基于机器学习的结直肠癌血清标志物筛选及早期诊断模型评估

Abstract
Figure/Table
References
Related Citation (2)

Download: PDF (4803 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Objective To improve the early diagnostic rate of colorectal cancer in order to have colorectal cancer patients diagnosed as early as possible for the best treatment result. Methods Based on the Machine Learning theory and practices, the forward method was adopted inlogistic regression(LR)in order to analyze and screen the serum marker of the best referential value. Support Vector Machine (SVM)and Back Propagation (BP)were used to establish an early diagnostic model for colorectal cancer. Results The experiment results showed that such serum markers as CEA、CA1724、CA242、CA153 and HSP60 were of diagnostic valuefor colorectal cancer. The LR colorectal cancer diagnostic model that combined the above mentioned five types of serum markers outperformed that of each individual serum marker. Conclusion Combined tests can enhance the detection sensitivity to colorectal cancer. The LR colorectal cancer diagnostic model has a higher diagnostic value than the model based on SVM.

Key words： feature selection feature classification logistic regression Support Vector Machine back propagation neural network colorectal cancer.

Received: 28 February 2016 Published: 05 January 2017

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors

Cite this article:

URL:

http://manu37.magtech.com.cn/Jwk_jsyxkx/jfj/EN/ OR http://manu37.magtech.com.cn/Jwk_jsyxkx/jfj/EN/Y2016/V34/I6/879

[1]	LEPORRIER J,MAUREL J,CHICHE L,et al.A population‐based study of the incidence,management and prognosis of hepatic metastases from colorectal cancer[J].British Journal of Surgery,2006,93(4):465.
[2]	SINGH H,NUGENT Z,DEMERS A A,et al.The reduction in colorectal cancer mortality after colonoscopy varies by site of the cancer[J].Gastroenterology,2010,139(4):1128.
[3]	GANEPOLA G A,NIZIN J,RUTLEDGE J R,et al.Use of blood-based biomarkers for early diagnosis and surveillance of colorectal cancer[J].World J Gastrointest Oncol,2014,6(4):83.
[4]	TIAN M F.The clinical value of the detections of CA199,CA125,CA153 and CEA in malignant tumors[J].Journal of Clinical & Experimental Medicine,2010,4630:243.
[5]	BASSI C,SALVIA R,GUMBS A A,et al.The value of standard serum tumor markers in differentiating mucinous from serous cystic tumors of the pancreas:CEA,Ca 19-9,Ca 125,Ca 15-3.[J].Langenbeck S Archives of Surgery,2002,387(7-8):281.
[6]	STURGEON C.Practice guidelines for tumor marker use in the clinic.[J].Clinical Chemistry,2002,48(8):1151.
[7]	李锦洲,盛家和,陈光意.肿瘤标志物检测在消化系统肿瘤诊断中作用[J].医药论坛杂志,2005,26(14):25.
[8]	原新红,田亚平,郭广宏.血清肿瘤标志物联合检测的评价[J].军医进修学院学报,2005,26(5):350.
[9]	邵文.血清肿瘤标志物联合检测对胃癌诊断的方案优化[J].中国社区医师:医学专业,2011,13(18):206.
[10]	JUNTERMANNS B,RADUNZ S,HEUER M,et al.Tumor markers as a diagnostic key for hilar cholangiocarcinoma[J].European Journal of Medical Research,2010,15(8):357.
[11]	SUNG J J Y,LAU J Y W,YOUNG G P,et al.An updated Asia Pacific Consensus Recommendations on colorectal cancer screening.[J].Gut,2015,64(57):1166.
[12]	MEHTA J,PRABHU R,ESHPUNIYANI P,et al.Evaluating the efficacy of tumor markers CA19-9 and CEA to predict operability and survival in pancreatic malignancies[J].Tropical Gastroenterology Official Journal of the Digestive Diseases Foundation,2010,31(3):421.
[13]	GEBAUER G,MULLER R W.Tumor marker concetratios innormal and malignant tissues of colorectal cancer patients and their prognostic relevance[J].Anticancer Res,1997,17(9):2939.
[14]	朱玉琨,瞿良,袁荣国,等.大肠癌患者血清CA242、CA19-9和CEA水平测定的临床意义[J].肿瘤研究与临床,2004,16(4):227.
[15]	张力,何元兵,刘挺,等.肿瘤标志物在肺部恶性肿瘤诊断中的意义[J].中国癌症杂志,2001,11(6):510.
[16]	陈涛,苏秀馨,全松,等.血清SGF与CEA、AFP、NSE、CA125在恶性肿瘤临床诊断中的对比研究[C].中华医学会第七次全国检验医学学术会议,2008.
[17]	戴鹏.血清肿瘤标志物测定在结直肠癌中的意义[D].山西医科大学,2008.
[18]	杜卫东,唐健雄,杨俭英,等.大肠癌血清肿瘤标志物联合测定的临床研究[J].结直肠肛门外科,2003,9(2):83.
[19]	BAGARIA B,SOOD S,SHARMA R,et al.Comparative study of CEA and CA19-9 in esophageal,gastric and colon cancers individually and in combination(ROC curve analysis)[J].Cancer Biology & Medicine,2013,10(3):148.
[20]	顾平,黄钢,韩源.Logistic 回归和 ROC 曲线分析多种肿瘤标志物在结直肠癌中的诊断价值[J].放射免疫学杂志,2007,20(3):202.
[21]	余捷凯,杨美琴,姜铁军,等.血清肿瘤标志物优化组合人工神经网络模型在大肠癌诊断中的应用[J].浙江大学学报:医学版,2004,33(5):407.