BP神经网络在大肠癌预后分析中的应用
|
摘要
目的
探讨大肠癌患者根治术后生存的影响因素；利用BP神经网络预测大肠癌患者根治术后的生存时间；比较BP神经网络和Logistic回归模型在大肠癌根治术后生存中的性能。
方法
采取查阅病案的方法收集资料；基因表达产物的检测采用SP免疫组化法；Cox比例风险回归模型筛选大肠癌根治术后生存的影响因素；通过比较大肠癌患者根治术后的实际生存时间和BP神经网络预测生存时间,判断BP神经网络预测生存时间的效果；通过ROC曲线下面积的比较,判断BP神经网络和Logistic回归模型在大肠癌患者根治术后生存中的预测性能。
结果
Cox多因素分析结果显示：影响大肠癌患者根治术后生存的因素：Dukes'分期(β=1.197,P<0.001,RR=3.309)、P16(β=-0.805,P<0.001,RR=0.447)、MMP-9(β=0.459,P=0.017,RR=1.582)、P53(β=1.799,P<0.001,RR=6.042)、nm23-H1(β=-0.740,P<0.001,RR=0.477)；BP神经网络预测大肠癌患者根治术后的生存时间和实际生存时间差别没有统计学意义(t=0.996,P=0.327,R2=0.663)；BP神经网络在模型拟合和预测方面性能均优于Logistic回归模型,模型拟合方面,两者ROC曲线下面积比较：Z≈1.75,P=0.04006,按(?)=0.05的检验水准,两者判别效果的差别有统计学意义,BP神经网络的模型拟合效果优于Logistic回归模型,预测性能比较：BP神经网络预测的正确判断率92.5%(37／40),Logistic回归模型的正确判断率82.5%(33／40)。
结论
Dukes分期、P16、MMP-9、P53、nm23-H,是大肠癌患者根治术后生存的重要影响因素,它们可以为临床医生正确判断患者预后、选择合适的治疗方案提供一定的参考依据。
BP神经网络可以预测大肠癌患者根治术后的生存时间,BP神经网络为生存时间的预测提供了一个新思路；在大肠癌根治术后的预后研究中,BP神经网络的性能优于Logistic回归模型,医学现象错综复杂,自变量与因变量间可能存在着复杂的非线性关系以及变量之间可能存在交互作用等,传统的统计学方法对资料有一定的限制,BP神经网络对资料限制少,且具有良好的非线性处理能力等优点,在医学领域可以有进一步的推广和应用。
Objectives:To explore prognostic influence factors of colorectal cancer; BP neural network was used to predict survival time of patients with colorectal cancer; To cpmpare the forecasting performance between BP neutal network and Logistic Regression in prognostic analysis of colorectal cancer.
Method:We adopted consulting disease-cases method to collect data; SP immunohistochemical method was used to detect gene expression products; The Cox proportional hazards regression model was used to detect prognostic influence factors of colorectal cancer; We could evaluate the forecasting performance of BP neural network by comparing the actual survival time and the predicting survival time; Through the comparison of area under the ROC curve between BP neural network and Logistic Regression, we could judge the forecasting performance between the both methods in prognostic analysis of colorectal cancer.
Results:Using Cox multivariate analysis,the main prognostic influence factors of colorectal cancer are Dukes stage (β=1.197 P<0.001,RR=3.309), P16(β=-0.805, P<0.001,RR=0.447), MMP-9(β=0.459, P=0.017,RR=1.582), P53(β=1.799, P<0.001,RR=6.042) nm23-H1(β=-0.740, P<0.001,RR=0.477); The diffence between the actual survival time and the predicting survival time by BP neural network is not statistically significant (t= 0.996, P= 0.327, R2= 0.663); BP nueral network is superior to Logistic regression in the both model-fit and prediction. In the model-fit, between the comparison of the area under the ROC curve, Z-1.75, P= 0.04006, the difference is statistically significant according to (?)=0.05. In the prediction, the accuracy rate by BP nueral network is 92.5%(37/40),but the correct rate of Logistic regression is 82.5%(33/40).
