跳到主要內容

臺灣博碩士論文加值系統

(44.192.38.248) 您好!臺灣時間:2022/11/27 07:52
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:鄧仲華
研究生(外文):Chung-Hua Teng
論文名稱:評估以非侵入方法在家預測高膽固醇血症檢查結果
論文名稱(外文):Using Non- invasive Method for Predicting Hypercholesterolemia Risk at Home
指導教授:邱泓文邱泓文引用關係
指導教授(外文):Hung-Wen Chiu
學位類別:碩士
校院名稱:臺北醫學大學
系所名稱:醫學資訊研究所
學門:醫藥衛生學門
學類:醫學技術及檢驗學類
論文種類:學術論文
論文出版年:2015
畢業學年度:103
語文別:中文
論文頁數:62
中文關鍵詞:自動神經元高膽固醇血症佛萊明罕危險預估評分表邏輯斯?A規決策樹型支持向量機腰圍身高比
外文關鍵詞:Artificial Neural NetworkhypercholesterolemiaFramingham Risk Scorespecific logistic meter loop regulationdecision tree support vector machineWHtR (waist-to-height ratio)
相關次數:
  • 被引用被引用:0
  • 點閱點閱:95
  • 評分評分:
  • 下載下載:2
  • 收藏至我的研究室書目清單書目收藏:0
高膽固醇血症(hyperlipidemia)為許多心血管與腦血管疾病的重要前驅因子,許多國人的十大死因,都和心血管與腦血管疾病有關,若能早期發現高膽固醇血症並且配合運動飲食及藥物治療,將可避免許多重大疾病的發生及惡化。

此研究以自動神經元(Artificial Neural Network, ANN),分析非侵入性身體檢查以預測高膽固醇血症的結果,分析資料期間為2012年期間 ,共收集1003名新竹科學園區新人體檢驗數據,以2006年行政院衛生署公布的代謝症候群標準及佛萊明罕危險預估評分表(Framingham Risk Score)以及和膽固醇風險因子有關的文獻。選取非侵入性檢查項目,並且容易在家量測之項目,包括年齡,腰圍身高比WhtR (waist-to-height ratio,腰圍除以身高值),身體質量指數BMI,抽菸,腰圍,高血壓,吸菸以預測高膽固醇血症發生的機率,軟體採用STATISACA 10.0 分析類神經網路,70%為訓練組(703人),30%為測試組(300人)。在1003個案例中,平均年齡為35.2歲,最小15歲,最大59歲。有288人(28.71%)為高膽固醇血症的患者6個變數除了抽菸以外在高膽固醇與無高膽固醇血症之間都有顯著差異(p value < 0.05)。測試使用不同神經元數目時,對ANN預測結果的差異性,分別測試了3、4、5、9及10個神經元,以4個神經元對高膽固醇血症預測結果較佳,類神經網路預測模型整體預測結果 ,正確率(accury)89.63%,敏感度(Sensitivity) 為75.00%,特異性(Specificity)95.52%與ROC曲線下面積為0.94。ANN與使用相同參數邏輯斯?A歸(logistic regression)和支持向量機SVM(support vector machine)比較有較佳的結果。

雖然醫療院所在台灣已經非常發達,但民眾定時量測抽血仍需耗時耗力,對健保及民眾的負擔也會增加。而這世界還是有很多地區不易抽血檢查。所以發展能在家中自行推估疾病的風險,還是有其重要性。 以ANN預測五項變數年齡,腰圍身高比WHtR,身體質量指數BMI,腰圍,高血壓可以在家的測量項目的結果,可以用來預測高膽固醇血症的可能性。

WHtR在各項變數中與高膽固醇血症有最高的相關係數,且在相關文獻中對成人高血壓,第二型糖尿病,高血脂,心血管疾病比BMI和腰圍統計顯著性更佳,顯示WHTR為優於WC和BMI檢測心血管代謝危險因素。建議WHtR應列入新的健康指標,良好的WhtR應小於0.5 。


High blood cholesterol (Hypercholesterolemia) is precursor of many cardiovascular and cerebrovascular diseases. Cardiovascular and cerebrovascular diseases are also two major diseases of top ten leading cause of death of Taiwanese people. Early detect hypercholesterolemia and combined with exercise, diet and drug treatment could avoid the deterioration of many major diseases. This study use ANN (Artificial Neural Network) to analysis non-invasive medical examination and predict the outcome of hypercholesterolemia.
1003 new employee physical examination data were collected from the Hsinchu
Science Park. According Department of Health in Taiwan published standards of metabolic syndrome 2006, Framingham Risk Score and the literature of cholesterol risk factors, select noninvasive and easy measure at home risk factors of hypercholesterolemia. The risk factor including age, WHtR (waist-to-height ratio), body mass index (BMI), smoking, waist circumference, blood pressure, smoking predicts the probability of occurrence. The analysis software uses STATISACA 10.0 for ANN. 703 physical examination persons (70%) as training group, the rest 300 person (30%) as the test group . In these 1003 case, the average age is 35.2 years old (maxima age is 59 and minima age is 15), 289 case has Hypercholesterolemia. Six risk factor has significant differences (p<0.005) besides smoking. Use 3,4,5,9 and 10 number of neuron for predict hypercholesterolemia, 4 number of neuron has better outcome. Our result demonstrated that our ANN model can predict the occurrence of hypercholesterolemia people, the overall accuracy of this ANN is 89.63%, sensitivity is 75.00%, specificity is 95.52% and ROC area is 0.94 .ANN model compare logistic regression and SVM(support vector machine) which has better result.
Although health care system is consummate in Taiwan .People take blood test still cost money and time. And still has some backwater area difficult to take blood test. It’s important to develop non-invasion method to measure hypercholesterolemia.
Our study highlight the ANN model analysis use 5 risk factor include age, WHtR, BMI waist and hypertension can predict the occurrence of hypercholesterolemia.
WHtR has better correlation coefficient in these variables and in pertinent literature has better statistically significance in adult hypertension, diabetes mellitus, hypercholesterolemia and cardiovascular disease. We suggest WhtR should be as a new health indicator in Taiwan, a favorable WHtR value should be less than 0.5.


