高级搜索

支持向量机预测食管鳞癌患者术后生存期

张天, 晁玮霞, 赵云岗, 王明, 王广超, 贺红梅, 刘瑞敏, 魏书堂, 韩大正, 朱晗, 马瑾, 谷娟, 马远方, 齐义军

张天, 晁玮霞, 赵云岗, 王明, 王广超, 贺红梅, 刘瑞敏, 魏书堂, 韩大正, 朱晗, 马瑾, 谷娟, 马远方, 齐义军. 支持向量机预测食管鳞癌患者术后生存期[J]. 肿瘤防治研究, 2015, 42(08): 765-771. DOI: 10.3971/j.issn.1000-8578.2015.08.004
引用本文: 张天, 晁玮霞, 赵云岗, 王明, 王广超, 贺红梅, 刘瑞敏, 魏书堂, 韩大正, 朱晗, 马瑾, 谷娟, 马远方, 齐义军. 支持向量机预测食管鳞癌患者术后生存期[J]. 肿瘤防治研究, 2015, 42(08): 765-771. DOI: 10.3971/j.issn.1000-8578.2015.08.004
ZHANG Tian, CHAO Weixia, ZHAO Yungang, WANG Ming, WANG Guangchao, HE Hongmei, LIU Ruimin, WEI Shutang, HAN Dazheng, ZHU Han, MA Jin, GU Juan, MA Yuanfang, QI Yijun. Support Vector Machine Predicts Survival of Esophageal Squamous Cell Carcinoma Patients[J]. Cancer Research on Prevention and Treatment, 2015, 42(08): 765-771. DOI: 10.3971/j.issn.1000-8578.2015.08.004
Citation: ZHANG Tian, CHAO Weixia, ZHAO Yungang, WANG Ming, WANG Guangchao, HE Hongmei, LIU Ruimin, WEI Shutang, HAN Dazheng, ZHU Han, MA Jin, GU Juan, MA Yuanfang, QI Yijun. Support Vector Machine Predicts Survival of Esophageal Squamous Cell Carcinoma Patients[J]. Cancer Research on Prevention and Treatment, 2015, 42(08): 765-771. DOI: 10.3971/j.issn.1000-8578.2015.08.004

支持向量机预测食管鳞癌患者术后生存期

基金项目: 国家自然科学基金(30700366,81072039);河南大学研究生科研创新专项资助(Y1326089)
详细信息
    作者简介:

    张天(1990-),男,硕士,主要从事食管癌肿瘤的研究

    通讯作者:

    马远方,E-mail: mayf@henu.edu.cn

    齐义军,E-mail: qiyijun@hotmail.com

  • 中图分类号: R735.1

Support Vector Machine Predicts Survival of Esophageal Squamous Cell Carcinoma Patients

  • 摘要: 目的 应用支持向量机(support vector machine, SVM)建立食管鳞状细胞癌(esophageal squamous cell carcinoma, ESCC)术后生存期预测模型并评估该模型判断ESCC生存期的效能。方法 随访168例接受根治性手术治疗的ESCC患者,分析ESCC临床病理特征和14-3-3σ、热休克蛋白gp96、巨噬细胞移动抑制因子(migrationinhibitory factor, MIF)等3个蛋白的表达规律与ESCC生存期的相关性;应用Matlab软件进行SVM运算,对训练组128例ESCC患者建立最优预后分类模型ESCC-SVM,并用测试组40例患者验证分类效率,ROC曲线分析ESCC-SVM及其他预后相关因子对高低死亡风险ESCC的识别能力。结果 ESCC-SVM由性别、T分期、组织学分级、淋巴结转移、TNM分期、14-3-3σ和gp96等7个最优属性组成,该模型区分训练组和测试组ESCC五年整体生存率的最大AUC分别为0.96、0.86、准确率分别为97.7%、90.0%,明显优于目前临床应用的TNM分期(准确率分别为62.5%、67.5%)及其他各临床病理属性。Cox多因素比例风险回归模型分析发现年龄、T分期、gp96和ESCC-SVM是影响ESCC术后生存期的独立因素。ESCC-SVM与性别、T分期、组织学分级、淋巴结转移、TNM分期和14-3-3σ均显著相关。结论 本研究建立的ESCC-SVM为预后评估、临床治疗方案选择及个体化治疗提供了理论依据。

     