Conclusions:Dukes stage、P16、MMP-9、P53、nm23-H1 are the main prognostic influence factors of colorectal cancer, They can help clinicians to judge the prognosis of the patients and choose the right treatment options. The BP neural network can predict survival time of patients with colorectal cancer. BP neural network offers a new way to predict the survival time,besides, BP neural network is superior to Logistic regression in the both model-fit and prediction of colorectal cancer. The Medical phenomenon is very complex. Besides,the relation between dependent variable and independent variable may be non-linear or the interaction between variables may exist,and ao on. At the same time, the traditional statistical methods have certain limitations. BP neural network has fewer limits to data and has a good non-linear processing. So it can be applied and promoted in the medical field.
探讨大肠癌患者根治术后生存的影响因素；利用BP神经网络预测大肠癌患者根治术后的生存时间；比较BP神经网络和Logistic回归模型在大肠癌根治术后生存中的性能。
方法
采取查阅病案的方法收集资料；基因表达产物的检测采用SP免疫组化法；Cox比例风险回归模型筛选大肠癌根治术后生存的影响因素；通过比较大肠癌患者根治术后的实际生存时间和BP神经网络预测生存时间,判断BP神经网络预测生存时间的效果；通过ROC曲线下面积的比较,判断BP神经网络和Logistic回归模型在大肠癌患者根治术后生存中的预测性能。
结果
Cox多因素分析结果显示：影响大肠癌患者根治术后生存的因素：Dukes'分期(β=1.197,P<0.001,RR=3.309)、P16(β=-0.805,P<0.001,RR=0.447)、MMP-9(β=0.459,P=0.017,RR=1.582)、P53(β=1.799,P<0.001,RR=6.042)、nm23-H1(β=-0.740,P<0.001,RR=0.477)；BP神经网络预测大肠癌患者根治术后的生存时间和实际生存时间差别没有统计学意义(t=0.996,P=0.327,R2=0.663)；BP神经网络在模型拟合和预测方面性能均优于Logistic回归模型,模型拟合方面,两者ROC曲线下面积比较：Z≈1.75,P=0.04006,按(?)=0.05的检验水准,两者判别效果的差别有统计学意义,BP神经网络的模型拟合效果优于Logistic回归模型,预测性能比较：BP神经网络预测的正确判断率92.5%(37／40),Logistic回归模型的正确判断率82.5%(33／40)。
结论
Dukes分期、P16、MMP-9、P53、nm23-H,是大肠癌患者根治术后生存的重要影响因素,它们可以为临床医生正确判断患者预后、选择合适的治疗方案提供一定的参考依据。
BP神经网络可以预测大肠癌患者根治术后的生存时间,BP神经网络为生存时间的预测提供了一个新思路；在大肠癌根治术后的预后研究中,BP神经网络的性能优于Logistic回归模型,医学现象错综复杂,自变量与因变量间可能存在着复杂的非线性关系以及变量之间可能存在交互作用等,传统的统计学方法对资料有一定的限制,BP神经网络对资料限制少,且具有良好的非线性处理能力等优点,在医学领域可以有进一步的推广和应用。
Objectives:To explore prognostic influence factors of colorectal cancer; BP neural network was used to predict survival time of patients with colorectal cancer; To cpmpare the forecasting performance between BP neutal network and Logistic Regression in prognostic analysis of colorectal cancer.
Method:We adopted consulting disease-cases method to collect data; SP immunohistochemical method was used to detect gene expression products; The Cox proportional hazards regression model was used to detect prognostic influence factors of colorectal cancer; We could evaluate the forecasting performance of BP neural network by comparing the actual survival time and the predicting survival time; Through the comparison of area under the ROC curve between BP neural network and Logistic Regression, we could judge the forecasting performance between the both methods in prognostic analysis of colorectal cancer.
Results:Using Cox multivariate analysis,the main prognostic influence factors of colorectal cancer are Dukes stage (β=1.197 P<0.001,RR=3.309), P16(β=-0.805, P<0.001,RR=0.447), MMP-9(β=0.459, P=0.017,RR=1.582), P53(β=1.799, P<0.001,RR=6.042) nm23-H1(β=-0.740, P<0.001,RR=0.477); The diffence between the actual survival time and the predicting survival time by BP neural network is not statistically significant (t= 0.996, P= 0.327, R2= 0.663); BP nueral network is superior to Logistic regression in the both model-fit and prediction. In the model-fit, between the comparison of the area under the ROC curve, Z-1.75, P= 0.04006, the difference is statistically significant according to (?)=0.05. In the prediction, the accuracy rate by BP nueral network is 92.5%(37/40),but the correct rate of Logistic regression is 82.5%(33/40).