目錄

頁數
標題 i
學位考試委員審定書 ii
論文書目同意公開申請書 iii
學位考試保密同意書暨簽到表 iv
誌謝 v
目錄 vii
表目錄 ix
圖目錄 x
中文摘要 xi
英文摘要 xiii
第一章 緒論
1.1 研究動機 1
1.2 研究目的 3
第二章 文獻探討
2.1 高膽固醇血症的病理生理學 4
2.2 慢性病平均年齡的下降 6
2.3 國人十大死因和高膽固醇血症 7
2.4 現行台灣的膽固醇檢驗政策 9
2.5 膽固醇與心血管及代謝症候群預測相關的研究 11
2.6 非侵入性膽固醇檢測法 12
2.7 資料探勘與類神經網路在膽固醇及心血管相關的文獻 14
2.8 文獻整理與分析 16
第三章 研究材料與方法
3.1 研究架構 17
3-2 病患收集及分析 18
3.3.1 類神經網路 21
3.3.2 邏輯斯?A歸 22
3.3.3 支持向量機 23
3.4 統計分析方法 24
3.5 倫理考量 25
第四章 分析與結果
4.1 資料分析 26
4.2 神經網路預測模型的建立與效能評估 33
4.2.1 類神經網路預測模型建立 33
4.2.2 類神經網路預測模型效能評估 35
4.3 邏輯斯?A歸模型建置與效能評估 42
4.4 支持向量機SVM(support vector machine)模型建置與效能評估 44
第五章 討論與結論
5.1 討論 48
5.1.1 與相關研究之比較 48
5.1.2 類神經網路預測模型與邏輯斯迴歸模型相比 49
5.1.3 類神經網路預測模型與SVM模型相比 50
5.2 結論 51
5.3 研究限制 53
5.4 未來展望 55

參考資料
英文文獻 56
中文文獻 58
附錄
附錄一 佛萊明罕指數評分表 59










表目錄

表2-1 101年國人十大死因 7
表3-1 個案輸入資料變項分類表 20
表4-1年齡及身高腰圍比預測對高膽固醇血症變數統計 26
表4-2:高膽固醇血症與體重過重之卡方檢定 26
表4-3:高膽固醇血症與高血壓之卡方檢定 27
表4-4:高膽固醇血症與腰圍超標之卡方檢定 27
表4-5:高膽固醇血症與有無吸菸之卡方檢定 28
表4-6 各項變數與高膽固醇血症相關係數分析 32
表4-7 更改隱藏層神經元數目的ANN預測能力統計 35
表4-8 ANN Training set 預測結果表 36
表4-9 ANN Test set 預測結果表 38
表4-10 ANN over all 預測結果表 40
表4-11 類神經網路與邏輯斯?A歸效能表 43
表4-12 SVM 訓練組預測結果表 44
表4-13 類神經網路與SVM 訓練組效能表 45
表4-14 SVM 測試組預測結果表 45
表4-15 類神經網路與SVM 測試組效能表 46
表4-16 SVM Over all 預測結果表 46
表4-17 類神經網路與SVM over all效能表 47




圖目錄
圖3-1研究架構圖 17
圖3-2 類神經網路示意圖 21
圖3-3 STATISTICA操作介面 24
圖4-1 病患的年齡的分布於95%信賴區間鬚盒圖 27
圖4-2 病患的(WHtR)的分布於95%信賴區間鬚盒圖 27
圖4-3 病患的身體質量指數(BMI)的分布於95%信賴區間鬚盒圖 28
圖4-4病患的收縮壓(SBP)的分布於95%信賴區間鬚盒圖 28
圖4-5 病患的舒張壓(DSBP)的分布於95%信賴區間鬚盒圖 29
圖4-6 病患的腰圍(waist)的分布於95%信賴區間鬚盒圖 29
圖4-7 類神經網路示意圖 32
圖4-8 ANN訓練組 ROC Curve 35
圖4-9 ANN測試組 ROC Curve 37
圖4-10 ANN Over all ROC Curve 39
圖4-11 邏輯斯?A歸模型預測結果ROC Curve 40


