本文選題：肺結(jié)核 + 流行特征　； 參考：《蘭州大學(xué)》2017年碩士論文

【摘要】：目的:分析2004-2014年全國(guó)肺結(jié)核疾病監(jiān)測(cè)發(fā)病數(shù)據(jù),反映和揭示全國(guó)肺結(jié)核病的基本流行特征(高危發(fā)病年齡人群、高危發(fā)病月份和重點(diǎn)發(fā)病地區(qū))和發(fā)病趨勢(shì)。通過(guò)對(duì)各地區(qū)發(fā)病率時(shí)間軌跡進(jìn)行相似性聚類(lèi)分析研究,分離出多個(gè)具有不同肺結(jié)核發(fā)病率時(shí)間軌跡特點(diǎn)的地區(qū)類(lèi)別,為全國(guó)分類(lèi)預(yù)防和合理規(guī)劃肺結(jié)核疾病醫(yī)療衛(wèi)生資源提供依據(jù)。除此之外,為了提前預(yù)知我國(guó)各地區(qū)的肺結(jié)核發(fā)病情況,一個(gè)新型的多地區(qū)相互協(xié)作的肺結(jié)核發(fā)病預(yù)測(cè)模型(MR-GCLSSVM)被提出,對(duì)比了新構(gòu)建的多地區(qū)肺結(jié)核發(fā)病預(yù)測(cè)模型和兩個(gè)單一地區(qū)發(fā)病模型在全國(guó)32個(gè)地區(qū)肺結(jié)核發(fā)病率數(shù)據(jù)集上的預(yù)測(cè)能力,并成功地預(yù)測(cè)了2015年32個(gè)地區(qū)的肺結(jié)核發(fā)病率。研究的結(jié)果能為我國(guó)各地區(qū)肺結(jié)核防治提供定量依據(jù),也可為全國(guó)公共衛(wèi)生事業(yè)的可持續(xù)發(fā)展制定切實(shí)有效的預(yù)防和治理策略提供參考。方法:基于中國(guó)疾病預(yù)防控制中心(CDC)法定報(bào)告?zhèn)魅静?shù)據(jù)庫(kù)的肺結(jié)核疫情數(shù)據(jù),使用統(tǒng)計(jì)、群智能優(yōu)化參數(shù)與神經(jīng)網(wǎng)絡(luò)結(jié)合的方法對(duì)肺結(jié)核疫情數(shù)據(jù)進(jìn)行處理、分析和建模。本研究主要使用到的方法包括:描述性流行病學(xué)法、季節(jié)指數(shù)法、自組織特征映射聚類(lèi)方法(SOM)和MR-GCLSSVM模型(多地區(qū)的灰狼算法和交叉驗(yàn)證結(jié)合優(yōu)化參數(shù)的最小二乘支持向量機(jī)模型)。結(jié)論:1.總體趨勢(shì):全國(guó)肺結(jié)核病發(fā)病率在2005年達(dá)到最高峰值后,有明顯下降的總體趨勢(shì)。全國(guó)總體發(fā)病情況和防控狀態(tài)均表現(xiàn)良好。2.年齡分布:高危和低危發(fā)病人群分別為70-74歲和0-4歲,有明顯的年齡特征分布且為先低峰后高峰的雙峰分布特點(diǎn)。3.月份分布:肺結(jié)核發(fā)病率以一年為周期,1-6月是肺結(jié)核的流行月份,高危月份為1月、3月和4月,低危月份為9-12月。有明顯的月份分布且為自1月起至12月發(fā)病率持續(xù)下降的分布特點(diǎn)。4.地區(qū)分布:高危地區(qū)包含廣西、海南、貴州、西藏和新疆等經(jīng)濟(jì)不發(fā)達(dá)和醫(yī)療水平相對(duì)較低的地區(qū)。發(fā)病低危地區(qū)為北京、天津、上海和山東等經(jīng)濟(jì)發(fā)達(dá)和醫(yī)療衛(wèi)生水平較高的地區(qū)。肺結(jié)核病發(fā)病率的高低危地區(qū)分布和地區(qū)的經(jīng)濟(jì)發(fā)展和醫(yī)療衛(wèi)生水平可能有一定的關(guān)系。5.聚類(lèi)分析:全國(guó)各地區(qū)發(fā)病率時(shí)間軌跡的相似性聚類(lèi)研究中得出了4個(gè)具有不同發(fā)病率時(shí)間軌跡的地區(qū)類(lèi)。聚類(lèi)結(jié)果表明:貴州和新疆地區(qū)被聚類(lèi)為第1類(lèi),這兩個(gè)地區(qū)的發(fā)病率軌跡平均值普遍高于其他3類(lèi),具有很強(qiáng)的相似性。第4類(lèi)包含的地區(qū)(北京、天津、河北、遼寧、上海、江蘇、山東、云南和寧夏)發(fā)病率時(shí)間軌跡也具有較高的相似性,且有發(fā)病率軌跡平均值普遍較低的特點(diǎn)。可以根據(jù)不同的地區(qū)類(lèi)包含的特點(diǎn)采取分類(lèi)策略防控肺結(jié)核。6.多地區(qū)發(fā)病預(yù)測(cè):在多地區(qū)肺結(jié)核發(fā)病率預(yù)測(cè)上,本文提出了一個(gè)預(yù)測(cè)精準(zhǔn)度高、預(yù)測(cè)誤差小和建模方便的多地區(qū)協(xié)同的MR-GCLSSVM模型,為多地區(qū)疾病的向前預(yù)測(cè)提供了一個(gè)較先進(jìn)的模型。
[Abstract]:Objective: to analyze the data of pulmonary tuberculosis surveillance in China from 2004 to 2014, and to reveal the basic epidemic characteristics of pulmonary tuberculosis (age group, month and region) and the trend of the disease. Based on the similarity analysis of incidence time locus in different regions, several regional types with different time trajectories of pulmonary tuberculosis incidence were isolated. To provide the basis for national classification prevention and rational planning of tuberculosis disease medical and health resources. In addition, in order to predict the incidence of pulmonary tuberculosis in various regions of China in advance, a new multi-region cooperative model for predicting the incidence of pulmonary tuberculosis (MR-GCLSSVM) was proposed. In this paper, the predictive ability of the newly constructed multi-region pulmonary tuberculosis incidence prediction model and two single area incidence models on the data sets of 32 regions in the whole country were compared, and the incidence of pulmonary tuberculosis in 32 regions in 2015 was successfully predicted. The results of the study can