本文關(guān)鍵詞： BPNN 手足口病 重癥化進(jìn)程 MIV　出處：《鄭州大學(xué)》2014年碩士論文　論文類型：學(xué)位論文

【摘要】：目的 該研究應(yīng)用BP神經(jīng)網(wǎng)絡(luò)（BPNN）原理建立重癥手足口病相關(guān)因素和重癥化進(jìn)程預(yù)測模型，用以探討B(tài)PNN模型在重癥手足口病臨床診斷和重癥化進(jìn)程預(yù)測中的應(yīng)用價(jià)值，為手足口病的臨床診斷和流行病學(xué)研究奠定基礎(chǔ)。 方法 以手足口病流行病學(xué)現(xiàn)況調(diào)查資料為基礎(chǔ)，整群抽取河南省鄭州市某醫(yī)院2013年4－6月收治的344例手足口病患兒作為調(diào)查對象進(jìn)行問卷調(diào)查。采用MATLAB7.0軟件中的神經(jīng)網(wǎng)絡(luò)工具箱構(gòu)建BPNN模型，分析得出影響重癥手足口病臨床診斷相關(guān)因素的平均影響值（Mean Impact Value，MIV），按MIV值的絕對值大小排出因子順位，并與多因素logistic回歸模型分析結(jié)果進(jìn)行比較。對影響力較大的MIV值結(jié)果歸一化得出綜合因素水平計(jì)算公式，并根據(jù)收集的自發(fā)病到重癥過程中有完整資料的病例，進(jìn)一步分析此水平與重癥化進(jìn)程之間的關(guān)系。 結(jié)果 1.單因素logistic回歸結(jié)果顯示，精神差、血糖升高、頸強(qiáng)直、易驚、嗜睡、手足抖動、嘔吐、肢體無力、熱峰≥39℃、白細(xì)胞≥15×109/L等10個(gè)因素有意義；多因素logistic回歸結(jié)果顯示，易驚、手足抖動、嗜睡、嘔吐、精神差、白細(xì)胞≥15×109/L、頸強(qiáng)直是重癥手足口病臨床診斷的相關(guān)因素。 2.本次訓(xùn)練好的網(wǎng)絡(luò)訓(xùn)練樣本對訓(xùn)練數(shù)據(jù)的分類正確率為100%，測試樣本對測試數(shù)據(jù)的分類正確率＞90%，BPNN模型擬合較好。 3. BPNN模型最終網(wǎng)絡(luò)結(jié)構(gòu)設(shè)定為27→8→1，影響重癥手足口病前10位相關(guān)因素（MIV值絕對值）依次為：易驚（0.4614）、精神差（0.3050）、手足抖動（0.1019）、嘔吐（0.0912）、熱程≥3d（0.0711）、頸強(qiáng)直（0.0461）、白細(xì)胞≥15×109/L（0.046）、嗜睡（0.028）、血糖升高（0.015）、呼吸節(jié)律改變（0.012）。 4.通過比較BPNN模型和多因素logistic回歸結(jié)果，發(fā)現(xiàn)兩者主要臨床診斷相關(guān)因素排序順序基本一致，熱程≥3d與精神差和白細(xì)胞≥15×109/L均有交互作用（P＜0.05），熱程≥3d是一個(gè)重要的協(xié)變量。 5.在重癥手足口病重癥化進(jìn)程中，，綜合因素水平在重癥前一天之前的幾天上升趨勢明顯，在重癥前一天和重癥當(dāng)天之間略微上升，并在重癥當(dāng)天達(dá)到峰值，隨后下降。 結(jié)論 BPNN模型可用于建立重癥手足口病相關(guān)因素模型，并可對手足口病新發(fā)病例作出重癥化進(jìn)程預(yù)測，可用于手足口病的臨床診斷和重癥化進(jìn)程預(yù)測。
[Abstract]:Purpose. In this study, BP neural network (BP neural network) principle was used to establish the prediction model of severe hand, foot and mouth disease (HFMD) related factors and severity process, and to explore the application value of BPNN model in the clinical diagnosis and prognosis of severe HFMD. To lay a foundation for the clinical diagnosis and epidemiological study of hand, foot and mouth disease. Method. Based on the epidemiological data of hand, foot and mouth disease, A cluster survey was conducted on 344 children with hand, foot and mouth disease in a hospital in Zhengzhou, Henan province from April to June in 2013. The BPNN model was constructed by using the neural network toolbox of MATLAB7.0 software. The results showed that the mean value of influencing factors related to the clinical diagnosis of severe hand, foot and mouth disease was the mean value of mean Impact value, and the rank of factors excreted according to the absolute value of MIV value. The results were compared with the results of multivariate logistic regression model. The formula of comprehensive factor level was obtained by normalizing the results of the influential MIV values, and according to the collected cases with complete data from the onset to the critical stage, Further analysis of the relationship between this level and the severity process. Results. 1. The results of univariate logistic regression showed that 10 factors were significant, such as mental retardation, increased blood glucose, neck rigidity, agitation, drowsiness, wobble of hands and feet, vomiting, limb weakness, heat peak 鈮

本文編號：1533320