Please wait a minute...
浙江大学学报(工学版)
JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE)  2018, Vol. 52 Issue (12): 2365-2371    DOI: 10.3785/j.issn.1008-973X.2018.12.015
Computer Technology     
Postoperative survival prediction model of BP neural network with variable cluster
MENG Jun, DENG Xiao-yu, YU Jie-zhou
College of Electrical Engineering, Zhejiang University, Hangzhou 310058, China
Download:   PDF(1021KB) HTML
Export: BibTeX | EndNote (RIS)      

Abstract  

A variable cluster method combining scenario cognition and membership degree ranking was proposed based on fuzzy C-means (FCM) cluster algorithm aiming at the postoperative survival prediction of colorectal cancer patients. Dimension reduction on samples of colorectal cancer patients were conducted; six characteristic variables were selected. Next, a postoperative survival prediction model was constructed for colorectal cancer patients with BP neural network. To verify the validity of this model, principal component analysis (PCA) was used to reduce the dimensions of the sample to train a BP neural network, and the comparison of accuracy rates between models based on FCM and PCA was conducted. Results verifly that the BP neural network model based on FCM variable cluster has more accurate prediction rate. The proposed variable cluster method can effectively screen out variables that have high pertinence and good interpretability of survival time, thus improves the forecast accuracy of BP neural network model.

Received: 20 December 2017      Published: 13 December 2018
CLC:  TP181  
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Cite this article:

MENG Jun, DENG Xiao-yu, YU Jie-zhou. Postoperative survival prediction model of BP neural network with variable cluster. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2018, 52(12): 2365-2371.

URL:

http://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2018.12.015     OR     http://www.zjujournals.com/eng/Y2018/V52/I12/2365


基于变量聚类的BP神经网络术后生存期预测模型

针对结直肠癌患者术后生存期预测，基于模糊C均值（FCM）聚类算法，提出一种结合场景认知和隶属度排序的变量聚类方法，对结直肠癌患者样本进行降维，并筛选出6个特征变量.结合BP神经网络，建立一个结直肠癌患者术后生存期预测模型.为了验证该模型的有效性，利用主成分分析（PCA）对样本进行降维，并训练BP神经网络，对比FCM模型及PCA模型的预测准确率.结果显示，基于FCM变量聚类的BP神经网络模型预测准确率更高，所提出的变量聚类方法能够有效筛选出对于生存期有相关性和解释性的变量，从而提高BP神经网络模型的预测准确率.

