【摘要】：心腦血管疾病死亡居死因首位。流行病學(xué)統(tǒng)計與病理學(xué)研究均證明了氣象、污染因子的變化與心腦血管疾病事件發(fā)生之間有密切的聯(lián)系�；诔墒斓臍庀�、污染預(yù)報系統(tǒng)進(jìn)行心腦血管疾病事件發(fā)生的預(yù)報可以對特定人群進(jìn)行提前干預(yù)，減少疾病的發(fā)病率與病死率。本文使用北京市4年氣象、污染與醫(yī)院急診記錄，通過統(tǒng)計方法分析三者之間的影響關(guān)系，采用人工神經(jīng)網(wǎng)絡(luò)和支持向量機(jī)兩種人工智能方法建立以氣象、污染因子為輸入變量預(yù)測心腦血管疾病急診量的模型。 收集北京市2008-2011三甲醫(yī)院急診就診記錄與同期的常規(guī)氣象、污染監(jiān)測資料,如氣溫、氣壓、濕度、風(fēng)速、SO2濃度、NO2濃度、Pm10濃度等。對醫(yī)療資料中的診斷結(jié)果進(jìn)行規(guī)范化，并提取ICD-10編碼為I00-I99范圍內(nèi)的條目為本文急診量資料。對數(shù)據(jù)進(jìn)行初步統(tǒng)計分析，發(fā)現(xiàn)氣象、污染因子之間存在復(fù)雜的中高度線性相關(guān)關(guān)系，不適合對輸入變量個數(shù)敏感的建模方法；急診量資料存在年份增長效應(yīng)，引入年份啞變量作為輸入變量加以控制；輸入變量與輸出變量的線性相關(guān)不高，因此對所有變量進(jìn)行7天平滑處理。 人工智能方法對于復(fù)雜的、非線性模型有著獨特的優(yōu)勢。經(jīng)過上述處理后的1455條數(shù)據(jù)按照建模過程需要隨機(jī)分為訓(xùn)練集、測試集和獨立樣本集三組。分別使用帶動量因子的BP神經(jīng)網(wǎng)絡(luò)與支持向量機(jī)回歸模型進(jìn)行擬合實驗。訓(xùn)練數(shù)據(jù)的特征與模型參數(shù)的選擇一同影響最終的建模效果，因此本文分別比較了兩種建模方法中如隱含層單元數(shù)、懲罰因此等具有代表性意義的參數(shù)變化對測試集平均絕對誤差的影響情況，，進(jìn)行了模型參數(shù)優(yōu)化。最終選擇兩種建模方法下的最適合于本文數(shù)據(jù)的模型。 在獨立樣本集上的預(yù)測效果檢驗上，人工神經(jīng)網(wǎng)絡(luò)模型與支持向量機(jī)回歸模型的預(yù)測值序列與原值序列均呈現(xiàn)高度線性相關(guān)，而后者所得結(jié)果的平均絕對誤差更低,且對高峰、低谷值這類少數(shù)樣本的預(yù)測效能比前者好。最終選擇以徑向基為核函數(shù)的支持向量機(jī)回歸模型為本研究中氣象、污染因子影響心腦血管疾病急診量的最適模型。
[Abstract]:Cardiovascular and cerebrovascular diseases were the leading cause of death. Epidemiological statistics and pathological studies have proved that there is a close relationship between meteorology, pollution factors and the occurrence of cardiovascular and cerebrovascular diseases. Based on the mature meteorology, the pollution forecasting system can predict the occurrence of cardiovascular and cerebrovascular diseases in advance and reduce the morbidity and mortality of the disease. In this paper, four years of meteorological records, pollution and hospital emergency records in Beijing are used to analyze the relationship between them, and artificial neural network and support vector machine (SVM) are used to establish meteorology. The pollution factor is an input variable to predict the emergency volume of cardiovascular and cerebrovascular diseases. To collect the records of emergency visits and routine meteorological and pollution monitoring data such as air temperature, air pressure, humidity, wind speed, SO2 concentration, NO2 concentration, Pm10 concentration and so on. The diagnostic results in medical data were standardized, and the items encoded by ICD-10 into I00-I99 were extracted for the emergency volume data of this article. A preliminary statistical analysis of the data shows that there is a complex linear correlation between meteorological and pollution factors, which is not suitable for modeling methods sensitive to the number of input variables. The emergent data have the effect of annual growth, and the year dummy variable is introduced as input variable to be controlled, and the linear correlation between input variable and output variable is not high, so all variables are smoothed for 7 days. Artificial intelligence has unique advantages for complex, nonlinear models. The 1455 data processed above are randomly divided into three groups: training set, test set and independent sample set according to the need of modeling process. BP neural network with driving factor and support vector machine regression model are used for fitting experiment. The characteristics of training data and the selection of model parameters affect the final modeling effect, so this paper compares the two modeling methods such as the number of hidden layer units. Therefore, the model parameters are optimized by the influence of the representative parameter changes on the average absolute error of the test set. Finally, we choose the most suitable model for the data of this paper under the two modeling methods. In the test of prediction effect on independent sample set, the prediction value series of Ann model and support vector machine regression model are highly linearly correlated with original value series, and the average absolute error of the results obtained from the latter is lower, and the average absolute error of the results is lower, and the average absolute error of the results is higher than that of the support vector machine regression model. The prediction efficiency of a few samples such as low value is better than that of the former. Finally, the support vector machine regression model with radial basis function as kernel function is chosen as the optimal model for the influence of pollution factors on emergency volume of cardiovascular and cerebrovascular diseases in this study.
【學(xué)位授予單位】：華南理工大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2013
【分類號】：TP18;R122.2

