發(fā)布時間：2018-03-24 12:44

  本文選題：肝硬化　切入點：BP神經(jīng)網(wǎng)絡(luò)　出處：《山西醫(yī)科大學(xué)》2017年碩士論文

【摘要】：目的:將遺傳算法BP神經(jīng)網(wǎng)絡(luò)模型引入到肝硬化的病例數(shù)據(jù)資料中,對肝硬化分期診斷的分類進行預(yù)測分析,利用遺傳算法對BP神經(jīng)網(wǎng)絡(luò)的優(yōu)化作用,彌補BP神經(jīng)網(wǎng)絡(luò)自身的不足,從而提高肝硬化分期分類預(yù)測效果。方法:通過收集2006年1月到2015年12月近10年的山西醫(yī)科大學(xué)第一附屬醫(yī)院消化內(nèi)科被診斷為肝硬化的住院患者的病例資料,針對數(shù)據(jù)的特點,分別對肝硬化分期數(shù)據(jù)分別進行Logistic回歸、BP神經(jīng)網(wǎng)絡(luò)和遺傳算法BP神經(jīng)網(wǎng)絡(luò)模型的建模和預(yù)測。對三種模型進行比較。選擇合適的模型對肝硬化分期數(shù)據(jù)進行分類預(yù)測。結(jié)果:1、分別對Logistic回歸、BP神經(jīng)網(wǎng)絡(luò)和GA-BP建模和預(yù)測,結(jié)果顯示:GA-BP的ACC中位數(shù)達到90%,高于BP神經(jīng)網(wǎng)絡(luò)83.33%,遠高于Logistic回歸46.67%;GA-BP的TPR中位數(shù)達到95.55%,高于BP神經(jīng)網(wǎng)絡(luò)90.23%,遠高于Logistic回歸48.14%;GA-BP的TNR中位數(shù)達到75%,高于BP神經(jīng)網(wǎng)絡(luò)62.5%,遠高于Logistic回歸50%;GA-BP的PV+中位數(shù)達到95.35%,高于BP神經(jīng)網(wǎng)絡(luò)91.30%,遠高于Logistic回歸80%;GA-BP的PV-中位數(shù)達到77.80%,高于BP神經(jīng)網(wǎng)絡(luò)57.10%,遠高于Logistic回歸19.40%;GA-BP的AUC中位數(shù)達到84.4%,高于BP神經(jīng)網(wǎng)絡(luò)74.9%,遠高于Logistic回歸48.7%。2、比較遺傳算法優(yōu)化前后的預(yù)測效果,結(jié)果顯示:優(yōu)化前,ACC是73.33%,優(yōu)化后,ACC可以達到90%,預(yù)測性能得到了改善和提升。其他五個預(yù)測評價指標(biāo)也是優(yōu)化后更高。結(jié)論:研究數(shù)據(jù)首先將Logistic回歸與BP神經(jīng)網(wǎng)絡(luò)比較分析,BP神經(jīng)網(wǎng)絡(luò)更適合處理本次研究數(shù)據(jù)。再用遺傳算法來優(yōu)化BP神經(jīng)網(wǎng)絡(luò),可以使分類預(yù)測效果提高�？梢缘贸鲞z傳算法優(yōu)化方法的肝硬化分期分類預(yù)測效果較BP神經(jīng)網(wǎng)絡(luò)有較大的提高,具有對肝硬化分期分類預(yù)測的可行性。
[Abstract]:Objective: the genetic algorithm BP neural network model is introduced into the case data of liver cirrhosis, classification of diagnosis of liver cirrhosis were predictive analysis, optimization function based on genetic algorithm BP neural network, BP neural network to compensate for the lack of their own, so as to improve the classification effect of cirrhosis stages. Methods: collected from January 2006 through the First Affiliated Hospital in December 2015 to nearly 10 years of Shanxi Medical University was diagnosed as liver cirrhosis patients, according to the characteristics of data, respectively, on the stage of cirrhosis data Logistic regression, modeling and prediction of BP neural network and genetic algorithm BP neural network model. The comparison of three models. Choose a suitable model of staging data classification the prediction of liver cirrhosis. Results: 1, respectively, of Logistic regression, BP neural network and GA-BP modeling and prediction results: GA-BP the median of ACC reached 90%, 83.33% higher than the BP neural network, Logistic regression is much higher than 46.67%; median TPR GA-BP reached 95.55%, 90.23% higher than that of BP neural network, Logistic regression is much higher than 48.14%; median TNR GA-BP reached 75%, higher than the BP neural network is 62.5%, much higher than the median 50% Logistic regression; PV+ GA-BP reached 95.35% 91.30%, higher than the BP neural network, Logistic regression is much higher than 80%; median PV- GA-BP reached 77.80%, 57.10% higher than that of BP neural network, Logistic regression is much higher than 19.40%; median AUC GA-BP reached 84.4%, higher than the BP neural network is 74.9%, far higher than the Logistic 48.7%.2 regression, the prediction effect, compared before and after optimization of genetic algorithm optimization results show: before, ACC is 73.33%, after optimization, ACC can reach 90%, the prediction performance has been improved. The other five prediction evaluation index is optimized after higher. Conclusion: the first research data The comparative analysis of Logistic regression and BP neural network, BP neural network is more suitable for processing the research data. Then the genetic algorithm to optimize BP neural network, can make the classification prediction effect can be obtained. To improve the genetic algorithm optimization method of classification of cirrhosis stages compared with BP neural network prediction effect is greatly improved, the feasibility of liver cirrhosis stage classification and prediction.

