本研究主要是使用三維人體體型量測數據當預測變項，與資料探勘研究方法在糖尿病、高血壓與高血脂等慢性病預測模式之建構，在這研究領域是新嘗試。
根據行政院衛生署統計台灣人口十大死因顯示，國人罹患糖尿病、高血壓與高血脂而導致死亡位居台灣十大死因之中。而這三種疾病有些共同特徵都是隨著年齡而快速增加危險因子，與部分相同相關危險因子存在生活環境中。基本上，在國人罹患上述疾病是與許多預知危險因子中的生活型態關係密切。
研究目的是一個預測模式對臨床醫師們平常工作在危險因子無法正常的判斷預測時適時輔助預測危險因子。從預防醫學的觀點而言，一些危險因子的收集可從有效調查代替生化檢驗或是身體檢查。尤其，當預測人體健康狀況時，身體健檢、生活型態變項、家族疾病史等在疾病上扮演重要角色。至於臨床醫師們的觀點，一個有效的預測模式能夠大大的幫助完成診斷、治療與健康教育。在台灣如健康保險轉換成實體系統，對預防醫學角色是更為重要。
資料探勘是利用人工智慧、資料庫與統計等相關技術，從大量資料中挖掘不易發現且有用的資訊或知識，本研究方法使用基因演算法與案例庫推理的混合式資料探勘技術，將權重最佳化與容易探勘擷取出資料庫知識的最佳結合。
研究樣本從2000年七月至2001年七月共收集1370個住院健檢樣本，研究發現三種慢性病的三維預測模式中找到腰臀比是比身體質量指數顯著。在糖尿病方面找到顯著新變項是腰圍輪廓面積。在高血脂方面找到顯著新變項是腰圓周長。在高血壓方面，找到顯著新變項是腰圓周長、身體表面積、左手臂體積等，這都是研究新發現。

The objective of this paper is to construct a prediction model for chronic diseases such as Diabetes Mellitus, Hypertension, and Hyperlipidemia through the application of methods in Data Mining using three dimensional human body measurements as a new venture of this research filed.
According to records from Department Of Health, Diabetes Mellitus, Hypertension, and Hyperlipidemia were major manifestations among Taiwanese population leading to deaths of top ten causes in Taiwan. These three indications had some characteristics in common as increasing risk with increasing age and sharing the same pool of risk factors in our living environment. Basically, they are such diseases closely related with people’s life-styles as one can predict by some predisposing factors.
The ultimate goal of a prediction model is to foresee risk not normally judged by clinicians’ routine works. From the perspectives of preventive medicine, some risk factors were collected from active survey instead of biochemical tests or physical examinations. Especially, the body measurement, life-style variables, and family history of diseases play important roles in predicting a man’s health. As for clinicians’ points of view, a useful predicting model can greatly help on implementation of diagnosis, treatment, and health education. The role of preventive medicine became more important as health insurance system in Taiwan transforming into prospective payment systems.
The central role of data Mining uses artificial intelligence, database, and statistical methods to extract meaningful information from puzzles of variables and data. This particular study utilizes both genetic algorithm and case base reasoning in hybrid data mining technology. The research suggests this approach to be easy an effective technique to acquire of knowledge from database.
This study has collected 1370 subjects from department of health examination, Chang Gung Memorial Hospital from Jul. 2000 to Jul. 2001 years. Results from predicting selected chronic diseases by anthropometrical and three-dimension measurements are promising and innovative in field of biomedical sciences. Specifically, significant predictors for Hyperlipidemia, Diabetes Mellitus, and Hypertension are wait—hip ratio, waist-profile-area, waist-circum, trunk-surf-area, and left-arm-volume, respectively.