Conclusions:Dukes stage、P16、MMP-9、P53、nm23-H1 are the main prognostic influence factors of colorectal cancer, They can help clinicians to judge the prognosis of the patients and choose the right treatment options. The BP neural network can predict survival time of patients with colorectal cancer. BP neural network offers a new way to predict the survival time,besides, BP neural network is superior to Logistic regression in the both model-fit and prediction of colorectal cancer. The Medical phenomenon is very complex. Besides,the relation between dependent variable and independent variable may be non-linear or the interaction between variables may exist,and ao on. At the same time, the traditional statistical methods have certain limitations. BP neural network has fewer limits to data and has a good non-linear processing. So it can be applied and promoted in the medical field.
引文
[1]Kem P Painer M, Raihal, Sourander L.A marked increase in the incidence of colorectal cancer over two decades in southwest Finland. J Clin Epidemiol,1997,50(2):147-151.
[2]Vogelstein B, Fearon EB, Harnilto SR, et al. Genetic alterations during colorectal tumor development. N Engl J Med,1988,319(9):525-532.
[3]张振亚,赵泽贞.大肠癌流行病学研究现状及展望.肿瘤防治研究,2000,27(2)：154-156
[4]邓伟,金丕焕.人工神经网络及其在预防医学中的应用.中国公共卫生,2002,18(10)：1265-1267
[5]任宏,姜庆五.人工神经网络及其在预防医学领域的应用.上海预防医学杂志,2003,15(1)：22～24
[6]张蓉,郭文有,闫再宏,等.CyclinD1、 p16的表达与大肠癌生物学行为的关系.中国误诊学杂志,2006,6(11)：2046-2048
[7]王丽琼,张曦,许瑞吉,等.周期素D1与p16蛋白及Rb基因在大肠癌中的表达及意义.云南医药,2007,28(5)：434-437
[8]吴红霞.p16、Ki267蛋白在大肠腺瘤、腺癌组织中的表达及意义.山西医科大学学报,2007,38(8)：705-707
[9]贾明华,唐芙爱,刘霞等.MMP-9、uPA在大肠癌中的表达及临床意义.医药论坛杂志,2008,29(5)：22-26
[10]秦冰,瞿峰.TIMP-1、 MMP-2、 MMP-9在大肠癌组织中表达的临床意义.胃肠病学和肝病学杂志,2008,17(11)：890～892
[11]历春,盖晓东,刘晓红.COX-2,MMP-9和bFGF在大肠癌中的表达及临床意义.北华大学学报,10(1)：46～49
[12]胡君,霍中华,储著凌,等.大肠癌患者血清HSP60和MMP-9的变化及其意义.中国热带医学,2009,9(6)：1072～1073
[13]孙国贵.Syk和nm23-H1在大肠癌中的表达及其临床意义.[硕士学位论文].河北：河北医科大学,2008
[14]王从玉,邓跃华,刘弋,等.nm23 VEGF-C及VEGFR-3在大肠癌中的表达及意义.中国肿瘤临床,2008,35(19)：1117-1121
[15]薛立娟,王维忠,张文岚,等.p53和nm23蛋白表达与大肠癌浸润转移的关系.中国免疫学杂志,2001,17(1)：30-32
[16]马志祥,刘安丽,刘家恒.nm23基因在大肠癌组织中的表达及临床意义.临床与实践,2005,9(2)：124-125
[17]曲利娟,余英豪,谈景旺,等.大肠癌组织中Fas/FasL系统、nm23表达与转移的关系.临床与实验病理学杂志,2002,18(2)：153-155
[18]Tabuchi Y, Nakamura T, Kuniyasu T. et al. Expression of nm23-H1 in colorectal carcinomer assosiation with metastasis, histological stage, or surviva[J].Surg Today,29(2):116— 20; 1999
[19]Lee JC. LinYJ, chow NH, et al. Reappraisal of the role of nm23-H1 in colorectal cancers[J].J Surg oncol,76(1):58— 62;2001
[20]Martin Schumacher,Reibhard Robner,Werner Varch. Neural networks and logistic regression:Part I [J]. Comp Stat Data Anal,1996 (21):661-662