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 何麗華,張金良,張穎,王生,葉康平,石紅梅,鄭小雨,陳斌;高溫對大鼠血壓及血管活性物質(zhì)的影響[J];北京大學(xué)學(xué)報(醫(yī)學(xué)版);2005年04期

2 王睿;;關(guān)于支持向量機(jī)參數(shù)選擇方法分析[J];重慶師范大學(xué)學(xué)報(自然科學(xué)版);2007年02期

3 施曉耕;梁鳳萍;黃聿;黃如訓(xùn);;人工寒潮對高血壓和正常血壓大鼠腦血管收縮反應(yīng)性的不同影響[J];第四軍醫(yī)大學(xué)學(xué)報;2007年16期

4 任傳成,劉久波,葉天雄,李茂玉;氣象因素對ET、TXB_2、6-Keto-PGF_1α的影響[J];放射免疫學(xué)雜志;1999年01期

5 王一飛;;21世紀(jì)的4P醫(yī)學(xué)與生殖健康[J];國際生殖健康/計劃生育雜志;2010年01期

6 劉方,張金良,陸晨,吳桂賢;北京地區(qū)氣溫與急性冠心病的時間序列研究[J];環(huán)境與健康雜志;2005年04期

7 馬玉霞;謝月玉;王式功;尚可政;;人工神經(jīng)網(wǎng)絡(luò)方法在氣象因素預(yù)測高血壓發(fā)病中的應(yīng)用[J];環(huán)境與健康雜志;2007年03期

8 楊敏娟;潘小川;;北京市大氣污染與居民心腦血管疾病死亡的時間序列分析[J];環(huán)境與健康雜志;2008年04期

9 劉利群;潘小川;鄭亞安;Wichmann HE;Franck U;;氣象因素與心腦血管疾病急診人次的時間序列分析[J];環(huán)境與健康雜志;2008年07期

10 李國星;郭玉明;王佳佳;潘小川;;2004—2006年北京夏季最低氣溫對心腦血管疾病急診數(shù)的影響[J];環(huán)境與健康雜志;2009年08期

相關(guān)碩士學(xué)位論文 前4條

1 方寧;氣象因素對山西省長治市五種常見疾病的急診狀態(tài)發(fā)生的影響[D];中南大學(xué);2011年

2 高磊;基于人工神經(jīng)網(wǎng)絡(luò)的心血管疾病醫(yī)療氣象預(yù)警模型設(shè)計[D];山東大學(xué);2010年

3 周麗君;腦梗死患者血流動力學(xué)的季節(jié)性變化[D];南昌大學(xué);2010年

4 席秋江;寒潮條件下腦血管病發(fā)病的相關(guān)因素及機(jī)制的研究[D];南昌大學(xué);2010年

本文編號：2400466