目 錄
書名頁………………………………………………………………… i
論文口試委員審定書………………………………………………… ii
授權書………………………………………………………………… iii
博碩士論文電子檔案上網授權書…………………………………… iv
授權書(博碩士論文)………………………………………………… v
中文提要……………………………………………………………… vi
英文提要……………………………………………………………… vii
誌謝…………………………………………………………………… ix
目錄…………………………………………………………………… x
表目錄………………………………………………………………… xii
圖目錄………………………………………………………………… xiii
一、 緒 論……………………………………………………… 1
二、 文 獻 回 顧………………………………………………… 3
2.1糖尿病相關研究……………………………………………… 3
2.2 高血壓相關研究……………………………………………… 5
2.3 高血脂相關研究……………………………………………… 8
2.4 人工智慧技術在醫學相關應用……………………………… 10
2.5 技術文獻回顧………………………………………………… 12
2.5.1案例庫推理………………………………………………… 12
2.5.2 K個最近相鄰法(k-NN)…………………………………… 14
2.5.3屬性權重………………………………………………… 16
2.5.4基因演算法………………………………………………… 17
2.5.5類神經網路………………………………………………… 19
三、 研究方法…………………………………………………… 21
3.1研究設計與流程……………………………………………… 21
3.2基因演算法-案例庫推理(GA-CBR)…………………………… 23
3.2.1 Y是連續性值……………………………………………… 24
3.2.2 Y是非連續性值…………………………………………… 25
3.3其它演算法比較……………………………………………… 27
3.3.1基因規劃分類樹(GPCT)…………………………………… 27
3.3.2基因規劃迴歸樹(GPMRT)…………………………………… 27
四、 實驗與結果………………………………………………… 29
4.1資料收集……………………………………………………… 29
4.2資料屬性……………………………………………………… 30
4.3資料前置處理………………………………………………… 30
4.4結果…………………………………………………………… 32
4.4.1糖尿病……………………………………………………… 32
4.4.2 高血脂……………………………………………………… 34
4.4.3 高血壓……………………………………………………… 36
五、 討論 ……………………………………………………………38
六、 結論………………………………………………………… 43
七、 未來研究方向……………………………………………… 44
參考文獻…………………………………………………………… 45

[1] 王悟師, 林信男：長期飲酒引起的肝硬化及柯沙科夫氏症候群案例, 當代醫學,18卷, 11期, 1991, pp.960-963.
[2] 行政院衛生署: 台灣地區主要死因. 台灣,行政院衛生署報告 2002. ( http://www.doh.gov.tw/lane/statist/89/Welcome.html )
[3] 行政院衛生署: 台灣地區歷年每十萬人口死亡率按主要死亡原因. 台灣, 行政院衛生署報告 2002. ( http://www.doh.gov.tw/lane/statist/89/Welcome.html )
[4] 行政院衛生署: 臺灣地區十大死因年齡結構別死亡概況. 台灣, 行政院衛生署報告 2002. ( http://www.doh.gov.tw/lane/statist/89/Welcome.html )
[5] 林信男：酒癮相關疾病, 當代醫學,18卷, 10期, 1991, pp.880-884.
[6] 林榮第, 吳慶南, 李鍾祥：吸菸與健康, 當代醫學, 19卷, 12期, 1992, pp.950-957.
[7] 梁錦華, 劉正典, 陳寶輝, 王朝欣, 王鐘貴, 黃明哲, 蕭泉豹, 阮仲垠, 陳定堯:台灣地區脂肪肝之臨床意義及診斷. 台灣醫誌, 1986;85;161-8
[8] 廖運範, 陳東榮：脂肪肝, 當代醫學, 19卷, 7期, 1992, pp.568-572.
[9] 潘文涵, 黃伯超： 國民營養健康狀況變遷調查, 1993-1996.
[10] Abdolmaleki, P., Buadu, L. D. and Naderimansh, H., “Feature Extraction and Classification of Breast Cancer on Dynamic Magnetic Resonance Imaging Using Artificial Neural Network,” Cancer Letters, Vol. 171, Issue: 2, pp.183-191, October 2001.
[11] Aha, D. W., “A Study of Instance-based Learning Algorithms for Supervised Learning Tasks: Mathematical, Empirical, and Psychological Evaluations,” TR 90-42, Irvine, CA: University of California, Department of Information and Computer Science, 1990.
[12] Antonino, S., Maurizio, P., Lino, M., Monica, T. and Doniela, M., “Body Mass Index and Liver Enzyme Activity in Serum,” Clin Chem, Vol. 37, pp.720-3, 1991.
