臺灣博碩士論文加值系統

急性闌尾炎是外科手術中最常見的疾病，雖然急性闌尾炎的治療直接而容易，但是卻難以準確診斷急性闌尾炎的發生。目前並沒有任何的血液檢查或影像檢查可以準確地診斷出急性闌尾炎。對醫師而言，準確地檢測出該病症以減低病患因闌尾炎而導致闌尾穿孔，或降低因誤判而產生陰性闌尾切除率，藉以維護病患安全，仍是一種挑戰。
症狀的詢問、判斷與理學檢查對於急性闌尾炎的診斷非常重要；但因醫療人力的限制與成本的上揚、具有豐富診斷經驗的醫師並無法隨時為有需求的病患服務。為了解除此種限制而能達成低成本、高醫療品質的目標，醫療研究者嘗試發展各種高解析影像檢查工具及實驗室檢驗法，期能有效地提高闌尾炎的診斷準確性。然而，根據各種研究及臨床結果的顯示，已發展出影像檢查工具及實驗室檢驗法仍無法有效地提升闌尾炎診斷的準確率。
資訊科技的進步提供了一個可能解決問題的方法，本研究嘗試利用資料探勘的分類分析法，以醫師對病患徵候症狀判斷與血液檢查的結果為基礎，期能建構一個可協助醫師正確診斷闌尾炎的分類模式，以提升闌尾炎診斷的醫療品質。本研究的結果或許能引發其他醫療專家對於發展其他疾病的電腦輔助系統的興趣。

Acute appendicitis is the most common disease, which needs surgical intervention, in the world. Although the treatment of acute appendicitis is simple and straightforward, its diagnosis is still difficult. No single laboratory or image examination can make the diagnosis of acute appendicitis more accurate. Therefore, it is still a challenge to physicians to reduce appendiceal perforation and negative appendectomy rates.
Traditionally, history taking and physical examination are still very important in appendicitis diagnosis. Due to the raise of human resource cost, unavailability of experienced physicians and requirement of medical quality, the accuracy of appendicitis diagnosis should be improved with new low-cost methods. For this reason, many methods, including new high resolution image tools and laboratory examination, have been used to raise the diagnostic accuracy of acute appendicitis. However, the results are not satisfied.
The information technology may provide alternative approaches to acute appendicitis diagnosis. In this study, the classification approach and committee machine are applied to build a prognostic model to provide a economical diagnostic assistance for acute appendicitis. The results of this study should be helpful to the development of the computer-aided system in the other medical field.

1. 緒論 1
1.1 研究背景 1
1.2 研究動機與目的 2
1.3 研究流程 4
2. 文獻回顧 6
2.1 急性闌尾炎的診斷 6
2.2 急性闌尾炎的單一檢查測試 8
2.3 急性闌尾炎的診斷輔助計分系統 9
2.4 可協助闌尾炎診斷的變數 10
2.5 分類分析技術 11
2.5.1 決策樹歸納法 11
2.5.2 支援向量機（Support Vector Machine） 13
2.6 增強模式分類效能的委員會機制 15
2.6.1 Bagging委員會機制 15
2.6.2 AdaBoost委員會機制 16
3. 研究方法 19
3.1 研究材料 19
3.2 模式建構流程及評估方法 23
4. 實驗評估 25
4.1 變數及變數型態的選取 25
4.1.1 利用八項類別變數建構預測模式 25
4.1.2 利用五項類別變數及三項數值變數建構預測模式 26
4.1.3 利用新的三項變數及原有八個類別變數建構預測模式 26
4.1.4 利用六項類別變數及五項數值變數建構預測模式 27
4.2委員會機器的增強效果分析 28
4.3 預測模式與ALVARADO計分法的比較 29
4.4 實證評估總結 32
5.結論與建議 34
5.1 結論 34
5.2 研究限制及建議 35
參考文獻 36

[A86] Alvarado, A.(1986), A Practical Score for the early Diagnosis of Acute Appendicitis, Annals of Emergency Medicine, 15, pp.557-564.