[21]周利锋,高尔生,金丕焕.BP神经网络与Logistic回归对比初探.中国卫生统计,1998,15(1)：1-4
[22]陈春凯.Matlab人工神经网络工具箱中的BP工具函数及其应用.许昌师专学报,2002,21(5)：39-42
[23]李丽霞,王彤,范逢曦.BP神经网络设计探讨.现代预防医学,2005,32(2)：1
[24]戚德虎,康继昌.BP神经网络的设计.计算机工程与设计,19(2)：94
[25]范熠,王素萍,杨芸,等.基于BP人工神经网络的太原地区医院获得性肺炎发生情况的评测分析.中国卫生统计,2008,(25)：241
[26]王俊杰,陈景武.BP神经网络原理及其在医学统计应用中的设计技巧.中国卫生统计,2008,25(5)：547～549
[27]蔡兵.BP神经网络隐层结构的设计方法.通化师范学院学报,2007,28(2)18～19
[28]徐建伟,刘桂芬.Bayesian正规化BP神经网络及其在医学预测中的应用.中国卫生统计,2007,24(6)：597～599
[29]邓伟,金丕焕,林果.BP神经网络修剪算法筛选白血病预后危险因素.复旦学报2003,30(2)：154～157
[30]邓伟.BP神经网络的构建与优化的研究及其在医学统计中的应用.[博士学位论文].复旦大学,2002
[31]蒋良孝,李超群.基于BP神经网络的函数逼近方法及其MATLAB实现.微型机与应用,2004,(1)：52～53
[32]余良晖,贾文龙,薛亚洲,等.MATLAB实现BP神经网络的煤炭需求预测.煤炭经济研究,2007,(10)：34～36
[33]张德丰.MATLAB神经网络仿真与应用.北京：电子工业出版社,2009
[34]赵振.Cox比例风险回归模型和BP神经网络在肝移植受体预后分析中的应用.[硕士学位论文].四川大学华西公共卫生学院,2006
[35]贺佳,张智坚,贺宪民.肝癌术后无瘤生存期的人工神经网络预测.数理统计与管理,2002,21(4)：14～16
[36]高蔚,聂绍发,施侣元.神经网络在生存分析中的应用进展.中国卫生统计,2006,23(4)：358～360
[37]宇传华,徐勇勇.非参数法估计ROC曲线下面积.中国卫生统计,1999,16(4)：241～244
[38]胡明珠,李康.两种临床诊断方法效果的ROC曲线比较.数理医药学杂志,2005,18(4)：293～295
[39]Hanley JA, Me Neil BJ. A method of comparing the areas under a receiver operating characteristic curves derived from the same case. Radiology,1983,148:839～843
[40]孙高,杨静宇.基于人工神经网络的肺癌诊断研究[J].中国卫生统计,1999,16(3)：142-144
[41]张卓勇,刘思东,丁保军,等.人工神经网络用于肺癌的辅助诊断[J].高等化学学报,1998,19(4)：530-533
[42]Walczak S, Nowack WJ. An artificial neural network approach to diagnosing epilepsy using lateralized bursts of theta EEGs. J Med Syst,2001,25 (1):9-20
[43]Schmitt WH, Linder R, Reinhold Keller E, et al. Improved differentiation between Churg-Strauss syndrome and Wegener's granulomatosis by an artificial neural network. Arthritis Rheum,2001,44 (8):1887～1896
[44]Wadie BS, Badawi AM, Ghoneim MA. The relationship of the International Prostate Symptom Score and objective parameters for diagnosing bladder outlet obstruction. Part Ⅱ:the potential usefulness of artificial neural networks. J Urol,2001,165 (1):35～37
[45]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
[46]李丽霞.BP神经网络及其在在疾病预后分类问题中的应用.[硕士学位论文].太原：山西医科大学,2002
[1]邓伟,金丕焕.人工神经网络及其在预防医学中的应用.中国公共卫生,2002,18(10)：1265-1267
[2]岳勇.BP人工神经网络在结核病防治中的应用研究.[硕士学位论文].重庆医科大学,2006
[3]蒋良孝,李超群.基于BP神经网络的函数逼近方法及其MATLAB实现.微型机与应用,2004,(1)：52～53
[4]余良晖,贾文龙,薛亚洲等.MATLAB实现BP神经网络的煤炭需求预测.煤炭经济研究,2007,(10)：34～36
[5]张德丰.MATLAB神经网络仿真与应用.北京：电子工业出版社,2009
[6]Chen, S., C. F N. Cowan, and P M. Grant. "Orthogonal least squares learning algorithm for radial basis function networks," IEEET ransactions on Neural Networks,1991,2(2):302-309
[7]Dennis, J. E., and R. B. Schnabel. Numerical Methods for Unconstrained Optimization and Nonlinear Equations. Englewood Cliffs, NJ:Prentice-Hall,1983.