[13] Armengol, E., Palaudaries, A. and Plaza, E., “Individual Prognosis of Diabetes Long-term Risks: A CBR Approach,“ Method Inform Med, Vol.40, pp.46-51, 2001.
[14] Artur, C. and Zdzislawa, S., “Diabetes Mellitus and Cancer,” European Journal of Internal Medicine, Vol.11, pp.245-252, 2000.
[15] Assmann, G. and Schulte, H., “Relation of High-Density Lipoprotein Cholesterol and Triglycerides to Incidence of Atherosclerotic Coronary Artery Disease,” American Journal of Cardiology, Vol.70, No.7, pp.733-7, Sep 1992.
[16] Barriga, K. J., Hamman, R. F., Hoag, S., Marshall, J. A. and Shetterly, S. M., “Population Screening for Glucose Intolerant Subjects Using Decision Tree Analyses,” Diabetes Research and Clinical Practice, Vol.34, pp.S17-S29, Suppl 1996.
[17] Bauer, J. R., Kenneth, W. and Alsing, S. G, “Kelly A Feature Screening Using Signal-to-Noise Ratios,” Neurocomputing, Vol. 31, Issue: 1-4, pp. 29-44, March 2000.
[18] Beevers, D. G., “Alcohol and Hypertension,” Lancet, Vol.41, pp.114, 1977.
[19] Blaz, Z., Janez, D. W., Kattan, J. and Robert, B. I., “Machine Learning for Survival Analysis: A Case Study on Recurrence of Prostate Cancer,” Artificial Intelligence in Medicine, Vol. 20, pp.59-75, 2000.
[20] Bray, G. A., “Obesity : Definition, Diagnosis and Disadvantages,” The Med. J. Australia, Vol.142, pp.S2-S8, 1985.
[21] Cappccio, F. P., Strazgullo, P. and Farinaro, E., “Uric Acid Metabolism and Tubular Sodium Handling,” JAMA, Vol.270, pp.354-359, 1993.
[22] Carlos, A., Pena, R. and Moshe, S., “Evolutionary Computation in Medicine: An Overview,” Artificial Intelligence in Medicine, Vol.19, pp.1-23, 2000.
[23] Chaturvedi, N., Stevens, L. and Fuller, J. H., “Which Features of Smoking Determine Mortslity Risk in Former Cigarette Smokers with Diabetes?,” Diabetes Care, Vol.20, pp.1266-1272, 1997.
[24] Cost, S. and Salzberg, S., “A Weighted Nearest Neighbor Algorithm for Learning with Symbolic Features,” Machine Learning, Vol.10, pp. 57-78, 1993.
[25] Creutzfeldt, W., “Liver Disease and Disbetes Mellitus In: Popper H, Schaffner F. Progress in liver Disease,” New York, Grune & Stratton, Vol.3, pp371, 1970.
[26] Davis, L., Handbook of Genetic Algorithms, Thomson Computer Press, 1991.
[27] Dazzi, D., Taddei, F., Gavarini, A., Uggeri, E. and Negro, R., “The Control of Blood Glucose in the Critical Diabetic Patient: a Neuro-Fuzzy Method,” Journal of Diabetes and Its Complications, Vol.15, pp.80-87, 2001.
[28] Denke, M. A., “Lipids, Estrogen Status, and Coronary Heart Disease Risk in Women,” Medicine & Science in Sports & Exercise, Vol.28, No.1, pp.13-4, Jan 1996.
[29] Despres, J. P., Prud’homme, D., Pouliot, M., Tremblay, A. and Bouchard, C., “Estimation of Deep Abdominal Adipose-Tissue Accumulation from Simple Anthropometric Measurements in Men,” The American Journal of Clinical Nutrition, Vol.54, pp.471-477, 1991.
[30] Deurenberg, P., Weststrate, J. A. and Seidell, J. C., “Body Mass Index as a Measure of Body Fatness:Age-and Sex Specific Prediction Formulas,” Br. j. Nutr, Vol.65, pp.105-114, 1991.
[31] Dhar, V. and Stein, R., Intelligent Decision Support Methods, Prentice Hall, 1997.