provide quantitative basis for the prevention and control of pulmonary tuberculosis in various regions of China, and can also provide a reference for the sustainable development of public health in China to formulate effective prevention and treatment strategies. Methods: based on the data of tuberculosis epidemic in the database of infectious diseases reported by the China Center for Disease Control and Prevention, the data of tuberculosis epidemic situation were processed, analyzed and modeled by the methods of statistics, optimization parameters of swarm intelligence and neural network. The main methods used in this study include descriptive epidemiology, seasonal index, Self-organizing feature mapping clustering method (SOM) and MR-GCLSSVM model (multi-region gray wolf algorithm and cross-validation combined with optimized parameters of the least squares support vector machine model). Conclusion 1. General trend: the incidence of pulmonary tuberculosis in the country reached its highest peak in 2005, there is a significant decline in the overall trend. The overall incidence and prevention and control status of the country are good. 2. 2. Age distribution: high risk population and low risk population were 70-74 years old and 0-4 years old respectively. Monthly distribution: the incidence of pulmonary tuberculosis is one year cycle. January, March and April are the high risk months, and the low risk months are September to December in the months of January, March and April, the high risk month is January, March and April, and the low risk month is September December. There is a significant monthly distribution and the distribution of incidence from January to December continued to decline. 4. Distribution: high-risk areas include Guangxi, Hainan, Guizhou, Tibet, Xinjiang and other economically underdeveloped and relatively low level of medical care. The low risk areas are Beijing, Tianjin, Shanghai and Shandong. There may be a certain relationship between the regional distribution of tuberculosis incidence and regional economic development and the level of medical and health care. Cluster analysis: in the study of similarity of incidence time locus in different regions of China, four regional groups with different incidence time trajectories were obtained. The clustering results show that Guizhou and Xinjiang regions are clustered into the first category, and the average incidence rate of the two regions is generally higher than that of the other three groups, which has strong similarity. The time trajectories of incidence in the areas included in the fourth category (Beijing, Tianjin, Hebei, Liaoning, Shanghai, Jiangsu, Shandong, Yunnan and Ningxia) are also similar, and the average values of incidence trajectories are generally lower than those in the regions of Beijing, Tianjin, Hebei, Liaoning, Shanghai, Jiangsu, Shandong, Yunnan and Ningxia. According to the characteristics of different regional classes, classification strategies can be adopted to prevent and control tuberculosis. 6. Multi-region incidence prediction: a MR-GCLSSVM model with high prediction accuracy, small prediction error and convenient modeling was proposed in this paper. It provides a more advanced model for the forward prediction of disease in many areas.
【學(xué)位授予單位】：蘭州大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：R521;R181.3

