非酒精性脂肪肝是越來越盛行的現代文明病，而且有年輕化的趨勢，如果未加以適當控制，將會進一步損害患者的健康。早期發現並且早期治療，可以大幅降低醫療成本。本研究使用成大醫院家庭醫學部所蒐集的資料，針對非酒精性脂肪肝提出一個預測模型。首先運用資料採礦的技術，探索出非酒精性脂肪肝與各種症狀的關聯性。在建立明確的規則後，再導入模糊理論的方法以及對於資料集的調整，對模型做進一步的改善。所提出的模型具有89.06%的特異性(specificity)，而對輕度與中度以上脂肪肝的敏感性(sensitivity)分別是70.07%和57.19%。

Nonalcoholic fatty liver disease (NAFLD) is a common lifestyle disease. NAFLD victims are getting younger and younger and NAFLD can endanger people's health if not controlled properly. Early detection and treatment of NAFLD patients can lower the medical cost significantly. This study uses the data from the Department of Family Medicine of National Cheng Kung University Hospital to propose a predictive model for NAFLD. This model depends on the data mining techniques which are used to discover the various symptom associations with NAFLD. After a crisp rule of NAFLD is created, the fuzzy theory and adjustment of dataset are introduced to improve the model. The specificity of the proposed model is 89.06% and the sensitivities of mild and moderate (and above) NAFLD are 70.07% and 57.19% respectively.

[1] Anna Alisi, Melania Manco, et al., “Pediatric Nonalcoholic Fatty Liver Disease in 2009”, The Journal of Pediatrics, vol. 155, no. 4, pp. 469-474, 2009.
[2] EM Brunt, CG Janney, AM Di Bisceglie, et al., “Nonalcoholic steatohepatitis: a proposal for grading and staging the histological lesions”, The American Journal of Gastroenterology, vol. 94, no. 9, pp. 2467-2474, 1999.
[3] 賴世偉、廖光福、黃金財，健檢民眾非酒精性脂肪肝盛行率之分析—以台中市一醫學中心為例，輔仁醫學期刊，vol. 3，no. 2，pp. 75-80，2005。
[4] BMI in Taiwan, http://health99.doh.gov.tw/OnlinkHealth/Onlink_BMI.aspx (last visited: Jun 27, 2011)
[5] Lancet, “Appropriate body-mass index for Asian populations and its implications for policy and intervention strategies”, WHO Expert Consultation, vol. 363, no. 9403, pp. 157-163, 2004.
[6] 譚健民、吳昭新，脂肪肝之超音波影像診斷，台灣醫學雜誌，vol. 85，no. 1，pp. 45-53，1986。
[7] Usama Fayyad, Gregory Piatetsky-Shapiro, and Padhraic Smyth, “From Data Mining to Knowledge Discovery in Databases”, AI Magazine, vol. 17, no. 3, page 39, 1996.
[8] K. Parsaye, “Surveying Decision Support: New Realms of Analysis”, Database Programming and Design, vol. 9, no. 4, pp. 27-33, 1996.
[9] Jiawei Han, and Micheline Kamber, Data Mining: Concepts and Techniques 2nd edition, Elsevier Inc., page 5, 2006.
[10] Usama Fayyad, Gregory Piatetsky-shapiro, and Padhraic Smyth, “The KDD Process for Extracting Useful Knowledge from Volumes of Data”, Communications of the ACM, vol. 39, no. 11, pp. 27-34, 1996.
[11] Ron Kohavi, “A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection”, Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence, vol. 2, no. 12, pp. 1137-1143, 1995.
[12] Geoffrey J. McLachlan, Kim-Anh Do, Christophe Ambroise, Analyzing Microarray Gene Expression Data, John Wiley & Sons, Inc., 2004.
[13] Hal Varian, “Bootstrap Tutorial”, The Mathematica Journal, vol. 9, no. 4, pp. 768-775, 2005.
[14] J. R. Quinlan, “Induction of Decision Trees”, Machine Learning, vol. 1, no. 1, pp. 81-106, 1986.
[15] C.-C. Chang and C.-J. Lin, “LIBSVM: A Library for Support Vector Machines”, ACM Transactions on Intelligent Systems and Technology, vol. 2, no. 3, pp. 1-27, 2011.
[16] Kevin N. Gurney, An Introduction to Neural Networks, UCL Press, 1997.
[17] J. R. Quinlan, C4.5: Programs for Machine Learning, Morgan Kaufmann Publishers, 1993.
[18] Haijian Shi, Best-first Decision Tree Learning, Masters Degree Theses, Department of Computer Science, The University of Waikato, New Zealand, pp. 20-21, 2007.
[19] L. A. Zadeh, “Fuzzy sets”, Information and Control, vol. 8, no. 3, pp. 338-353, 1965.
[20] Ronald R. Yager, and Dimitar P. Filev, Essentials of Fuzzy Modeling and Control 1st edition, John Wiley & Sons, Inc., 1994.
[21] Li-Xin Wang, "Fuzzy Systems Are Universal Approximators", First IEEE International Conference on Fuzzy Systems, pp. 1163-1170, 1992.
[22] Tomohiro Takagi, and Michio Sugeno, “Fuzzy Identification of Systems and Its Applications to Modeling and Control”, IEEE Transactions on Systems, Man, and Cybernetics, vol. 15, no. 1, pp. 116-132, 1985.
[23] Michio Sugeno, and G.T. Kang, “Structure Identification of Fuzzy Model”, Fuzzy Sets and Systems, vol. 28, no. 1, pp. 15-33, 1988.
[24] T. J. Ross, Fuzzy Logic with Engineering Applications, McGraw-Hill Inc., 1995.
[25] Mark Hall, Eibe Frank, Geoffrey Holmes, Bernhard Pfahringer, Peter Reutemann, and Ian H. Witten, “The WEKA Data Mining Software: An Update”, SIGKDD Explorations, vol. 11, no. 1, pp. 10-18, 2009.
[26] Metabolic syndrome standard in Taiwan(2007), http://www.bhp.doh.gov.tw/bhpnet/portal/Them_Show.aspx?Subject=200712250023&Class=2&No=200712250123 (last visited: Jun 27, 2011)
[27] Waist circumference standard in Taiwan(2005), http://www.bhp.doh.gov.tw/bhpnet/portal/Them_Show.aspx?Subject=200712250011&Class=2&No=200712250144(last visited: Jun 27, 2011)
[28] 柴國樑，脂肪肝預測模式之研究，義守大學管理科學研究所碩士論文，2000。
[29] 姚志成，運用資料探勘技術建構脂肪肝預測模式，中原大學資訊管理研究所碩士論文，2005。
[30] Tamaki Yamada, Mitsuru Fukatsu, et al., “Fatty Liver Predicts Impaired Fasting Glucose and Type 2 Diabetes Mellitus in Japanese Undergoing a Health Checkup”, Journal of Gastroenterology and Hepatology, vol. 25, no. 2, pp. 352–356, 2010.
[31] J.-S. R. Jang and C.-T. Sun, “Neuro-Fuzzy Modeling and Control”, Proceedings of the IEEE, vol. 83, no. 3, pp. 378–406, 1995.
[32] Cristina Olaru, and Louis Wehenkel, “A Complete Fuzzy Decision Tree Technique”, Fuzzy Sets and Systems, vol. 138, no. 2, pp. 221–254, 2003.