[1]St. Louis. 2006. Textbook of Clinical Chemistry and Molecular Diagnosis. 4th ed., 938 – 952. Missouri .Elsevier Saunders
[2]Chou P., Li CL, Tsai ST, 2001. Epidemiology of type 2 diabetes in Taiwan, Diabetes Res Clin Pract; 39(suppl.1): S29-S35.
[3]Luo W, Guo Z, Wu M, Hao C, Zhou Z, Yao X. 2014 Jun 16.Index of central obesity as a parameter to replace waist circumference in definition of metabolic syndrome in predicting cardiovascular disease. J Cardiovasc Med (Hagerstown) 2014 Jun 16.
[4]Anthony D., George P., Eaton C. 2014 Jun. Cardiac risk factors: biomarkers and genetic tests to determine cardiovascular risk. 421:11-5.FP Essent
[5] Cheng-Ding Chang, Chien. Chih Wang, Bernard. Jiang.2010.Using data mining techniques for multi-diseases prediction modeling of hypertension and hyperlipidemia by common risk factors.Expert Systems with Applications 38 (2011) 5507–5513
[6] Chan S, Frochlich J, et al. 2002.Association of skin cholesterol content, measured by a non-invasive method, with markers of inflammation and Framingham risk prediction. Am J Cardiol Mancini J, 89:1313-16.
[7] Suo YK1, Li G, Wang HQ, Lin L. Guang Pu Xue Yu Guang Pu Fen Xi. 2012 Jan. Non-invasive measurement of human blood cholesterol concentration based on dynamic spectrum method; 32(1):188-91.
[8] S.V. Mahesh Kumar, R. Gunasundari ,2013.Comparative Analysis and Earlier Detection of Cholesterol Based on the Measurement of Various Lipid Level Deposits in the Eye. Dital Image Processing.Vol5, No.7
[9] N.R. Shanker, A. Ezhil, S. Archana .2012.Non-invasive method of detection of cholesterol using image processing. International Journal of Medical Engineering and Informatics, 4 (3): 223 DOI: 10.1504/IJMEI.2012.048384
[10]M. S. Mohktar, F. Ibrahim, and N. A. Ismail .2013.NON-INVASIVE APPROACH TO PREDICT THE CHOLESTEROL LEVEL IN BLOOD USING BIOIMPEDANCE AND NEURAL NETWORK TECHNIQUES ., Biomed. Eng. Appl.Basis Commun. 25, 1350046 (2013) [7 pages] DOI: 10.4015/S1016237213500464
[ 11]Vlad Oncescu, Matthew Mancuso and David.2014. Cholesterol testing on a smartphone Erickson,Cite this: Lab Chip, 14, 759 DOI: 10.1039/c3lc51194d www.rsc.org/loc
[12] Khemphila, A.2010.Comparing performances of logistic regression, decision trees, and neural networks for classifying heart disease patients. Inst. of Technol. Dept. of Math. & Comput. Sci., King Mongkut''s Ladkrabang, Bangkok, Thailand ; Boonjing, V. Computer Information Systems and Industrial Management Applications (CISIM), International Conference 2010 Page(s):193 -198.Print ISBN:978-1-4244-7817-0
[13] Arpneek Kaur, Abhishek Bhardwaj ,Jalandhar,Punjab, India Arpneek Kaur et al.2014. Genetic Neuro Fuzzy System for Hypertension Diagnosis, / (IJCSIT) International Journal of Computer Science and Information Technologies, Vol. 5 (4), 2014, 4986-4989
[14] Juanmei Liu, Zi-Hui Tang, Fangfang Zeng, Zhongtao Li and Linuo Zhou,2013 Artificial neural network models for prediction of cardiovascular autonomic dysfunction in general Chinese population BMC Medical Informatics and Decision Making 2013, 13:80 doi:10.1186/1472-6947-13-808
The electronic version of this article is the complete one and can be found online at: http://www.biomedcentral.com/1472-6947/13/80
[15] Ashwell M, Gunn P, Gibson S.2011.Waist-to-height ratio is a better screening tool than waist circumference and BMI for adult cardiometabolic risk factors: systematic review and meta-analysis. Obes Rev. 2012 Mar;13(3):275-86. doi: 10.1111/j.1467-789X.2011.00952.x. Epub 2011 Nov 23. s.
[16] 許博智,2002.資料探勘在慢性病預測模式之建構
[17] 丁一賢,陳牧言,2005.資料探勘.滄海
[18] ROBERT B. KELLY, MD, MS, 2010.Diet and Exercise in the Management of Hyperlipidemia.Fairview Hospital/Cleveland Clinic Family Medicine Residency Program, Cleveland, Ohio. Am Fam Physician. 2010 May 1; 81(9):1097-1102.
[19]Craig WY, Palomaki GE,et al.1989. Cigarette smoking and serum lipid and lipoprotein concentrations: an analysis of published data. British Medical Jouranl. 1989 Mar 25;298(6676):784-8


QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top