[32] Elliott, P., Stamler, J. and Nichols, R., ” Further Analyses of 24 Hours Sodium Excretion and Blood Pressure within and Across Populations,” BMJ, Vol.312, pp.1249-53, 1996 .
[33] Faster, D. W., Diabetes Mellitus. In Isselbacher K. J. :Harrison’s Principles of Internal Medicine. 10thed. New York, McGraw-Hill book Company, 1983.
[34] Ferrannini, E., “Physiological and Metabolic Consequences of Obesity,” Metabolism, Vol.44, No.9, (suppl 3), pp.15-17, 1995.
[35] Feskens, E. J. and Kromhout, D., “Cardiovascular Risk Factors and the 25 Year Incidence of Diabetes Mellitus in Middle-Aged Men: The Zutphen Study,” Am J Epidemiol, Vol.130, pp.1101-1108, 1989.
[36] Folsom, A. R., ”Body Fat Distribution and 5─Year Risk of Death in Older Women,” JAMA, Vol.269, pp.483, 1993.
[37] Gillum, R. F., “The Association of Body Fat Distribution with Hypertension, Hypertensive Heart Disease, Coronary Heart Disease, Diabetes and Cardiovascular Risk Factors in Men and Women Aged 18-79 Years,” J. Chronic Dis, Vol.40, pp.421-428, 1987.
[38] Gordon, T., Castekki, W. P., Hjortland, M. C., Kannel, W. B. and Dawber, T. R., “Predicting Coronary Heat Disease in Middle-Aged and Older Persons─The Famingham Study,” JAMA, Vol.238, pp.497-499, 1977.
[39] Grundy, S. M., “holesterol and Coronary Heart Disease,” Scandinavian Journal of Clinical & Laboratory Investigation - Supplement. Vol.199, pp.17-24, 1990.
[40] Guidelines Subcommittee. 1999 World Health Organization-International Society of Hypertension Guidelines for the Management of Hypertension. J Hyertension, Vol.17, pp.151-83, 1999.
[41] Haydon, G. H., Jalan, R., Ala-Korpela, M., Hiltunen, Y., Hanley, J., Jarvis, L. M., Ludlum, C. A. and Hayes, P. C., “Prediction of Cirrhosis in Patients with Chronic Hepatitis C Infection by Artificial Neural Network Analysis of Virus and Clinical Factors,” Journal of Viral Hepatitis, Vol.5, No.4, pp.255-64, Jul 1998.
[42] Helman, D. E., Analogical Reasoning, Dordrecht: Kluwer Academic Publishers, 1988.
[43] Holland, J. H., ”Adaptation in Natural and Artificial System , MIT Press, Cambridge,“ MA:1992.
[44] Jacek, J., Eugene, J. H. and Peter, P.V., “Case-Based Reasoning for Interpretation of Data from Non-Destructive Testing,“ Enfineering Application of Artificial Intelligence, Vol.14, pp.401-417, 2001.
[45] Jiang, H., Paul, K. and Whelton, P. K., “Epidemiology and Prevent of Hypertension,” Medical Clinics of North America, Vol.81, pp.1077-97, 1997.
[46] John, H., Dennis, R. and Flaura, K., “The Learning Classifier System: an Evolutionary Computation Approach to Knowledge Discovery in Epidemiologic Surveillance,” Intelligence in Medicine, Vol.19, pp.53-74, 2000.
[47] Kawakami, N., Takatsuka, N. and Shimizu, H., “Effects of Smoking on the Incidence of Non-Insulin-Dependent Dieabetes Mllitus,” Am J Epidemiol, Vol.145, pp.103-109, 1997.
[48] Kolonder, J. L., Simpson, R. and Sycara-Cyransky, K., ”A Process Model of Case-Based Reasoning in Problem Solving,” Proceedings of IJCAI-85, Losangels, CA, pp.284-290, 1985.
[49] Kononenko, I., “Machine Learning for Medical Diagnosis: History, State of the Art and Perspective,” Artificial Intelligence in Medicine, Vol. 23, Issue: 1, pp. 89-109, August 2001.
