北京生物醫(yī)學(xué)工程

基于數(shù)據(jù)挖掘技術(shù)的消化道惡性腫瘤診斷

Diagnosis of Digestive Tract Cancer Based on Data Mining

作者：游佳陳卉武文芳夏翃楊淼劉志成

單位：首都醫(yī)科大學(xué)生物醫(yī)學(xué)工程學(xué)院（北京100069）

關(guān)鍵詞：數(shù)據(jù)挖掘；消化道惡性腫瘤；神經(jīng)網(wǎng)絡(luò)；Logistic回歸；樸素貝葉斯分類器

分類號：

出版年·卷·期（頁碼）：2011·30·2（132-136）

摘要：

目的探討數(shù)據(jù)挖掘技術(shù)在血清腫瘤標志物（STM）聯(lián)合檢測診斷消化道惡性腫瘤（DTC）中應(yīng)用的可能性，并比較Logistic回歸模型、神經(jīng)網(wǎng)絡(luò)和樸素貝葉斯分類器及臨床單一及聯(lián)合STM診斷DTC的性能。方法對301例DTC和114例消化道良性疾病患者的血清腫瘤標志物CA19-9、CA242、CA50、CEA檢測值，分別建立基于統(tǒng)計Logistic回歸、反向傳播神經(jīng)網(wǎng)絡(luò)和樸素貝葉斯方法的診斷分類器，并進行10折交叉驗證。利用診斷敏感度、特異度和接受者操作特征（ROC）曲線下面積對三種數(shù)據(jù)挖掘分類器、CA19-9以及4種STM并聯(lián)診斷DTC的性能進行評價。結(jié)果神經(jīng)網(wǎng)絡(luò)診斷模型的敏感度和ROC曲線下面積（Az）分別為92.0%和0.903，高于STM并聯(lián)診斷的敏感度83.4%（P<0.001）和CA19-9診斷的ROC曲線下面積0.806（P<0.001），特異度69.3%與STM并聯(lián)診斷的特異度68.4%相當(dāng)（P=1.00）；Logistic回歸模型的敏感度91.4%高于STM并聯(lián)診斷（P<0.001），特異度45.6%低于STM并聯(lián)診斷（P<0.001），Az=0.819與CA19-9診斷相當(dāng)（P=0.55）；貝葉斯分類器的敏感度72.8%低于STM并聯(lián)診斷（P<0.001），特異度75.4% 和Az=0.797與STM并聯(lián)診斷和CA19-9診斷相當(dāng)（P=0.13和P=0.61）。結(jié)論數(shù)據(jù)挖掘技術(shù)的分類方法中，神經(jīng)網(wǎng)絡(luò)的分類方法比單一STM及其并聯(lián)診斷的準確性高，Logistic回歸和貝葉斯方法的診斷水平與普通STM并聯(lián)診斷水平相當(dāng)；神經(jīng)網(wǎng)絡(luò)分類器的診斷性能優(yōu)于Logistic回歸模型和貝葉斯分類器，可進一步應(yīng)用于計算機輔助診斷中。

Objective To investigate the potential applications of data mining methods in the diagnosis of digestive tract cancer (DTC) using several tumor markers(STM), and to compare the diagnostic performance for DTC with several methods of Logistic regression model, neural network, Bayesian classifier, and clinical diagnosis using a single STM and the combination of STMs. Methods Serum levels of CA19-9 , CA242 ,CA50 and CEA in 301 patients with DTC and 114 persons with benign digestive disease were used to build diagnostic classifiers based on three data mining methods, including Logistic regression, BP based neural network and Bayesian network. Ten-fold cross validation was employed to test these classifiers. The diagnostic performance was assessed and compared on the basis of sensitivity, specificity and receiver operating characteristic (ROC) curve. Results Sensitivity and the area under the ROC curve (Az) of BP neural network were 92.0% and 0.903, which were greater than the sensitivity of STM parallel diagnosis (83.4%, P<0.001) and Az value of CA19-9 (0.806, P<0.001), respectively, while the specificity (69.3%) was similar with that of STM parallel diagnosis (68.4%, P=1.00). Logistic regression model had a higher sensitivity of 91.4% than that of STM parallel diagnosis (P<0.001), a lower specificity of 45.6% than that of STM parallel diagnosis (P<0.001), and an similar Az value of 0.819 with that of STM parallel diagnosis (P=0.55). The sensitivity of Bayesian classifier was 72.8%, which was less than that of STM parallel diagnosis (P<0.001), and the specificity (75.4%) and the Az (0.797) were similar with those of STM parallel diagnosis and CA19-9 (P=0.13 and P=0.61), respectively. Conclusions BP neural network had higher diagnostic accuracy than the parallel diagnosis of the four tumor markers. Logistic regression and Bayesian network had equivalent diagnostic level to the parallel diagnosis of the four tumor markers, and BP neural network has higher diagnostic performance than the other two classifiers.

參考文獻：

［1］楊昊，張帆，周萍，等．聯(lián)合檢測血清AFP、CEA、CA 199對消化道惡性腫瘤的診斷價值［J］．實用預(yù)防醫(yī)學(xué)，2005，12（2）：296-298．
［2］潘源，宋豐舉，崔林，等．胃癌聯(lián)合檢測CA72-4 CA242 CA19-9和CEA的臨床意義與診斷價值［J］．中國腫瘤臨床，2009，36（13）：729-731．
［3］夏峰，鄭姬，王曙光，等．多腫瘤標志物的聯(lián)合檢測和分析對胰腺癌診斷的價值探討［J］．消化外科，2006，5（2）：111-114．
［4］Erol R, Oulata RN, Sahin C, et al. A radial basis function neural network (RBFNN) approach for structural classification of thyroid diseases［J］. Journal of Medical Systems, 2008, 32(3): 215-220.
［5］Murat C, Mehmet E, Erkan ZE, et al. Early prostate cancer diagnosis by using artificial neural networks and support vector machines［J］. Expert Systems with Applications, 2009, 36: 6357-6361.
［6］易靜，蘇新良，王潤華．基于數(shù)據(jù)挖掘技術(shù)的乳腺癌高位淋巴結(jié)轉(zhuǎn)移判別分類［J］．現(xiàn)代預(yù)防醫(yī)學(xué)，2008，35（13）：2410-2413．
［7］Han JW, Kamber M. Data Mining: Concepts and Techniques［M］. 2nd Ed. Maryland Heights, MO: Elsevier, 2006：285.
［8］Song JH, Venkatesh SS, Conant EA, et al. Comparative analysis of logistic regression and artificial neural network for computer-aided diagnosis of breast masses［J］. Academic Radioloy, 2005, 12:487-495.
［9］Tangri N, Ansell D, Naimark D. Predicting technique survival in peritoneal dialysis patients: comparing artificial neural networks and logistic regression［J］. Nephrology Dialysis Transplantation, 2008, 23: 2972-2981.
［10］Tsai NC, Chen CW, Hsu SL. Computer-aided diagnosis for early-stage breast cancer by using wavelet transform ［J］. Computerized Medical Imaging and Graphics, 2011, 35(1): 1-8.

服務(wù)與反饋：

【文章下載】【加入收藏】

提示：您還未登錄，請登錄！點此登錄

51黑料吃瓜在线观看,51黑料官网|51黑料捷克街头搭讪_51黑料入口最新视频