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 李永文;程俊;王浩;趙飛;李新旭;陶武威;畢秀麗;金瑾;丁燕;耿紅;;山東省2015年肺結(jié)核發(fā)病時(shí)空特征分析[J];中華流行病學(xué)雜志;2016年09期

2 方允靜;浦棟;;灌南縣2004—2014年肺結(jié)核流行特征分析[J];海峽預(yù)防醫(yī)學(xué)雜志;2016年01期

3 張國(guó)欽;唐智多;竇立文;宋娜;李敬新;張玉華;鐘達(dá);傅衍勇;;天津市2006—2013年學(xué)生肺結(jié)核發(fā)病情況及流行病學(xué)特征[J];中國(guó)公共衛(wèi)生;2016年11期

4 林定文;余紅平;秦林原;彭娟;崔哲哲;蘇華斌;黃敏瑩;;基于時(shí)間序列模型的廣西肺結(jié)核患者登記數(shù)量發(fā)展趨勢(shì)分析[J];廣西醫(yī)學(xué);2015年09期

5 宋紅兵;洪光烈;;運(yùn)用灰色系統(tǒng)GM(1,1)模型預(yù)測(cè)安徽省肺結(jié)核發(fā)病趨勢(shì)[J];中國(guó)醫(yī)藥科學(xué);2015年08期

6 謝驍旭;袁兆康;;基于R的江西省肺結(jié)核發(fā)病率ARIMA-SVM組合預(yù)測(cè)模型[J];中國(guó)衛(wèi)生統(tǒng)計(jì);2015年01期

7 吳祖達(dá);;福州市2008—2012年學(xué)生肺結(jié)核發(fā)病特征分析[J];海峽預(yù)防醫(yī)學(xué)雜志;2014年04期

8 張磊;劉艷紅;;指數(shù)平滑法在預(yù)測(cè)深圳市寶安區(qū)肺結(jié)核病人發(fā)病人數(shù)的應(yīng)用[J];實(shí)用預(yù)防醫(yī)學(xué);2014年08期

9 莫小琴;李鐘慎;;混沌時(shí)間序列的LSSVM預(yù)測(cè)方法[J];華僑大學(xué)學(xué)報(bào)(自然科學(xué)版);2014年04期

10 陳銀蘋(píng);吳愛(ài)萍;余亮科;許雅麗;蔣寧;楊陽(yáng);張錦;張靜宇;曹燕花;;組合模型對(duì)肺結(jié)核發(fā)病趨勢(shì)的預(yù)測(cè)研究[J];中國(guó)全科醫(yī)學(xué);2014年21期

相關(guān)會(huì)議論文 前1條

1 韓琴;蘇虹;王忱誠(chéng);單曉偉;常微微;徐志偉;王靜;韓紅梅;;ARIMA模型與GRNN模型對(duì)性病發(fā)病率的預(yù)測(cè)研究[A];安徽省2011年度流行病與衛(wèi)生統(tǒng)計(jì)學(xué)學(xué)術(shù)論壇論文匯編[C];2011年

相關(guān)碩士學(xué)位論文 前4條

1 王薇;新疆維吾爾自治區(qū)2004-2014年間肺結(jié)核病流行狀況及趨勢(shì)分析[D];蘭州大學(xué);2016年

2 俞璐;基于支持向量機(jī)回歸的傳染病預(yù)測(cè)系統(tǒng)建模[D];中國(guó)科學(xué)技術(shù)大學(xué);2015年

3 齊志;基于SOM神經(jīng)網(wǎng)絡(luò)的聚類(lèi)可視化方法研究[D];東北師范大學(xué);2009年

4 萬(wàn)江;基于SOM基因聚類(lèi)的基因數(shù)據(jù)組織樣本聚類(lèi)[D];西安電子科技大學(xué);2005年

，

本文編號(hào)：2016044