本文選題：數(shù)據(jù)挖掘 + 人工神經(jīng)網(wǎng)絡�。� 參考：《青島大學》2017年碩士論文

【摘要】：目的:通過收集的包含多項預后因素的臨床資料,結(jié)合以人工神經(jīng)網(wǎng)絡的數(shù)據(jù)挖掘技術(shù),建立預測低位直腸癌患者術(shù)后5年生存狀況模型,并和傳統(tǒng)線性統(tǒng)計相關分析模型相較,評價其性能效果。方法:收集2009年1月~2011年8月在青大附院住院接受手術(shù)治療的186例罹患低位直腸癌的相關患者的臨床數(shù)據(jù)信息進行分析。并隨機將患者分為兩個集合:一組共150例,用于數(shù)據(jù)挖掘以建立疾病預后模型,為訓練集;一組共36例,不參加數(shù)據(jù)挖掘,用于模型的性能評價,為測試集。此過程中進行數(shù)據(jù)挖掘的方式是使用人工神經(jīng)網(wǎng)絡(ANN)。結(jié)果:T分期、腫瘤最大徑、是否有淋巴結(jié)轉(zhuǎn)移、是否遠處轉(zhuǎn)移、手術(shù)方式、血清CEA水平、病理類型7項指標均與低位直腸癌患者術(shù)后的5年生存相關(P0.005)。人工神經(jīng)網(wǎng)絡模型(ANN)對于患者的5年生存狀況預測,準確度為86.11%,敏感度為75.00%,特異度為89.29%,Logistic回歸模型預測的結(jié)果顯示,準確度77.78%,敏感度55.56%,特異度85.19%。總體來看ANN預測性能要好于Logistic回歸分析。結(jié)論:ANN數(shù)據(jù)挖掘技術(shù)可從與低位直腸癌患者復雜的臨床數(shù)據(jù)信息中尋找有意義的預后相關的因素,并借助這些因素通過建造預測模型,判別患者接受手術(shù)5年后的生存情況。
[Abstract]:Objective: to establish a 5 year survival model for low rectal cancer patients by collecting clinical data including multiple prognostic factors and combining with data mining technology of artificial neural network. Compared with the traditional linear statistical correlation analysis model, the performance of the model is evaluated. Methods: from January 2009 to August 2011, 186 patients with low rectal cancer who were hospitalized in Qingda affiliated Hospital were collected and analyzed. The patients were randomly divided into two sets: one group (150 cases) was used for data mining to establish disease prognosis model, the other group (36 cases) did not participate in data mining, which was used for model performance evaluation and test set. The method of data mining in this process is to use artificial neural network (Ann). Results the tumor size, tumor maximum diameter, lymph node metastasis, distant metastasis, operation mode, serum CEA level and pathological type were all correlated with 5-year survival of patients with low rectal cancer (P 0.005). The Ann model predicted the 5-year survival of patients with accuracy of 86.11, sensitivity of 75.00 and specificity of 89.290.The results of Logistic regression model showed that the accuracy was 77.78, the sensitivity was 55.56, and the specificity was 85.19. Overall, ANN prediction performance is better than Logistic regression analysis. Conclusion\
【學位授予單位】：青島大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：R735.37

【參考文獻】

相關期刊論文 前10條

1 閆以聰;;人工神經(jīng)網(wǎng)絡在醫(yī)學統(tǒng)計與信息處理方中的應用綜述[J];數(shù)理醫(yī)藥學雜志;2016年11期

2 張方圓;郁蕓;趙宇;楊坤;胡新華;;人工神經(jīng)網(wǎng)絡在臨床醫(yī)學中的應用[J];北京生物醫(yī)學工程;2016年03期

3 衛(wèi)洪波;鄭宗珩;;超低位直腸癌保肛手術(shù)技術(shù)及革新[J];國際外科學雜志;2016年01期

4 韓俊毅;陳炳官;;精準醫(yī)療背景下基因和基因組學對外科疾病治療決策的影響[J];腹部外科;2015年04期

5 陳超;郭學文;唐冬雪;曹延煒;牛海濤;;基于人工神經(jīng)網(wǎng)絡數(shù)據(jù)挖掘技術(shù)構(gòu)建浸潤性膀胱癌預后模型研究[J];泌尿外科雜志(電子版);2015年02期

6 茆家定;吳佩;楊光;武平;;超低位直腸癌保肛術(shù)的臨床應用價值[J];中華消化外科雜志;2015年06期

7 楊陽;魏東;;低位直腸癌外科治療新進展[J];國際外科學雜志;2015年05期

8 黃慶錄;李鴻飛;;腹腔鏡低位直腸癌保肛手術(shù)的研究進展[J];中國微創(chuàng)外科雜志;2015年01期

9 肖峰;丁明躍;尉遲明;;基于運動量的神經(jīng)網(wǎng)絡心率預測器的設計及對比研究[J];北京生物醫(yī)學工程;2014年04期

10 傅曉華;洪曉丹;劉石帶;葉毅芳;容穎慈;陳小陸;任斌;;人工神經(jīng)網(wǎng)絡模型在腎移植患者他克莫司個體化給藥中的應用[J];中國藥學雜志;2013年12期

，

本文編號：1923474