泌尿外科杂志（电子版）
泌尿外科雜誌（電子版）
비뇨외과잡지（전자판）
JOURNAL OF UROLOGY FOR CLINICIAN(ELECTRONIC VERSION)
2015年
2期
38-42
,共5页
陈超%郭学文%唐冬雪%曹延炜%牛海涛
陳超%郭學文%唐鼕雪%曹延煒%牛海濤
진초%곽학문%당동설%조연위%우해도
数据挖掘%人工神经网络(ANN)%浸润性膀胱癌%预后模型
數據挖掘%人工神經網絡(ANN)%浸潤性膀胱癌%預後模型
수거알굴%인공신경망락(ANN)%침윤성방광암%예후모형
Data mining techniques%Artificial Neural Network (ANN)%Invasive bladder cancer%Predic-tion model
目的：运用人工神经网络数据挖掘技术分析与浸润性膀胱癌患者预后有关的各种因素建立预测浸润性膀胱癌患者5年生存状态的预后模型，并与传统的Logistic回归分析比较评价其效果。方法收集从2006年1月至2009年12月在我院接受诊治的134例浸润性膀胱癌患者的资料。所采用数据挖掘技术为人工神经网络（ANN）。将所有病例分为两组：一组作为训练样本，不参与数据挖掘过程，共计27例；一组用于筛选变量及建立预测模型，参与数据挖掘过程共计107例。应用Logistic回归模型的相关评价指标来比较两种方法对于评价预后模型的准确度。结果 T分期、肿瘤直径、是否有淋巴结转移、肿瘤单发及多发、手术方式、病理分级，6项指标均与浸润性膀胱癌患者的5生存状态相关（P＜0．05）。ANN模型预测患者5年生存状态的准确率为85．18％、敏感度为57．14％和特异度为95．00％，Logistic回归模型的相关评价指标，准确率77．78％、敏感度44．44％、特异度94．44％。神经网络各项指标均优于Logistic回归模型。结论数据挖掘技术可从与浸润性膀胱癌患者预后相关的大量信息中挖掘出有意义的指标，并利用这些指标建立预测模型来判断患者5年后的生存状态。
目的：運用人工神經網絡數據挖掘技術分析與浸潤性膀胱癌患者預後有關的各種因素建立預測浸潤性膀胱癌患者5年生存狀態的預後模型，併與傳統的Logistic迴歸分析比較評價其效果。方法收集從2006年1月至2009年12月在我院接受診治的134例浸潤性膀胱癌患者的資料。所採用數據挖掘技術為人工神經網絡（ANN）。將所有病例分為兩組：一組作為訓練樣本，不參與數據挖掘過程，共計27例；一組用于篩選變量及建立預測模型，參與數據挖掘過程共計107例。應用Logistic迴歸模型的相關評價指標來比較兩種方法對于評價預後模型的準確度。結果 T分期、腫瘤直徑、是否有淋巴結轉移、腫瘤單髮及多髮、手術方式、病理分級，6項指標均與浸潤性膀胱癌患者的5生存狀態相關（P＜0．05）。ANN模型預測患者5年生存狀態的準確率為85．18％、敏感度為57．14％和特異度為95．00％，Logistic迴歸模型的相關評價指標，準確率77．78％、敏感度44．44％、特異度94．44％。神經網絡各項指標均優于Logistic迴歸模型。結論數據挖掘技術可從與浸潤性膀胱癌患者預後相關的大量信息中挖掘齣有意義的指標，併利用這些指標建立預測模型來判斷患者5年後的生存狀態。
목적：운용인공신경망락수거알굴기술분석여침윤성방광암환자예후유관적각충인소건립예측침윤성방광암환자5년생존상태적예후모형，병여전통적Logistic회귀분석비교평개기효과。방법수집종2006년1월지2009년12월재아원접수진치적134례침윤성방광암환자적자료。소채용수거알굴기술위인공신경망락（ANN）。장소유병례분위량조：일조작위훈련양본，불삼여수거알굴과정，공계27례；일조용우사선변량급건립예측모형，삼여수거알굴과정공계107례。응용Logistic회귀모형적상관평개지표래비교량충방법대우평개예후모형적준학도。결과 T분기、종류직경、시부유림파결전이、종류단발급다발、수술방식、병리분급，6항지표균여침윤성방광암환자적5생존상태상관（P＜0．05）。ANN모형예측환자5년생존상태적준학솔위85．18％、민감도위57．14％화특이도위95．00％，Logistic회귀모형적상관평개지표，준학솔77．78％、민감도44．44％、특이도94．44％。신경망락각항지표균우우Logistic회귀모형。결론수거알굴기술가종여침윤성방광암환자예후상관적대량신식중알굴출유의의적지표，병이용저사지표건립예측모형래판단환자5년후적생존상태。
Objectives Using the data mining techniques to analysis the various factors associated with the prognosis of patients with invasive bladder cancer,then establish survival prediction model of five years in pa-tients with invasive bladder cancer,and evaluate its results by comparing with the traditional Logistic regression analysis. Methods Data of total of 134 cases of patients with invasive bladder cancer from January 2006 to De-cember 2009 in our hospital were collected. All the cases can be divided into two groups:a group as the training sample,used to screen variables and establishment of prediction model,a total of 107 cases are involved in data mining process;The other group (a total of 27 cases)was used as a validation sample,a set of evaluation model of effect,is not involved in data mining process. Artificial neural network was used in the process of data mining technique. Results T stage,tumor diameter,whether to have lymph node metastasis,tumor(single and multi-ple),operation method and pathology classification,six indexes are all related to the five years rate of survival for the patients with invasive bladder cancer(P<0. 05). ANN model predict the accuracy rate of 5 years rate of survival is 85 . 18%,sensitivity to 57 . 14% and specific degrees for 95 . 00%,related evaluation index of Logis-tic regression model,accuracy rate 77. 78%,degree of sensitiveness 44. 44%,specificity 94. 44%. All the in-dicators of ANN are better than Logistic regression model. Conclusions Data mining techniques can excavate meaningful indicators from a lot of information associated with the prognosis of patients with invasive bladder cancer,and establish the prediction model based on these indicators to determine the survival state of the pa-tients after five years.