[8]Hebb, D.O.. The Organization of Behavior. New York:Wiley,1949.
[9]Himmelblau, D. M.. Applied Nonlinear Programming. New York:McGraw-Hill,1972.
[10]Jolliffe, I. T.. Principal Component Analysis. New York:Springer-Verlag, 1986.
[11]孙高,杨静宇.基于人工神经网络的肺癌诊断研究.中国卫生计,1999,16(3)：142-144
[12]张卓勇,刘思东,丁保军等.人工神经网络用于肺癌的辅助诊断.高等化学学报,1998,19(4)：530～533
[13]李家林,牟永阁,张利群等.基于组合神经网络的肺心病辅助诊断系统的实验研究.生物医学工程学,2001,18(4)：573-576
[14]Walczak S, Nowack WJ. An artificial neural network approach to diagnosing epilepsy using lateralized bursts of theta EEGs. J Med Syst,2001,25 (1):9-20
[15]Lee J S, Lee DS, Kim SK, et al. Localization of epileptogenic zones in F-18 FDG brain PET of patients with temporal lobe epilepsy using artificial neural network. IEEE Trans Med Imaging,2000,19 (4):347～355
[16]李志良,曾鸽鸣,胡芳,等.神经网络在肝硬化病因鉴别诊断中的应用.中国生物医学工程报,1997,16(1)：92-93
[17]Hopkins CB, Suleman J, Cook C. An artificial neural network for the electrocardiographic diagnosis of left ventricular hypertrophy. Crit Rev Biomed Eng,2000,28 (3-4):435～438
[18]De Groff CG, Bhatikar S, Hertzberg J, et al. Artificial neuralnetwork-based method of screening heart murmurs in children. Circulation,2001,103 (22):2711～2716
[19]邓伟,金丕焕,林果为.BP神经网络修剪算法筛选白血病预后危险因素.复旦学报,2003,30(2)：154～157
[20]贺佳,张智坚,贺宪民.肝癌术后无瘤生存期的人工神经网络预测.数理统计与管理,2002,21(4)：14～16
[21]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
[2]Vogelstein B, Fearon EB, Harnilto SR, et al. Genetic alterations during colorectal tumor development. N Engl J Med,1988,319(9):525-532.
[3]张振亚,赵泽贞.大肠癌流行病学研究现状及展望.肿瘤防治研究,2000,27(2)：154-156
[4]邓伟,金丕焕.人工神经网络及其在预防医学中的应用.中国公共卫生,2002,18(10)：1265-1267
[5]任宏,姜庆五.人工神经网络及其在预防医学领域的应用.上海预防医学杂志,2003,15(1)：22～24
[6]张蓉,郭文有,闫再宏,等.CyclinD1、 p16的表达与大肠癌生物学行为的关系.中国误诊学杂志,2006,6(11)：2046-2048
[7]王丽琼,张曦,许瑞吉,等.周期素D1与p16蛋白及Rb基因在大肠癌中的表达及意义.云南医药,2007,28(5)：434-437
[8]吴红霞.p16、Ki267蛋白在大肠腺瘤、腺癌组织中的表达及意义.山西医科大学学报,2007,38(8)：705-707
[9]贾明华,唐芙爱,刘霞等.MMP-9、uPA在大肠癌中的表达及临床意义.医药论坛杂志,2008,29(5)：22-26
[10]秦冰,瞿峰.TIMP-1、 MMP-2、 MMP-9在大肠癌组织中表达的临床意义.胃肠病学和肝病学杂志,2008,17(11)：890～892
[11]历春,盖晓东,刘晓红.COX-2,MMP-9和bFGF在大肠癌中的表达及临床意义.北华大学学报,10(1)：46～49
[12]胡君,霍中华,储著凌,等.大肠癌患者血清HSP60和MMP-9的变化及其意义.中国热带医学,2009,9(6)：1072～1073
[13]孙国贵.Syk和nm23-H1在大肠癌中的表达及其临床意义.[硕士学位论文].河北：河北医科大学,2008
[14]王从玉,邓跃华,刘弋,等.nm23 VEGF-C及VEGFR-3在大肠癌中的表达及意义.中国肿瘤临床,2008,35(19)：1117-1121
[15]薛立娟,王维忠,张文岚,等.p53和nm23蛋白表达与大肠癌浸润转移的关系.中国免疫学杂志,2001,17(1)：30-32