[ABP06]Atzmueller, M. , Baumeister, J. and Puppe, F. (2006), Semi-automatic learning of simple diagnostic scores utilizing complexity measures, Artificial Intelligence in Medicine, 37, pp.19-30.
[ACC86]Adams, I.D., Chan, M., Clifford, P.C., Cooke, W.M., Dallos, V., De Dombal, F.T., Edwards, M.H., Hancock, D.M., Hewett, D.J., McIntyre, N., Somerville, P.G., Spiegelhalter, D.J., Wellwood, J. and Wilson, D.H.(1986), Computer aided diagnosis of acute abdominal pain: a multicentre study, British Medical Journal, 293, pp.800-805.
[AMM07]Abdeldaim, Y., Mahmood, S. and Mc Avinchey, D.(2007), The Alvarado score as a tool for diagnosis of acute appendicitis, Irish Medical Journal, 101(1), p. 342.
[B96]Breiman, L., (1996), Bagging Predictors, Machine Learning, 24(2), pp.123-140.
[B99]Bauer, E.(1999), An Empirical Comparison of Voting Classification Algorithms: Bagging, Boosting, and Variants, Machine Learning, 36, pp. 105-139.
[BBB03] Bijnen, C.L., van den Broek, W.T., Bijnen, A.B., de Ruiter, P. and Gouma, D.J.(2003), Implications of Removing a Normal Appendix, Digestive Surgery, 20, pp.215-221.
[BC00]Bennett, K.P., and Campbell, C., (2000), Support vector machines: Hype or hallelujah?, ACM SIGKDD Explorations Newsletter, pp.1-13.
[BW00]Birnbaum, B. A. and Wilson, S.R.(2000), Appendicitis at the Millennium, Radiology, 215, pp. 337-348.
[CLG02]Chan, K. L. , Lee, T. W. , Goldbaum, M. H. , Weinreb, R. N. , Sejnowski, A. T. J.（2002）, Comparison of machine learning and traditional classifiers in glaucoma diagnosis. IEEE Transactions on Biomedical Engineering, 49, pp.963-974.
[CS00]Cristianini N., and Shawe-Taylor J., (2000), An Introduction to Support Vector Machines and other Kernel-based Learning Methods, Cambridge University Press.
[D00]Dietterich, T.(2000), An Experimental Comparison of Three Methods for Constructing Ensembles of Decision Trees: Bagging, Boosting, and Randomization, Machine Learning, 40, pp. 139-157.
[DDR06] Ditillo, M.F., Dziura, J.D. and Rabinovici, R.(2006), Is It Safe to Delay Appendectomy in Adults With Acute Appendicitis?, Annals of Surgery, 244, pp.656-660.
[DVS00] Dibike, Y.B., Velickov, S. and Solomatine, D.(2000), Support Vector Machine: Review and Application in Civil Engineering, 2nd Joint Workshop on Application of AI in Civil Engineering, March 2000, Cottbus, Germany
[EIL92] Eskelinen, M, Ikonen, J. and Lipponen, P.(1992), A computer-based diagnostic score to aid in diagnosis of acute appendicitis, Theoretical Surgery, 7, pp.86-90.
[F05]Filewood, F.(2006), Improving diagnosis and treatment for appendicitis, Nursing times, 101, pp.41.
[F87] Fenyo, G.(1987), Routine use of a scoring system for decision-making in suspected acute appendicitis in adults, Acta Chirurgica Scandinavica, 153, pp. 545-551.
[FK02] Flum, D.R. and Koepsell, T.(2002), The clinical and economic correlates of misdiagnosed appendicitis:nationwide analysis, Archives of Surgery, 137, pp.799-804.