[50] Koza, J. R., “Survey of Genetic Algorithms and Genetic Programming,” WESCON. Conference record. Microelectronics Communications Technology Producing Quality Products Mobile and Portable Power Emerging Technologies, pp.589, 1995.
[51] Kvist, H., Chowdhury, B., Grangard, U., Tylen, U. and Sjorstorm, L., “Total and Visceral Adipose-Tissue Volumes Derived from Measurements with Computed Tomography in Adult Men and Women: Predictive Equation,” The American Journal of Clinical Nutrition, Vol.48, pp.1351-1361, 1988.
[52] Lemieux, S., Prud’homme, D., Bouchard, C., Tremblay, A. & Despres, J. P., ”A Single Threshold Value of Waist Girth Identifies Normal-Weight and Overweight Subjects with Excess Visceral Adipose Tissue,” The American Journal of Clinical Nutrition, Vol.64, pp.685-693, 1996.
[53] Li, D. X., “Case Based Reasoning for AIDS Initial Assessment,” Knowledge Based Systems, Vol.8, No.1, 1995.
[54] Lin, K. W., "Applying Genetic Programming of Classification Tree with Multiple Variable," Master Thesis, Institute of Information, Yuan Ze University, 2002.
[55] Lin, S. M., "The Automatic Construction of Multivariate Split Point Regression: A Genetic Programming Approach," Master Thesis, Institute of Information, Yuan Ze University, 2002.
[56] Liszka-Hackzell, J. J., “Prediction of Blood Glucose Levels in Diabetic Patients Using a Hybrid AI Technique,” Computers and Biomedical Research, Vol.32, No. 2, pp.132-144, April 1999.
[57] MacMahon, S.W. and Norton, R.N., “Alcohol and Hypertension :Complication for Prevention and Treatment,” Ann Int Med, pp.105-124, 1986 .
[58] Mead, W. C. and Brown, S. K., “Adaptive Optimization and Control Using Neural Networks,” Nuclear Instruments and Methods in Physics Research A, Vol.352, pp.309-315, 1994.
[59] Modan, M. and Halkin, H., “Hyperinsulinemia or Increased Sympathetic Drive as Links for Obesity and Hypertension,” Diabetes Care Vol.14, pp.470-487, 1991.
[60] Mykkanen, L., Kuusisto, J. and Pyorala, K., “Increases Risk of Non-Insulin-Dependent Diabetes Mellitus in Elderly Hypertersion Subjects,” J of Hypertension, Vol.12, pp.1425-32, 1994.
[61] Nakano, H., Okamoto, Y., Nakabayashi, H., Takamatsu, S. and Tsujii, H., “Application of Neural Network to the Interpretation of Laboratory Data for the Diagnosis of Two Forms of Chronic Active Hepatitis,” International Hepatology Communications, Vol. 5, Issue: 3, pp. 160-165, July 1996.
[62] Ohlson, L. O., Larsson, B. and Bjorntorp, P., “Risk Factors for Type 2 (Non-Insulin- Dependent) Diabetes Mellitus,” Diabetologia, Vol.31, pp.798-805, 1988.
[63] Orhish, D., “Can Life-Style Changes Reverse Coronary Atherosclerosis?,” Hosp Pract, pp.123-132, 1991.
[64] Pogue, V. A., Ellis, C., Michel, j. and Francis, C. K., “New Staging System of the Fifth Joint National Committee Report on the Detection Evaluation, and Treatment of High Blood Pressure(JNC-V) Alters Assessment of the Severity and Treatment of Hypertension,” Hypertension, Vol.28, pp.713-8, 1996.
[65] Pouliot, M., Despres, J. P., Lemieux, S., Moorjani, S., Bouchard, C. & Tremblay, A., ”Waist Circumference and Abdominal Sagittal Diameter: Best Simple Anthropometric Indexes of Abdominal Visceral Adiposetissue Accumulation and Related Cardiovascular Risk in Men and Women,” The American Journal of Cardiology, Vol.73, pp.460-468, 1994.
[66] Punch, W. F. and Goodman, E. D., “Further Research on Feature Selection and Classification Using Genetic Algorithms,” Appeared in ICGA, pp.557-564, 1993.