【學(xué)位授予單位】：山西醫(yī)科大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：R575.2

【參考文獻】

相關(guān)期刊論文 前10條

1 謝多雙;胡僊;李瑞;羅清欽;符湘云;王惠芳;聶紹發(fā);;醫(yī)院感染人工神經(jīng)網(wǎng)絡(luò)預(yù)測模型的構(gòu)建[J];湖北醫(yī)藥學(xué)院學(xué)報;2015年03期

2 李曉峰;楊春山;王雪梅;丁樹春;;基于BP神經(jīng)網(wǎng)絡(luò)的乳腺癌患者存活概率的預(yù)測分析[J];計算機系統(tǒng)應(yīng)用;2014年05期

3 咼潤華;蘇婷婷;馬曉偉;;BP神經(jīng)網(wǎng)絡(luò)聯(lián)合模板匹配的車牌識別系統(tǒng)[J];清華大學(xué)學(xué)報(自然科學(xué)版);2013年09期

4 宋宇辰;甄莎;;BP神經(jīng)網(wǎng)絡(luò)和時間序列模型在包頭市空氣質(zhì)量預(yù)測中的應(yīng)用[J];干旱區(qū)資源與環(huán)境;2013年07期

5 尹光志;李銘輝;李文璞;曹偈;李星;;基于改進BP神經(jīng)網(wǎng)絡(luò)的煤體瓦斯?jié)B透率預(yù)測模型[J];煤炭學(xué)報;2013年07期

6 劉清云;呂艷輝;;改進的BP神經(jīng)網(wǎng)絡(luò)在醫(yī)療中的應(yīng)用研究[J];沈陽理工大學(xué)學(xué)報;2013年03期

7 王軼夫;孫玉軍;郭孝玉;;基于BP神經(jīng)網(wǎng)絡(luò)的馬尾松立木生物量模型研究[J];北京林業(yè)大學(xué)學(xué)報;2013年02期

8 白鶴鳴;沈潤平;師華定;董鈺春;;基于BP神經(jīng)網(wǎng)絡(luò)的空氣污染指數(shù)預(yù)測模型研究[J];環(huán)境科學(xué)與技術(shù);2013年03期

9 崔東文;;多隱層BP神經(jīng)網(wǎng)絡(luò)模型在徑流預(yù)測中的應(yīng)用[J];水文;2013年01期

10 胡海青;張瑯;張道宏;;供應(yīng)鏈金融視角下的中小企業(yè)信用風(fēng)險評估研究——基于SVM與BP神經(jīng)網(wǎng)絡(luò)的比較研究[J];管理評論;2012年11期

相關(guān)碩士學(xué)位論文 前10條

1 丁曉玲;不同病因肝硬化臨床特征對比分析[D];寧夏醫(yī)科大學(xué);2013年

2 梁麗;1048例住院肝硬化患者病因及臨床特征分析[D];重慶醫(yī)科大學(xué);2012年

3 韓榮榮;基于遺傳算法的BP神經(jīng)網(wǎng)絡(luò)在多目標(biāo)藥物優(yōu)化分析中的應(yīng)用[D];山西醫(yī)科大學(xué);2011年

4 楊洋;利用人工神經(jīng)網(wǎng)絡(luò)模型預(yù)測原發(fā)性高血壓的研究[D];中國醫(yī)科大學(xué);2010年

5 倪然;人工神經(jīng)網(wǎng)絡(luò)聯(lián)合腫瘤標(biāo)志對肺癌和大腸癌的預(yù)警[D];鄭州大學(xué);2009年

6 凌建春;社區(qū)計生、衛(wèi)生部門聯(lián)合開展艾滋病自愿咨詢檢測服務(wù)可行性研究[D];山西醫(yī)科大學(xué);2009年

7 呂瑩;肝硬化與舌質(zhì)改變的相關(guān)性研究[D];廣州中醫(yī)藥大學(xué);2008年

8 張紅升;人工神經(jīng)網(wǎng)絡(luò)技術(shù)在肺癌CT診斷中的應(yīng)用[D];鄭州大學(xué);2007年

9 周昕;基于BP神經(jīng)網(wǎng)絡(luò)的人臉識別技術(shù)的研究[D];南京理工大學(xué);2007年

10 潘e，

本文編號：1658350