[FMM05] Flum, D.R., McClure, T.D., Morris, A. and Koepsell, T.(2005), Misdiagnosis of Appendicitis and the Use of Diagnostic Imaging, Journal of American College of Surgeons, 201, pp.933-939.
[FS97]Freund, Y. and Schapire, R.E., (1997), A decision-theoretic generalization of on-line learning and an application to boosting, Journal of Computer and System Sciences, 55, pp.119-139.
[GC96] Graffeo, C.S. and Counselman, F.L (1996), Appendicitis, Emergency Medicine Clinics of North America, 14, pp. 653-671.
[H99] Hardin, D.M.(1999), Acute Appendicitis: Review and Update, American Family Physician, 60, pp.2027-2034.
[HCH04]Huang, Z. , Chen, H. , Hsu, Chia-Jung. , Chen, Wun-Hwa. , Wu, S. (2004), Credit rating analysis with support vector machines and neural networks: a market comparative study. Decision Support Systems, 37, pp.543-558 .
[HSK05]Horzic, M., Salamon, A., Kopljar, M., Skupnjak, M., Cupurdija, K. and Vanjak, D.(2005), Analysis of scores in diagnosis of acute appendicitis in women, Collegium Antropologicum, 29(1), pp. 133-138.
[J01] Jones, P.F.(2001), Suspected acute appendicitis: trends in management over 30 years, British Journal of Surgery, 88, pp.1570-1577.
[KJK03]Kulkarni, A. , Jayaraman, V. K. , Kulkarni, B. D. (2003), Control of chaotic dynamical system using support vetor machines. Physics Letter A , 317, pp.429-435.
[L05] Liang, M.K(2005), The Art and Science of Diagnosing Acute Appendicitis, Southern Medical Journal, 98, pp.1159-1160.
[LM97] Liu, C.D. and McFadden D.W.(1997), Acute abdomen and appendix, Greenfield L.J, et al.,eds. Surgery: scientific principles and practice. 2nd ed. Philadelphia, Lippincott-Raven, pp.1246-1261.
[MCY05] Mathis, R.D., Chiumento, A.B., Yeh, B. and Dollieslager, N.(2005), An Outcome Study of the Use of Computed Tomography for the Diagnosis of Appendicitis in a Community-based Emergency Department, Southern Medical Journal, 98, pp.1169-1172.
[MEC06] Mun, S., Ernst, R.D., Chen, K., Oto, A., Shah, S. and Mileski, W. J.(2006) , Rapid CT diagnosis of acute appendicitis with IV contrast material , Emergency Radiology, 12, pp.99-102.
[N05 ]Naoum, J. J.(2005), Do all Patients with Suspected Appendicitis Benefit from CT imaging in Community-based Emergency Departments? , Southern Medical Journal, 98, pp.1157.
[OD05]Old, J. L., Dusing, R. W., Yap, W. and Dirks, J.(2005), Imaging for Suspected Appendicitis, American Family Physician, 71, pp. 71-78.
[OFY99] Ohmann, C., Franke, C., Yang, Q. and the German Study Group of Acute Abdominal pain(1999), Clinical Benefit of a Diagnostic Score for Appendicitis- Results of a Prospective Interventional Study, Archives of Surgery, 134, pp.993-996.
[OMY96]Ohmann, C., Moustakis, V., Yang, Q.and Lang, K.(1996), Evaluation of automatic knowledge acquisition techniques in the diagnosis of acute abdominal pain , Artificial Intelligence in Medicine, 8, pp.23-36.
[PEJ96]Pesonen, E., Eskelinen, M. and Juhola, M.(1996), Comparison of different neural network algorithms in the diagnosis of acute appendicitis , International Journal of Bio-Medical Computing, 40, pp. 227-233.
[PKN82]Pieper, R. , Kager, L. and Nasman P.(1982), Acute Appendicitis: A Clinical Study of 1018 Cases of Emergency Appendectomy , Acta Chirurgica Scandinavica, 148. pp. 51-62.