[67] Ramoni, M., Riva, A., Stefanelli, M. and Patel, V., “An Ignorant Belief Network to Forecast Glucose Concentration from Clinical Databases,” Artificial Intelligence in Medicine, Vol. 7, Issue: 6, pp.541-559, December 1995.
[68] Riesbeck , C. K. and Schank, R., “Inside Case-Based Reasoning,” Lawrence Erlbaum Associates, Hillsdale, New Jersey, 1989.
[69] Rimm, E. B., Manson, J. E. and Stampfer, M. J., “Prospective Study of Cigaratte Smoking, Alcohol Use, and the Risk of Diabetes in Men,” Bollettino Di Microbiologia e Indagini Di Laboratorio, Vol.310, pp.555-559, 1995.
[70] Rimm, E. B., Manson, J. E. and Stampfer, M. J., “Cigaratte Smoking and the Risk of Diabetes in Women,” Am J Public Health, Vol.83, pp.211-214, 1993.
[71] Savage, M. B., Kun, S., Harjunmaa, H. and Peura, R. A., “Development of a Non-Invasive Blood Glucose Monitor: Application of Artificial, Neural Networks for Signal Processing Bioengineering Conference, 2000,” Proceedings of the IEEE 26th Annual Northeast, pp.29 —30, 2000.
[72] Science News, “Smoking Boosts Death Risk for Diabetics,” Science News, Vol.138, No.4, pp.61, 1990.
[73] Seidell, J. C., Cigolini, M. and Charzewska, J., “Androgenicity in Relation to Body Fat Distribution & Metabolism in 38-Year-Old Women-the European Fat Distribution Study,” J. Clin. Epi, Vol.43, pp.21-34, 1990.
[74] Shin, K. S. and Han, I., “Case-Based Reasoning Supported by Genetic Algorithms for Corporate Bond Rating,” Expert Systems with Applications, Vol. 16, pp. 85-95, 1999.
[75] Steven, k., Dennis, W. and Matthew, K., “Artificial Neural Networks for Early Detection and Diagnosis of Cancer,” Cancer Letters, Vol.77, pp.79-83, 1994.
[76] Tafeit, E., Moller, R. and Sudi, K., “The Determination of Three Subcutaneous Adipose Tissue Compartments in Non-Insulin-Dependent Diabetes Mellitus Women with Artificial Neural Networks and Factor Analysis,” Artificial Intelligence in Medicine, Vol. 17, Issue: 2, pp.181-193, October 1999.
[77] Van Itallie, T. b., “Health Implication of Overweight and Obesity in the United States,” Annals Intern Med, Vol.103, pp.983-988, 1985.
[78] Watson, I., “Case Based Reasoning is a Methodology not a Technology,” Knowledge Based Systems, Vol.12, pp.303-308, 1999.
[79] Whelton, P. K., “Epidemiology of Hypertension,” Lancet, Vol.344, pp.101-106, 1994 .
[80] Williams, R. R., Hunt, S. C. and Hasstedt, S. J., “Definition of Genetic Factors in Hypertension: a Search for Major Genes, Polygenes, and Homogeneous Sub-Types,” J cardiovascular pharmacology, Vol.12(Suppl. 3), pp. s7-s20, 1988.
[81] Yoichi, H., Rudy, S. and Katsumi, Y., “A Comparison Between two Neural Network Rule Extraction Techniques for the Diagnosis of Hepatobiliary Disorders,” Artificial Intelligence in Medicine, Vol.20, pp.205-216, 2000.
[82] Yu, M. W., Chang, H. C., Liaw, Y. F. and Lin, S. M., “Familial Risk of Hepatocellular Carcinoma Among Chronic Hepatitis B Carriers and Their Relatives,” Journal of the National Cancer Institute, Vol.92, No. 14, July 2000.
[83] Zurol, F., Ferraro, R. T., Fontvielle, A. M., Rising, R., Bogardus, C. and Ravussin, E., “Spontaneous Physical Activity and Obesity :Cross-Sectional and Longitudinal Studies in Pima Indians,” Am. J. physiol, Vol.263, pp.E296-300, 1992.