[16]马志祥,刘安丽,刘家恒.nm23基因在大肠癌组织中的表达及临床意义.临床与实践,2005,9(2)：124-125
[17]曲利娟,余英豪,谈景旺,等.大肠癌组织中Fas/FasL系统、nm23表达与转移的关系.临床与实验病理学杂志,2002,18(2)：153-155
[18]Tabuchi Y, Nakamura T, Kuniyasu T. et al. Expression of nm23-H1 in colorectal carcinomer assosiation with metastasis, histological stage, or surviva[J].Surg Today,29(2):116— 20; 1999
[19]Lee JC. LinYJ, chow NH, et al. Reappraisal of the role of nm23-H1 in colorectal cancers[J].J Surg oncol,76(1):58— 62;2001
[20]Martin Schumacher,Reibhard Robner,Werner Varch. Neural networks and logistic regression:Part I [J]. Comp Stat Data Anal,1996 (21):661-662
[21]周利锋,高尔生,金丕焕.BP神经网络与Logistic回归对比初探.中国卫生统计,1998,15(1)：1-4
[22]陈春凯.Matlab人工神经网络工具箱中的BP工具函数及其应用.许昌师专学报,2002,21(5)：39-42
[23]李丽霞,王彤,范逢曦.BP神经网络设计探讨.现代预防医学,2005,32(2)：1
[24]戚德虎,康继昌.BP神经网络的设计.计算机工程与设计,19(2)：94
[25]范熠,王素萍,杨芸,等.基于BP人工神经网络的太原地区医院获得性肺炎发生情况的评测分析.中国卫生统计,2008,(25)：241
[26]王俊杰,陈景武.BP神经网络原理及其在医学统计应用中的设计技巧.中国卫生统计,2008,25(5)：547～549
[27]蔡兵.BP神经网络隐层结构的设计方法.通化师范学院学报,2007,28(2)18～19
[28]徐建伟,刘桂芬.Bayesian正规化BP神经网络及其在医学预测中的应用.中国卫生统计,2007,24(6)：597～599
[29]邓伟,金丕焕,林果.BP神经网络修剪算法筛选白血病预后危险因素.复旦学报2003,30(2)：154～157
[30]邓伟.BP神经网络的构建与优化的研究及其在医学统计中的应用.[博士学位论文].复旦大学,2002
[31]蒋良孝,李超群.基于BP神经网络的函数逼近方法及其MATLAB实现.微型机与应用,2004,(1)：52～53
[32]余良晖,贾文龙,薛亚洲,等.MATLAB实现BP神经网络的煤炭需求预测.煤炭经济研究,2007,(10)：34～36
[33]张德丰.MATLAB神经网络仿真与应用.北京：电子工业出版社,2009
[34]赵振.Cox比例风险回归模型和BP神经网络在肝移植受体预后分析中的应用.[硕士学位论文].四川大学华西公共卫生学院,2006
[35]贺佳,张智坚,贺宪民.肝癌术后无瘤生存期的人工神经网络预测.数理统计与管理,2002,21(4)：14～16
[36]高蔚,聂绍发,施侣元.神经网络在生存分析中的应用进展.中国卫生统计,2006,23(4)：358～360
[37]宇传华,徐勇勇.非参数法估计ROC曲线下面积.中国卫生统计,1999,16(4)：241～244
[38]胡明珠,李康.两种临床诊断方法效果的ROC曲线比较.数理医药学杂志,2005,18(4)：293～295
[39]Hanley JA, Me Neil BJ. A method of comparing the areas under a receiver operating characteristic curves derived from the same case. Radiology,1983,148:839～843
[40]孙高,杨静宇.基于人工神经网络的肺癌诊断研究[J].中国卫生统计,1999,16(3)：142-144
[41]张卓勇,刘思东,丁保军,等.人工神经网络用于肺癌的辅助诊断[J].高等化学学报,1998,19(4)：530-533
[42]Walczak S, Nowack WJ. An artificial neural network approach to diagnosing epilepsy using lateralized bursts of theta EEGs. J Med Syst,2001,25 (1):9-20
[43]Schmitt WH, Linder R, Reinhold Keller E, et al. Improved differentiation between Churg-Strauss syndrome and Wegener's granulomatosis by an artificial neural network. Arthritis Rheum,2001,44 (8):1887～1896