[POE98]Pesonen, E., Ohmann, C., Eskelinen, M. and Juhola, M.(1998), Diagnosis of acute appendicitis in two databases. Evaluation of different neighborhoods with LVQ neural network , Methods of Information in Medicine, 37, pp. 59-63.
[Q86]Quinlan, J.R.(1986), Induction of Decision Trees, Machine Learning, 1, pp. 81-106.
[Q93]Quinlan, J.R.(1993), C4.5: Programs for Machine Learning, Morgan Kaufmann, San Mateo, C.A., pp.1-16(1993), on http://books.google.com
[RRR99]Rao, P. M., Rhea, J. T., Rattner, D. W., Venus, L. G. and Novelline, R. A.(1999), Introduction of Appendiceal CT-Impact on Negative Appendectomy and Appendiceal Perforation Rates, Annals of Surgery, 229, pp.344-349.
[S87] Schwartz, S. I.(1987), Tempering the Technological Diagnosis of Appendicitis, the New England Journal of Medicine, 317, pp. 703-704.
[S90]Schapire, R. E. (1990), The strength of weak learnability. Machine Learning, 5, pp.197-227.
[S94] Schwartz, S.I.(1994), Appendix, Principles of surgery. 6th ed., McGraw Hill, New York, pp.1307-1318.
[S99]Simon, H., (1999), Neural Networks ： A Comprehensive Foundation, pp.351-355.
[SKB07]Schneider, C., Kharbanda, A. and Bachur, R.(2007), Evaluation Appendicitis Scoring Systems Using a Prospective Pediatric Cohort, Annals of Emergency Medicine, article in press.
[SMS03]Shelton, T., McKinlay, R. and Schwartz, R. W.(2003), Acute Appendicitis: Current Diagnosis and Treatment, Current Surgery, 60, pp.502-505.
[VHB06] Vadeboncoeur, T. F., Heister, R. R., Behling, C. A. and Guss, D. A.(2006), Impact of helical computed tomography on the rate of negative appendicitis, American Journal of Emergency Medicine, 24, pp.43-47.
[VMD82]Van Way III, C. W., Murphy, J. R., Dunn, E. L. and Elerding, S. C.(1982), A Feasibility Study of Computer Aided Diagnosis in Appendicitis, Surgery, Gynecology and Obstetrics, 155, pp. 685-688.
[WEKA]http://www.cs.waikato.ac.nz/~ml/weka/index.html
[WMC96] Wagner J.M., McKinney W.P., Carpenter J.L.(1996), Does this patient have appendicitis?, the Journal of American Medical Association, 276, pp.1589-1594.
[YC03]Yuan, F. and Cheu, R. L. (2003). Incident detection using support vector machines. Transportation Research Part C, 11, pp.309-328.
[YP97]Yang, Y. and Pedersen, J. O. (1997). A comparative study on feature selection in text categorization. Proceedings of ICML-97, 14th International Conference on Machine Learning, pp.412–420.
[丁陳05]丁一賢、陳牧言，資料探勘，頁4-5，滄海，2005。
[王景南03]王景南，「多類支向機之研究」，元智大學資訊管理研究所碩士論文，2003年。
[林諺熙05]林諺熙，「應用支撐向量機法於保險詐欺之預判」，國立成功大學工業與資訊管理學系碩士在職專班碩士論文，2005年。
[黃建銘05]黃建銘，「支援向量機的參數選擇」，國立台灣科技大學資訊工程所碩士論文，2005。
[曾蔡蘇05]曾憲雄、蔡秀滿、蘇東興、曾秋蓉及王慶堯，資料探勘，頁5-1~5-39，旗標，2005。
[曾李03]曾新穆及李建億 譯，資料探勘，頁366-71，東華，2003。
[戴王陳91]戴研光、王鐘貴、陳寶輝及陳定堯(1991)，「1211例闌尾切除術之病理分析」，中消醫誌，1991, 8(1), pp.13-17.