum from patients with lung cancer and non-malignant lung diseases. Oncol Rep.2012; 27(4):911-916.
[175]Georgiou E, Valeri R, Tzimagiorgis G, et al. Aberrant p16 promoter methylation among Greek lung cancer patients and smokers:correlation with smoking. Eur J Cancer Prev.2007; 16(5):396-402.
[176]Wang J, Walsh G, Liu DD, et al. Expression of Delta DNMT3B variants and its association with promoter methylation of p16 and RASSFIA in primary non-small cell lung cancer. Cancer Res.2006; 66(17):8361-8366.
[177]Pfeifer GP, Yoon JH, Liu L, et al. Methylation of the RASSFIA gene in human cancers. Biol Chem.2002; 383(6):907-914.
[178]Lee SM, Lee WK, Kim DS, et al. Quantitative promoter hypermethylation analysis of RASSFIA in lung cancer:comparison with methylation-specific PCR technique and clinical significance. Mol Med Report.2012; 5(1):239-244.
[179]Niklinska W, Naumnik W, Sulewska A, et al. Prognostic significance of DAPK and RASSFIA promoter hypermethylation in non-small cell lung cancer (NSCLC). Folia Histochem Cytobiol.2009; 47(2):275-280.
[180]杨振华.28个肿瘤相关基闪启动子CpG岛甲基化及转录与非小细胞肺癌的相关性的研究.复旦大学：呼吸内科.2004.
[181]Belinsky SA, Nikula KJ, Palmisano WA, et al. Aberrant methylation of p16 (INK4a) is all early event in lung cancel and a potential biomarker for early diagnosis[J]. Proc Natl Acad Sci USA.1998,95(20):11891-11896.
[182]Eads CA, Lord RV, Kurumboor SK, et al. Fields of aberrant CPG island hypermethylation in Barrett's esophagus and associated adenocarcinoma[J]. Cancer Res,2000,60(18): 5021-5026.
[183]Zochbauer-Muller S, Lam S, Toyooka S, et al. Aberrant methylation of multiple genes in the upper aerodigestive tract epithelium of heavy smokers[J]. Int J Cancer.2003,107:612-616.
[184]Palmisano WA, Divine KK, Saccomarmo G, et al. Predicting lung cancer by detecting aberrant promoter methylation in sputum[J]. Cancer Res.2000,60(21):5954-5958.
[185]亢春彦FHIT、p16基因甲基化与肺癌关系的研究[D].郑州.郑州大学公共卫生学院.2004.
[186]宾萍.多环芳烃暴露对端粒长度的影响及易感性生物标志研究[D].[博士学位论文].北京,中国疾病预防控制中心,2008.
[187]Raynaud CM. Telomere shortening is correlated with the DNA damage response and telomeric protein down-regulation in colorectal preneoplastic lesions[J]. Ann Oncol,2008, 19(11):1875-1881.
[188]Aubert G, PM Lansdorp. Telomeres and aging[J]. Physiol Rev,2008,88(2):557-579.
[189]Desmaze C. Telomere-driven genomic instability in cancer cells[J]. Cancer Lett,2003, 194(2):173-182.
[190]耿志华,张敦华.端粒酶与肺癌的诊断和预后[J].国外医学：呼吸系统分册,2002,22(1)：1-3.
[191]Wentzensen IM, Mirabello L. The association of telomere length and cancer:a meta-analysis [J]. Cancer Epidemiol Biomarkers Prev,2011,20(6):1238-1250.
[192]Jang JS, Choi YY, Lee WK et al. Telomere length and the risk of lung cancer [J]. Cancer Sci, 2008,99(7):1385-1389
[193]Southworth H, O'Connell M. Data mining and statistically guided clinical review of adverse event data in clinical trials. J Biopharm Stat.2009; 19(5):803-817.
[194]Stiglic G, Kocbek S, Pernek I, et al. Comprehensive decision tree models in bioinformatics. PLoS One.2012; 7(3):e33812.
[195]谢邦昌.数据挖掘Clementine应用研究[M].北京：机械工业出版社,2008,19.
[196]于长春,贺佳等.数据挖掘技术在医学领域中的应用.第二军医大学学报,2003,24：1250-1252.
[197]孙立伶,陆文奇.胃癌肿瘤标志物的研究新进展.当代医学.2010,16(27)：10-11.
[198]Pongtheerat T, Pakdeethai S, Purisa W, et al. Promoter methylation and genetic polymorphism of glutathione S-transferase P1 gene (GSTP1) in Thai breast-cancer patients. Asian Pac J Cancer Prev.2011; 12(10):2731-2734.
[199]Lima LM, de Souza LR, da Silva TF, et al. DNA repair gene excision repair cross complementing-group 1 (ERCC1) in head and neck squamous cell carcinoma:analysis of methylation and polymorphism (G19007A), protein expression and association with epidemiological and clinicopathological factors. Histopathology.2012; 60(3):489-496.
[200]Hsu CP, Hsu NY, Lee LW, et al. Ets2 binding site single nucleotide polymorphism at the hTERT gene promoter--effect on telomerase expression and telomere length maintenance in non-small cell lung cancer. Eur J Cancer.2006; 42(10):1466-1474.
[201]宾萍,冷曙光,程娟,等.多环芳烃接触工人外周血全基因组DNA端粒长度与代谢 相关基因多态性的关系.中华劳动卫生职业病杂志.2011,29(6)：401-404.
[202]吴春琼.决策树与神经网络的分类比较.福建电脑.2010(7)：53-54.
[203]赵雪清,安晓东.决策树与人工神经网络的对比分析.电脑开发与应用.2007；20(11)：13-15.
[1]洪文学,李佳书,严衍玲.人工神经网络在肿瘤检测和诊断中的应用研究进展.北京生物医学工程.2007,26(4)：446-449.
[2]李丽霞,张敏,郜艳晖,等.人工神经网络在医学研究中的应用[J].数理医药学杂志,2009,22(1)：80-82.
[3]王伟.人工神经网络原理-入门与应用[M].北京：北京航空航天大学出版社,1995.
[4]吴拥军,吴逸明,张振中.人工网络技术在肺癌诊断中的应用研究[J].中华微生物学和免疫学杂志.2003,23(8)：646-649.
[5]余雪丽.神经网络与实例学习.中国铁道出版社,1996.
[6]黄德生,周宝森,刘延龄,等.BP人工神经网络用于肺鳞癌预后预测.中国卫生统计.2000,17(6)：337-340.
[7]白耀辉,陈明.利用自组织特征映射神经网络进行可视化聚类[J].计算机仿真.2006,23(1)：180-183.
[8]Shen S, Sandham W, Granat M, et al. MRI fuzzy segmentation of brain tissue using neighborhood attraction with neural-network optimization. IEEE Trans Inf Technol Biomed. 2005; 9(3):459-467.
[9]袁金秋,刘雅莉,杨克虎.基于人工神经网络的数据挖掘技术在临床中应用进展.图书与情报.2010,(3)：95-98.
[10]Acton PD, Newberg A. Artificial neural network classifier for the diagnosis of Parkinson's disease using [99mTc]TRODAT-1 and SPECT. Phys Med Biol.2006; 51(12):3057-3066.
[11]Gutte H, Jakobsson D, Olofsson F, et al. Automated interpretation of PET/CT images in patients with lung cancer. Nucl Med Commun.2007; 28(2):79-84.
[12]Abe H, Ashizawa K, Li F, et al. Artificial neural networks (ANNs) for differential diagnosis of interstitial lung disease:results of a simulation test with actual clinical cases. Acad Radiol. 2004; 11(1):29-37.
[13]Eggers KM, Ellenius J, Dellborg M, et al. Artificial neural network algorithms for early diagnosis of acute myocardial infarction and prediction of infarct size in chest pain patients. Int J Cardiol.2007; 114(3):366-374.
[14]杨盈赤.胰腺癌患者血清肿瘤标志物检测的临床价值研究.2007.中国协和医科大学,北京协和医学院,清华大学医学部,中国医学科学院：外科学.
[15]Srinivasan V, Eswaran C, Sriraam N, et al. Approximate entropy-based epileptic EEG detection using artificial neural networks. IEEE Trans Inf Technol Biomed.2007; 11(3):288-295.
[16]Kara S, Guven A, Oner AO. Utilization of artificial neural networks in the diagnosis of optic nerve diseases. Comput Biol Med.2006; 36(4):428-437.
[17]Hu Y, Zhang S, Yu J, et al. SELDI-TOF-MS:the proteomics and bioinformatics approaches in the diagnosis of breast cancer. Breast.2005; 14(4):250-255.
[18]杨美琴,郁琳琳,余捷凯,等.人工神经网络肿瘤标志物模型的建立及应用研究.中华 检验医学杂志.2005,28(5)：492-494.
[19]奉镭,邓明明,王开正,等.血清蛋白质谱结合人工神经网络在胃癌诊断中的研究.中国医师进修杂志.2010,33(4)：13-15.
[20]Yu JK, Chen YD, Zheng S. An integrated approach to the detection of colorectal cancer utilizing proteomics and bioinformatics. World J Gastroenterol.2004; 10(21):3127-3131.
[21]施明辉,周昌乐.人工神经网络在中医诊断中的应用现状与趋势[J].中国中医药信息杂志.2007,14(1)：2-5.
[1]Beaglehole R, Bonita R, Magnusson R. Global cancer prevention:an important pathway to global health and development. Public Health.2011; 125(12):821-831.
[2]支修益.我国肺癌流行病学现状分析[J].中国处方药.2009,(2)：56-57.
[3]Kumar M, Agarwal SK, Goel SK. Lung cancer risk in north Indian population:role of genetic polymorphisms and smoking. Mol Cell Biochem.2009; 322(1-2):73-79.
[4]李代蓉,周清华,等.肺癌遗传易感性的研究进展[J].中国肺癌杂志.2003,6(2)：158-162.
[5]Rotunno M, Yu K, Lubin JH, et al. Phase I metabolic genes and risk of lung cancer:multiple polymorphisms and mRNA expression. PLoS One.2009; 4(5):e5652.
[6]Yang M, Choi Y, Hwangbo B, et al. Combined effects of genetic polymorphisms in six selected genes on lung cancer susceptibility. Lung Cancer.2007; 57(2):135-142.
[7]Ginsberg G, Smolenski S, Hattis D, et al. Genetic Polymorphism in Glutathione Transferases (GST):Population distribution of GSTM1, T1, and P1 conjugating activity. J Toxicol Environ Health B Crit Rev.2009; 12(5-6):389-439.
[8]Ginsberg G, Angle K, Guyton K, et al. Polymorphism in the DNA repair enzyme XRCC1: utility of current database and implications for human health risk assessment. Mutat Res. 2011; 727(1-2):1-15.
[9]Shaffi SM, Shah MA, Bhat IA, et al. CYP1A1 polymorphisms and risk of lung cancer in the ethnic Kashmiri population. Asian Pac J Cancer Prev.2009; 10(4):651-656.
[10]Wright CM, Larsen JE, Colosimo ML, et al. Genetic association study of CYP1A1 polymorphisms identifies risk haplotypes in nonsmall cell lung cancer. Eur Respir J.2010; 35(1)：152-159.
[11]钱碧云,韩宏伟,谷峰,等CYP1A1 GSTM1基因多态性和吸烟与肺癌易感性关系的病例对照研究.中国肿瘤临床.2006,33(9)：500-502.
[12]夏觅真,薛绍礼,金永堂,等.肺癌患者与非肺癌人群CYP1A1基因Msp I位点多态性.现代医药卫生.2007,23(21)：3164-3165.
[13]王德全,陈思东,汪保国,等.广州地区182例汉族人细胞色素P4501A1和2E1基因多态性与肺癌关系的病例对照研究[J].中国肺癌杂志,2006,9(6)：497-501.
[14]McErlean A, Ginsberg MS. Epidemiology of lung cancer. Semin Roentgenol.2011; 46(3):173-177.
[15]Lee KM, Kang D, Lee SJ, et al. Interactive effect of genetic Polymorphism of glutathione S transferase M1 and smoking on squamous Cell lung cancer risk in Korea [J]. Oncol Rep, 2006,16(5):1035-1039.
[16]Lee KM, Kang D, Clapper ML, et al. CYP1A1, GSTM1, and GSTP1 polymorphisms, smoking, and lung cancer risk in a pooled analysis Among Asian populations [J]. Cancer Epidemiology Biomarkers and Prevention.2008,17(5):1120-1126.
[17]Ada AO, Kunak SC, Hancer F, et al. Association between GSTM1, GSTT1, and GSTP1 polymorphisms and lung cancer risk in a Turkish population. Mol Biol Rep.2012; 39(5):5985-5993.
[18]姚武,王娜,吴拥军,等GSTM1、GSTT1基因缺失与肺癌易感性的关系[J].中国公共卫生.2006,22(9)：1070-1072.
[19]曾勉,陈思东,谢灿茂,等.肺癌易感性标记物与肺癌关系的病例对照研究.中国公共卫生.2005,21(7)：771-774.
[20]郭占林,高旭东.N-乙酰化转移酶基因多态性与肺癌易感性关系的研究进展[J].国际呼吸杂志.2007,27(16)：1224-1226.
[21]Chiou HL, Wu MF, Chien WP, et al. NAT2 fast acetylator genotype is associated with an increased risk of lung cancer among never-smoking women in Taiwan. Cancer Lett.2005; 223(1):93-101.
[22]高建平,杨国宗,郑家祥,等.肺癌患者乙酰化代谢基因型探讨[J].检验医学与临床.2007,4(6)：480-481.
[23]Zupa A, Sgambato A, Bianchino G, et al. GSTM1 and NAT2 polymorphisms and colon, lung and bladder cancer risk:a case-control study. Anticancer Res.2009; 29(5):1709-1714.
[24]Rotunno M, Yu K, Lubin JH, et al. Phase I metabolic genes and risk of lung cancer:multiple polymorphisms and mRNA expression. PLoS One.2009; 4(5):e5652.
[25]Shen W, Zhang J, Mao G, et al. A long-wavelength, fluorogenic probe for epoxide hydrolase: 7-(2-(oxiran-2-yl)ethoxy) resorufin. Biol Pharm Bull.2009; 32(9):1496-1499.
[26]Zienolddiny S, Campa D, Lind H, et al. A comprehensive analysis of phase I and phase II metabolism gene polymorphisms and risk of non-small cell lung cancer in smokers[J]. Carcinogenesis.2008,29(6):1164-1169.
[27]Tilak AR, Kumar S, Jain M, et al. Association of functionally important polymorphism of microsomal epoxide hydrolase gene (EPHX1) with lung cancer susceptibility. Cancer Invest. 2011;29(6):411-418.
[28]梁戈玉,浦跃朴,尹立红.南京汉族群体肺癌易感性相关基因的研究[J].遗传.2004,26：584-588.
[29]Schneider J, Classen V, Helmig S. XRCC1 polymorphism and lung cancer risk. Expert Rev Mol Diagn.2008; 8(6):761-780.
[30]Schneider J, Classen V, Helmig S. XRCC1 polymorphism and lung Cancer risk [J]. Exper Rev Mol Diagn,2008,8(6):761-780.
[31]Yin J, Vogel U, Ma Y, et al. The DNA repair gene XRCC1 and genetic susceptibility of lung cancer in a northeastern Chinese population. Lung Cancer.2007; 56(2):153-160.
[32]王娜,吴拥军,吴逸明,等.CYP1A1和XRCC1基因多态性与肺癌易感性[J].郑州大学学报(医学版).2012,47(1)：28-30.
[33]Qian B, Zhang H, Zhang L, et al. Association of genetic polymorphisms in DNA repair pathway genes with non-small cell lung cancer risk. Lung Cancer.2011; 73(2):138-146.
[34]Cui Z, Yin Z, Li X, et al. Association between polymorphisms in XRCC1 gene and clinical outcomes of patients with lung cancer:a meta-analysis. BMC Cancer.2012; 12:71.
[35]许崇安,刘佳丽,王晓杰,等XRCC1 Arg194Trp多态性与亚洲人群肺癌易感性的Meta分析[J].现代肿瘤医学,2011,19(6)：1123-1128.
[36]汪保国,陈恩东,周卫平,等.细胞色素P4501A1和谷胱苷肽硫转移酶基因多态性与肺癌关系的病例对照研究[J].中华肿瘤杂志,2004,26(2)：93-97.
[37]Wenzlaff AS, Cote ML, Bock CH, et al. CYP1A1 and CYP1B1 polymorphisms and risk of lung cancer among never smokers:a population-based study. Carcinogenesis.2005; 26(12):2207-2212.
[38]白图雅,常福厚,王敏杰,等GSTT1及CYP1A1基因多态性与肺癌易感性关系[J].中国公共卫生,2011,27(6).
[39]顾艳斐,张宗德,张树才,等.细胞色素P450基因多态性与肺癌易感性的相关性分析[J].中华医学杂志,2007,87(43)：3064-3068.
[40]梁戈玉,浦跃朴,尹立红,等.基因多态性在肺癌发生中交互作用.中国公共卫生2007,23(8)：902-903.