[1] SIEGEL R L, MILLER K D, FEDEWA S A, et al. Colorectal cancer statistics, 2017[J]. CA:a Cancer Journal for Clinicians, 2017, 67(3):177-193.
[2] CHEN W, ZHENG R, BAADE P D, et al. Cancer statistics in China, 2015[J]. CA:a Cancer Journal for Clinicians, 2016, 66(2):115-132.
[3] HORNBROOK M C, GOSHEN R, CHOMAN E, et al. Early colorectal cancer detected by machine learning model using gender, age, and complete blood count data[J]. Digestive Diseases and Sciences, 2017, 62(10):2719-2727.
[4] MONTAZERI M, MONTAZERI M, MONTAZERI M, et al. Machine learning models in breast cancer survival prediction[J]. Technology and Health Care Official Journal of the European Society for Engineering and Medicine, 2015, 24(1):31-42.
[5] THONGKAM J, XU G, ZHANG Y. AdaBoost algorithm with random forests for predicting breast cancer survivability[C]//IEEE International Joint Conference on Neural Networks. Hong Kong:IEEE, 2008:3062-3069.
[6] YAO D, YANG J, ZHAN X. Predicting breast cancer survivability using random forest and multivariate adaptive regression splines[C]//International Conference on Electronic and Mechanical Engineering and Information Technology. Harbin:IEEE, 2011:2204-2207.
[7] HUANG S H, LOH J K, TSAI J T, et al. Predictive model for 5-year mortality after breast cancer surgery in Taiwan residents[J]. Chinese Journal of Cancer, 2017, 36(4):23.
[8] SVETNIK V, LIAW A, TONG C, et al. Random forest:a classification and regression tool for compound classification and QSAR modeling[J]. Journal of Chemical Information and Computer Sciences, 2003, 43(6):1947.
[9] KUNIZAKI M, SAWAI T, TAKESHITA H, et al. Clinical value of serum p53 antibody in the diagnosis and prognosis of colorectal cancer[J]. Anticancer Research, 2016, 36(8):4171-4175.
[10] WANG P, LIANG J, WANG Z, et al. The prognostic value of p53 positive in colorectal cancer:a retrospective cohort study[J]. Tumour Biology, 2017, 39(5):1010428317703651.
[11] KOUROU K, EXARCHOS T P, EXARCHOS K P, et al. Machine learning applications in cancer prognosis and prediction[J]. Computational and Structural Biotechnology Journal, 2015, 13(C):8-17.
[12] JAIN A K, CHANDRASEKARAN B. 39 dimensionality and sample size considerations in pattern recognition practice[J]. Handbook of Statistics, 1982, 2(39):835-855.
[13] FRANCO G D. Principal component analysis and factor analysis[J]. Principal Component Analysis, 2002:150-166.
[14] KLEMA V, LAUB A J. The singular value decomposition:Its computation and some applications[J]. IEEE Transactions on Automatic Control, 1980, 25(2):164-176.
[15] 姜园, 张朝阳, 仇佩亮, 周东方. 用于数据挖掘的聚类算法[J]. 电子与信息学报, 2005(4):655-662 JIANG Yuan, ZHANG Chao-yang, QIU Pei-liang, et al. Clustering algorithm for data mining[J]. Journal of Electronics and Information Technology, 2005(4):655-662
[16] BEZDEK J C, EHRLICH R, FULL W. FCM:The fuzzy C-means clustering algorithm[J]. Computers and Geosciences, 1984, 10(2):191-203.
[17] PAL N R, BEZDEK J C. On cluster validity for the fuzzy C-means model[J]. IEEE Transactions on Fuzzy Systems, 2002, 3(3):370-379.
[18] PITTS W. A logical calculus of the ideas immanent in nervous activity[J]. Bulletin of Mathematical Biology, 1943, 5(4):115-133.
[19] 王彦东, 吴佩. 肿瘤的脉管内侵犯与转移[J]. 国际外科学杂志, 2007, 34(3):209-212 WANG Yan-dong, WU Pei. Intravascular invasion and metastasis of tumor[J]. International Journal of Surgery, 2007, 34(3):209-212
[20] KHORANA A A, RYAN C K, COX C, et al. Vascular endothelial growth factor, CD68, and epidermal growth factor receptor expression and survival in patients with stage Ⅱ and stage Ⅲ colon carcinoma:a role for the host response in prognosis[J]. Cancer, 2003, 97(4):960-968.
[21] CHAN J A, MEYERHARDT J A, NIEDZWIECKI D, et al. Association of family history with cancer recurrence and survival among patients with stage Ⅲ colon cancer[J]. Jama the Journal of the American Medical Association, 2008, 299(21):2515-2523.
[22] 宫媛, 吴本俨, 苏斌斌. 272例直肠癌患者的预后影响因素分析[J]. 解放军医学杂志, 2008, 33(5):608-610 GONG Yuan, WU Ben-yan. Analysis of prognostic factors in 272 patients with rectal cancer[J]. Medical Journal of Chinese People's Liberation Army, 2008, 33(5):608-610
[23] NAKAMURA T, MITOMi H, KANAZAWA H, et al. Tumor budding as an index to identify high-risk patients with stage Ⅱ colon cancer[J]. Diseases of the Colon and Rectum, 2008, 51(5):568-572.
[24] WULFKUHLE J D, LIOTTA L A, PETRICOIN E F. Proteomic applications for the early detection of cancer[J]. Nature Reviews Cancer, 2003, 3(4):267.
[25] MARCUS G. Deep Learning:a critical appraisal[EB/OL]. (2018-01-02)[2018-04-18]. https://arxiv.org/abs/1801.00631.
[1] LIU Ru-hui, HUANG Wei-ping, WANG Kai, LIU Chuang, LIANG Jun. Semi-supervised constraint ensemble clustering by fast search and find of density peaks[J]. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2018, 52(11): 2191-2200.
[2] HU Li-sha, WANG Su-zhen, CHEN Yi-qiang, GAO Chen-long, HU Chun-yu, JIANG Xin-long, CHEN Zhen-yu, GAO Xing-yu. Fall detection algorithms based on wearable device: a review[J]. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2018, 52(9): 1717-1728.
[3] YU Jian-bo, DONG Chen-yang, LI Chuan-feng, LIU Hai-qiang. Statistical α-algorithm based process mining on clinical pathway[J]. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2017, 51(10): 1881-1890.