    Abstract: Objective To develop an esophageal squamous cell carcinoma-support vector machine(ESCCSVM) classifier for ESCC survival prediction, and to evaluate its performance of prognostic prediction. Methods Based on the survival data of 168 ESCC patients, we determined the correlation between ESCC survival and clinicopathological features, the expression levels of three biomarkers, 14-3-3σ, heatshock protein gp96 and macrophage migration inhibitory factor(MIF). The SVM algorithm performing in Matlab was used to develop an optimal ESCC-SVM classifier for prognostic prediction by using 128 ESCC patients randomly selected out of 168 patients as the training set and the rest 40 cases as a test set to verify the classification efficiency. Receiver operating characteristic(ROC) curve analysis was used to evaluate the potential of ESCC-SVM classifier and other prognostic factors for identification of high- and low-risk patients. Results ESCC-SVM classifier comprised sex, T stage, histological grade, lymph node metastasis, TNM stage, 14-3-3σ and gp96 as the optimal factors. ROC curve analysis showed that ESCC-SVM produced the largest AUC both in the training and validation groups (0.96, 0.86, respectively), with an accuracy of 97.7% and 90.0%, respectively, which performed significantly better than TNM system(accuracy 62.5%, 67.5%, respectively) and other clinicopathological features. SVM classifier was significantly correlated with sex, T stage, histological grade, lymph node metastasis, TNM stage and 14-3-3σ. Multivariate Cox proportional hazards regression analysis indicated that age, T stage, gp96 and ESCC-SVM were independent prognostic factors of ESCC. Conclusion The seven-feature SVM classifier for ESCC prognosis prediction would provide theoretical evidence for the prognosis, clinical treatment selection and individualized treatment.

     

  • [1] Ferlay J, Shin H R, Bray F, et al. Estimates of worldwide burden of cancer in 2008: GLOBOCAN 2008[J]. Int J Cancer, 2010, 12 7(12): 2893-917.
    [2] Holmes RS, Vaughan TL. Epidemiology and pathogenesis of esophageal cancer[J]. Semin Radiat Oncol, 2007, 17(1): 2-9.
    [3] Jemal A, Bray F, Center M M, et al. Global cancer statistics[J]. CA Cancer J Clin, 2011, 61(2): 69-90.
    [4] Liu LH, Meng J, Zhang C, et al. Serum protein fingerprint diagnoic patterns was estaslished by MALDI-TOF MS for human esophagial carcinoma[J]. Zhong Liu Fang Zhi Yan Jiu, 2012, 39 (2): 169-72. [刘丽华, 孟君, 张璁, 等. 运用MALDI-TOF MS方 法建立食管癌患者血清蛋白指纹图谱诊断模型[J]. 肿瘤防治研 究, 2012, 39(2): 169-72.]
    [5] Pennathur A, Luketich J D. Resection for esophageal cancer: strategies for optimal management[J]. Ann Thorac Surg, 2008, 85 (2): S751-6.
    [6] Lin Y, Chen JQ, Li JC, et al. Value of postoperative radiochemotherapy for thoracic esophageal squamous cell carcinoma with lymph node metastasis[J]. Zhonghua Zhong Liu Za Zhi, 2014, 36(2): 151-4. [林宇, 陈俊强, 李建成, 等. 淋巴结 阳性胸段食管鳞癌术后放化疗的价值[J]. 中华肿瘤杂志, 2014, 36 (2): 151-4.]
    [7] Allum WH, Stenning SP, Bancewicz J, et al. Long-term results of a randomized trial of surgery with or without preoperative chemotherapy in esophageal cancer[J]. J Clin Oncol, 2009, 27 (30): 5062-7.
    [8] Spinosa EJ, Carvalho AC. Support vector machines for novel class detection in bioinformatics[J]. Genet Mol Res, 2005, 4(3): 608-15.
    [9] Pennathur A, Gibson MK, Jobe BA, et al. Oesophageal carcinoma[J]. Lancet, 2013, 381(9864): 400-12.
    [10] Wang H, Huang G. Application of support vector machine in cancer diagnosis[J]. Med Oncol, 2010, 28(Suppl1): s613-8.
    [11] Wang SJ, Zhang LW, Yu WF, et al. Establishment of a diagnostic model of serum protein fingerprint pattern for esophageal cancer screening in high incidence area and its clinical value [J]. Zhonghua Zhong Liu Za Zhi 2007, 29(2): 441-3. [王士杰, 张立玮, 于卫芳, 等. 高发区筛查人群食管鳞癌血清蛋白指纹图谱诊断 模型的建立及临床价值[J]. 中华肿瘤杂志, 2007, 29(6): 441-3.]
    [12] Hermeking H. The 14-3-3 cancer connection[J]. Nat Rev Cancer, 20 03, 3(12): 931-43.
    [13] Dougherty MK, Morrison DK. Unlocking the code of 14-3-3[J]. J Cell Sci, 2004, 117(10): 1875-84.
    [14] Mackintosh C. Dynamic interactions between 14-3-3 proteins and phosphoproteins regulate diverse cellular processes[J]. Biochem J, 20 04, 381(2): 329-42.
    [15] Freeman AK, Morrison DK. 14-3-3 Proteins: diverse functions in cell proliferation and cancer progression[J]. Semin Cell Dev Biol, 20 11, 22(7): 681-7.
    [16] Iacobuzio-Donahue CA, Ashfaq R, Maitra A, et al. Highly expressed genes in pancreatic ductal adenocarcinomas: a comprehensive characterization and comparison of the transcription profiles obtained from three major technologies[J]. Cancer Res, 2003, 63(24): 8614-22.
    [17] Perathoner A, Pirkebner D, Brandacher G, et al. 14-3-3sigma expression is an independent prognostic parameter for poor survival in colorectal carcinoma patients[J]. Clin Cancer Res, 20 05, 11(9): 3274-9.
    [18] Shiba-Ishii A, Noguchi M. Aberrant stratifin overexpression is regulated by tumor-associated CpG demethylation in lung adenocarcinoma[J]. Am J Pathol, 2012, 180(4): 1653-62.
    [19] Shiba-Ishii A, Kano J, Morishita Y, et al. High expression of stratifin is a universal abnormality during the course of malignant progression of early-stage lung adenocarcinoma[J]. Int J Cancer, 20 11, 129(10): 2445-53.
    [20] Okumura H, Kita Y, Yokomakura N, et al. Nuclear expression of 14 -3-3 sigma is related to prognosis in patients with esophageal squamous cell carcinoma[J]. Anticancer Res, 2010, 30(12): 5175-9.
    [21] Ren HZ, Pan GQ, Wang JS, et al. Reduced stratifin expression can serve as an independent prognostic factor for poor survival in patients with esophageal squamous cell carcinoma[J]. Dig Dis Sci, 2010, 55(9): 2552-60.
    [22] Wang X P, Wang Q X, Lin H P, et al. Significance of clinicopathology and expression of heat shock protein 72 and glycoprotein 96 in human hepatocellular carcinoma[J]. Afr J Microbiol Res, 2011, 5(31): 5607-14.
    [23] Wang XP, Wang QX, Ying XP, et al. Correlation between clinicopathology and expression of heat shock protein 72 and glycoprotein 96 in human gastric adenocarcinoma[J]. Tohoku J Exp Med, 2007, 212(1): 35-41.
    [24] Zheng HC, Takahashi H, Li XH, et al. Overexpression of GRP78 and GRP94 are markers for aggressive hehavior and poor progonosis in gastric carcinoma[J]. Hum Pathol, 2008, 39(7): 10 42-9.
    [25] Wang XP, Wang QX, Guo LS, et al. Immunolocalization of heat shock protein 72 and glycoprotein 96 in colonic adenocarcinoma[J]. Acta Histochem, 2008, 110(2): 117-23.
    [26] Wang X, Wang Q, Lin H. Correlation between clinicopathology and expression of heat shock protein 72 and glycoprotein 96 in human esophageal squamous cell carcinoma[J]. Clin Dev Immunol, 2010, 2010: 212537.
    [27] Wang XP, Liu GZ, Song AL, et al. Expression and significance of heat shock protein 70 and glucose-regulated protein 94 in human esophageal cancer[J]. World J Gastroenterol, 2005, 11(3): 429-32.
    [28] Wang Q, An L, Chen Y, et al. Expression of endoplasmic reticulum molecular chaperon GRP94 in human lung cancer tissues and its clinical significance[J]. Chin Med J (Engl), 2002, 115(11): 1615-9.
    [29] Lin CY, Lin TY, Wang HM, et al. GP96 is over-expressed in oral cavity cancer and is a poor prognostic indicator for patients rece iving radiotherapy[J]. Radiat Oncol, 2011, 6:136.
计量
  • 文章访问数:  1278
  • HTML全文浏览量:  353
  • PDF下载量:  531
  • 被引次数: 0
出版历程
  • 收稿日期:  2014-08-03
  • 修回日期:  2014-12-28
  • 刊出日期:  2015-08-24

目录

    /

    返回文章
    返回
    x 关闭 永久关闭