[44]Wadie BS, Badawi AM, Ghoneim MA. The relationship of the International Prostate Symptom Score and objective parameters for diagnosing bladder outlet obstruction. Part Ⅱ:the potential usefulness of artificial neural networks. J Urol,2001,165 (1):35～37
[45]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
[46]李丽霞.BP神经网络及其在在疾病预后分类问题中的应用.[硕士学位论文].太原：山西医科大学,2002
[1]邓伟,金丕焕.人工神经网络及其在预防医学中的应用.中国公共卫生,2002,18(10)：1265-1267
[2]岳勇.BP人工神经网络在结核病防治中的应用研究.[硕士学位论文].重庆医科大学,2006
[3]蒋良孝,李超群.基于BP神经网络的函数逼近方法及其MATLAB实现.微型机与应用,2004,(1)：52～53
[4]余良晖,贾文龙,薛亚洲等.MATLAB实现BP神经网络的煤炭需求预测.煤炭经济研究,2007,(10)：34～36
[5]张德丰.MATLAB神经网络仿真与应用.北京：电子工业出版社,2009
[6]Chen, S., C. F N. Cowan, and P M. Grant. "Orthogonal least squares learning algorithm for radial basis function networks," IEEET ransactions on Neural Networks,1991,2(2):302-309
[7]Dennis, J. E., and R. B. Schnabel. Numerical Methods for Unconstrained Optimization and Nonlinear Equations. Englewood Cliffs, NJ:Prentice-Hall,1983.
[8]Hebb, D.O.. The Organization of Behavior. New York:Wiley,1949.
[9]Himmelblau, D. M.. Applied Nonlinear Programming. New York:McGraw-Hill,1972.
[10]Jolliffe, I. T.. Principal Component Analysis. New York:Springer-Verlag, 1986.
[11]孙高,杨静宇.基于人工神经网络的肺癌诊断研究.中国卫生计,1999,16(3)：142-144
[12]张卓勇,刘思东,丁保军等.人工神经网络用于肺癌的辅助诊断.高等化学学报,1998,19(4)：530～533
[13]李家林,牟永阁,张利群等.基于组合神经网络的肺心病辅助诊断系统的实验研究.生物医学工程学,2001,18(4)：573-576
[14]Walczak S, Nowack WJ. An artificial neural network approach to diagnosing epilepsy using lateralized bursts of theta EEGs. J Med Syst,2001,25 (1):9-20
[15]Lee J S, Lee DS, Kim SK, et al. Localization of epileptogenic zones in F-18 FDG brain PET of patients with temporal lobe epilepsy using artificial neural network. IEEE Trans Med Imaging,2000,19 (4):347～355
[16]李志良,曾鸽鸣,胡芳,等.神经网络在肝硬化病因鉴别诊断中的应用.中国生物医学工程报,1997,16(1)：92-93
[17]Hopkins CB, Suleman J, Cook C. An artificial neural network for the electrocardiographic diagnosis of left ventricular hypertrophy. Crit Rev Biomed Eng,2000,28 (3-4):435～438
[18]De Groff CG, Bhatikar S, Hertzberg J, et al. Artificial neuralnetwork-based method of screening heart murmurs in children. Circulation,2001,103 (22):2711～2716
[19]邓伟,金丕焕,林果为.BP神经网络修剪算法筛选白血病预后危险因素.复旦学报,2003,30(2)：154～157
[20]贺佳,张智坚,贺宪民.肝癌术后无瘤生存期的人工神经网络预测.数理统计与管理,2002,21(4)：14～16
[21]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
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |