臺灣博碩士論文加值系統

子宮頸癌是全世界婦女最常罹患的癌症，雖然子宮頸癌的發生率與死亡率已明顯逐年下降，惟發生率仍高居女性癌症首位，且其死亡率仍居我國十大癌症之第八位。本研究運用決策樹C5.0演算法、決策樹CART演算法、支援向量機SMO演算法及邏輯斯迴歸等四種資料探勘工具，同時採用10折交叉驗證方式進行內、外部模型之驗證，建立子宮頸癌病患的存活情形模型，並挖掘出對存活情形之有效規則。
本研究利用全民健康保險研究資料庫中，以1999年至2002年申請子宮頸癌重大傷病作為本研究對象11,617人。不論就整體平均預測正確率及個別模型最高預測正確率而言，決策樹C5.0（80.83%）的預測能力皆優於邏輯斯迴歸（80.47%）、決策樹CART（80.29%）、支援向量機（79.93）等技術之預測能力。模型穩定度方面，則以支援向量機優於決策樹C5.0、邏輯斯迴歸、決策樹CART。
從資料探勘所得重要因素中，發現病患年齡、轉移至骨癌、肺癌、肝癌、抹片檢查、治療後產生尿毒症、腹膜炎及陰道直腸?等併發症等變數，都是影響子宮頸癌病患存活的重要預後因子。本研究所發現影響子宮頸癌病患之預後因子及其規則，提供此疾病於治療或預防上之參考依據。

Cervical cancer is the most common disease that strikes women in the world. Even though the morbidity and the mortality have been decreasing in recent years, the morbidity rates of cervical cancer are the first leading type and the mortality rates are the eighth of the top ten cancers in Taiwan. Data mining was used in this research including C5.0, CART, SVM and Logistic Regress algorithm to find the effective association rule and build up the model of survivability in cervical cancer. We also used 10-fold cross-validation methods to validate the training data and testing data.
This study used data from the National Health Insurance database. Data includes 11,617 persons who have applied catastrophic illness of cervical cancer from 1999 to 2002.The results will respectively be indicated the accuracy of testing data as follows. Decision tree (C5.0) is the best predictor with 80.83% accuracy; Logistic Regression is came out to be the second with 80.47% accuracy ; Decision tree CART came out to be the third with 80.29% accuracy ; Support vector machine came out to be the fourth with 79.93% accuracy.
In this study, we found there are many variables including age of patient, bone cancer, lung cancer, liver cancer, non-attendance Cervical Smear, peritonitis and uremia were important factors of the prognosis. We fond the rules and the factors of prognosis which would affect the survivability of the patients of survical cancer in this research. Therefore we can provide reference for patients on treatment or prevent.

書名頁 i
論文口試委員審定書 ii
授權書 iii
中文摘要 iv
英文摘要 v
誌謝 vi
目錄 vii
表目錄 viii
圖目錄 ix
第1章 緒論 1
1.1 研究背景 1
1.2 研究動機 3
1.3 研究目的 4
第2章 文獻探討 5
2.1 子宮頸癌 5
2.2 子宮頸癌的預後因子 8
2.3 資料探勘 13
2.4 存活分析 20
第3章 研究方法 22
3.1 實驗資料及對象 22
3.2 研究設計及流程 22
3.3 研究變項及定義 25
第4章 實驗結果 28
4.1 基本資料分析 28
4.2 預測模型評估 33
4.3 重要影響變數及規則說明 39
第5章 討論 50
第6章 結論與建議 53
6.1 結論 53
6.2 建議 54
6.3 研究限制 54
參考文獻 56
一、中文部分 56
二、英文部分 58
附錄 一 62
附錄 二 63

一、中文部分
[1] 王本仁，黃心苑，周穎政，「全民健保子宮頸抹片檢查受檢情形影響因子分析－個體時間依序列時間之實證研究，1997~2000」，台灣衛誌，第24卷第1期，2005年。
[2] 世界衛生組織，http://www.who.int。
[3] 朱堂元，「類乳突病毒與子宮頸癌的預防篩檢」人，台北市醫師公會會刊，第44卷第5期，49-53頁，2000年。
[4] 行政院衛生署，衛生統計資訊網 http://www.doh.gov.tw/statistic/index.htm。
[5] 行政院衛生署國民健康局，台灣癌症登記系統http://crs.cph.ntu.edu.tw/main.php?Page=A5。
[6] 林政道，吳宜鴻，中西醫會診－子宮頸癌，書泉出版社，2001年。
[7] 周振陽，陳建仁，游山林，婦女健康新展望─子宮頸癌預防政策白皮書，財團法人厚生基金會，2007年。
[8] 夏萍等，實用婦科護理，華杏出版股份有限公司，2008年。
[9] 許軒之，梁雲，方富民，孫立民，陳惠君，王重榮，「第三期後期子宮頸癌
[10] 國家衛生研究院，TCOG子宮頸癌臨床指引，2008。
[11] 國家衛生研究院，http://www.nhi.gov.tw/webdata/AttachFiles。
[12] 郭文建，陳麗州，莊淑慧，張光耀，「資料挖掘技術簡介與應用」，電信研究雙月刊，第32卷第6期，719-729頁，2003年。
[13] 張語恬，朱基銘，簡戊鑑，「比較三種資料探勘演算法預測子宮頸癌五年存活的外部通用行效能」，台灣家醫誌，第17卷第4期，2007年。
[14] 陳松吟，「全民健康保險子宮頸癌抹片篩檢使用型態六年之追蹤研究」，國立陽明大學，碩士論文，2003年。
[15] 陳尚文，林芳仁，梁基安，陽是能，劉瑞燦，涂振邦，蕭安成，吳學鼎，「子宮頸癌放射線治療的結果及直腸後遺症的分析（新光醫院的五年經驗）」，放射治療與腫瘤學，第5卷第1期，11-18頁，1998年。
[16] 黃承龍，「支援向量機應用於醫學健檢之肝病分類」，國立高雄第一科技大學，碩士論文，2006年。
[17] 葉光揚，「如何正確使用生物統計—Survival Analysis」，長庚內科通訊，8-9頁，1998年。
[18] 游進益，許振益，陳榮達，「多發性原發惡性腫瘤－病例報告」，耳鼻喉科醫學會雜誌，第30卷第4期，389-393頁，1995年。
[19] 廖繼鋐，「我國中老年醫療使用及對全民健保醫療費用影響之探討」，國立中正大學，碩士論文，1997年。
[20] 賴耿光，馬玉麟，許瑞昌，葉坤土，賴義雄，林隆堯，周明智，「子宮頸癌術後放射線治療病人組織病理學預後因子之多變數分析」，放射治療與腫瘤學，第9卷第1期，53-63頁，2002年。
[21] 賴瓊慧，「子宮頸癌的預後因素及化學治療在子宮頸癌治療的角色」，中華癌醫會誌，第 16卷第2期，9-15頁，2000年。

二、英文部分
[1] Abidi, A., Xing, G., Nasseri, K., Cress, R., Mourton, S., and Leiserowitz, G., “Age and Race Disparity in Incidence, Treatment and Survival of Cervical Cancer in California,” Gynecologic Oncology, Vol. 111, Issue. 2, pp. 384, 2008.
[2] Abraham, A., Chen, Y., and Yang, B., “Feature Selection and Classification Using Flexible Neural Tree,” Neurocomputing, Vol. 70, Issue. 1, pp. 305–313, 2006.
[3] Akay, M. F., “Support Vector Machines Combined with Feature Selection for Breast Cancer Diagnosis,” Expert Systems With Applications, Vol. 36, pp. 3240–3247, 2008.
[4] American Cancer Society, Cancer Source Book for Nurse, 8st ed, Jones and Bartlett Publishers Inc., 2004.
[5] Avci, E., and Avci D., “Using Combination of Support Vector Machines for Automatic Analog Modulation Recognition,” Expert Systems With Applications, Vol. 36, pp. 3956-3964, 2009.
[6] Agrawal, R., and Srikant, R., “Fast Algorithms for Mining Association Rules in Large Databases. In Proceedings of the Twentieth International Conference Very Large Databases,” VLDB’94, pp. 478–499, 1994.
[7] Ballegooijen, M. J., Marle, M. E., and Patnick, J., “Overview of Important Cervical Cancer Screening Process Values in European Union(EU) Countries and Tentative Predictions of the Corresponding Effectiveness and Cost-Effectiveness,” European Journal of Cancer, Vol. 36, pp. 2177-2188, 2000.
[8] Bellotti, T., and Crook, J., “Support Vector Machines for Credit Scoring and Discovery of Significant Features,” Expert Systems With Applications, Vol. 36, Issue. 2, Part 2, pp. 3302-3308, 2009.
[9] Bray, F., Guerra, Y. M., and Pardin, D. M., “The Comprehensive Cancer Monitoring Programme in Europe,” European Journal of Public Health, Vol. 13, pp. 61-66, 2003.
[10] Breiman, L., Friedman, J., Olshen, R., and Stone, C., “Classification and Regression Trees. (C&RT) Monterey,” CA: Wadsworth International Group, 1984.
[11] Chang, C. J., and Shyue, S. W., “A study on the Application of Data Mining to Disadvantaged Social Classes in Taiwan’s Population Census,” Expert Systems with Applications, Vol. 36, pp. 510-518, 2009.
[12] Chapman, G. W. J., “Survival of Advanced Age Females with Cervical Carcinoma,” Gynecol Oncol, Vol. 46, Issue. 3, pp. 287-291, 1992.
[13] Clegg, L. X., Li, F. P., Hankey, B. F., Chu, K., and Edwarda, B. K., “Cancer Survival among US Whites and Minorities:A SEER(Surveillance,Epidemiology,and End Results ) Program Population-Base Srudy,” Archives of Internal Medicine, Vol. 162, pp. 1985-1993, 2002.
[14] Chen, R. J., Chang, D. Y., Yen, M. L., Lee E. F., Huang, S. C., Chow, S. N., and Hsieh, C. Y., “Prognostic Factors of Primary Adenocarcinoma of the Uterine Cervix,” Gynecolgic Oncology , Vol. 69, pp. 157-164, 1998.
[15] Delen, D., Walker, G., and Kadam, A., “Predicting Breast Cancer Survivability: a Comparison of Three Data Mining Methods,” Artificial Intelligence in Medicine, Vol. 34, Issue. 2, pp. 113-127, 2005.
[16] Dhanalakshmi, P., Palanivel, S., and Ramalingam, V., “Classification of Audio Signals Using SVM and RBFNN,” Expert Systems with Applications. (Forthcoming)
[17] Fagundes, H., Perez, C. A., Grigsby, P. W., and Lockett, M. A., “Distant Metastasis after Irradiation Alone in Carcinoma of the Uterine Cervix,” Int J Radat Oncol Biol Phy, Vol. 24, Issue. 2, pp. 197-204, 1992..
[18] Gluckman, J. L., and Crissman, J. D., “Survival Rates in 548 Patients with Multiple Neoplasms of the Upper Aerodigestive Tract,” Laryngoscope, Vol. 93, pp. 71-74, 1983.
[19] Gao, F., Manatunga, A. K., and Chen, S., “Identification of Prognostic Factors with Multivariate Survival Data,” Computational Statistics and Data Analysis, Vol. 45, pp. 813-824, 2004.
[20] Gunn, S. R., “Support Vector Machines for Classification and Regression,” Technical Report University of Southampto, 1998.
[21] Herrero, R., Castle, P. E., and Schiffman, M.,”Epidemiologic Profile of Type-Specific Human Papillomavirus Inflection and Cervical Neoplasia in Guanacaste, Costa Rica,” J Inf. Dis, Vol. 191, pp. 1796-807, 2005.
[22] Hakama, M., Miller, A. B., and Day, N. E., “Screening for Cancer of the Uterine Cervix.International Agency for Research on Cancer,” Lyon IARC Sci.Publ,.Vol. 100, 1986.
[23] Henriksen, E., “The Lymphatic Spread of Carcinoma of the Cervix and the Body of the Uterus: A Study of 420 necropsies,” Am J Obstet Gynecol, Vol. 58, pp. 924-942, 1949.
[24] Howell, E. A., Chen, Y. T., and Concato, J., “Differences in Cervical Cancer Mortality among Black and White Women,” Obstet Gynecol, Vol. 94, pp. 509-515, 1999.
[25] Imaginis, Cervical Cancer-Introduction, Women''s Health - Cervical Cancer, http://www.imaginis.com/cervical-cancer, 2008.
[26] Keys, H. M., Bundy, B. N., and Stechman, F. B., “Cisplatin Radiationand Adjuvant Hysterectomy Compared with Eadiation and Adjuvant Hysterectomy for Bulky Stage Ib Cervical Carcinoma,” N Engly J Med, Vol. 340, pp. 1154-1161, 1999.
[27] Kim, H. S., Park, N. H., and Kang, S. B., “Rare Metastases of Recurrent Cervical Cancer to the Pericardium and Abdominal Muscle,” Arch Gynecol Obstet, Vol. 278, pp. 479-482, 2008.
[28] Li, Q., Meng, Q., Cai, J., Yoshino, H., “A Mochida Predicting Hourly Cooling Load in the Building: A Comparison of Support Vector Machine and Different,” Energy Conversion and Management Vol. 50, pp. 90-96, 2009.
[29] Lisboa, P. J. G., “ A Review of Evidence of Health Benefit from Artificial Neural Networks in Medical Intervention,” Neural Networks, Vol. 15, Issue. 1, pp. 11-19, 2002.
[30] Lai, C. H., Hsueh, S., Hung, M. Y., Chang, M. F., and Soong, Y. K., “The Uses and Limitations of DNA Flow Cytometry in Stage Ib or II Cervical Carcinoma,” Cancer, Vol. 72, pp. 3655-3662, 1993.
[31] Mathew, A., Pandey, M., and Murthy, N. S., “Survival Analysis: Caveats and Pitfall,” European Journal Surgical Oncology, Vol. 25, pp. 321-329, 1999.
[32] Merrill, R. M., Merrill, A. V., and Mayer, L. S., “Factors Associated with No Surgery Or radiation Therapy for Invasive Cervical Cancer in Black and White Women,” Ethn Dis, Vol. 10, pp. 248-256, 2000.
[33] Miller, A. B., Chamberlain, J., and Day, N. E., “Report on a Workshop of UICC Project on Evaluation of Screening for Cervical,” Int J Cancer, Vol. 46, pp. 761-769, 1990.
[34] Morris, M., Eifel, P. J., Lu, J., Grigsby, P. W., Levenback, C., Stevens, R. E., Rotman, M., Gershenson, D. M., and Mutch, D. G., “Pelvic radiation with concurrent chemotherapy compared with pelvic and para-aortic radiation for hight-risk cervical cancer,” N Engl J Med,Vol. 340, pp.1137-1143, 1999.
[35] Ohno, T., Kato, S., Sato, S., Fukuhisa, K., Nakano, T., Tsujii, H., and Arai, T., “Long-Term Survival and Risk of Second Cancers After Radiotherapy for Cervical Cancer,” International Journal of Radiation Oncology Biology Physics, Vol. 69 , Issue. 3, pp. 740-745, 2007.
[36] Parazzini, F., Hildesheim, A., Ferraroni, M. L., and Vecchia, C., “Brinton LA. Relative and Attributable risk for Cervical Cancer: a Comparative Study in the United States and Italy,” Int J Epidemiol, Vol. 19, pp. 539-545, 1990.
[37] Peng, Y., Yao, B., and Jiang, J., “Knowledge-Discovery Incorporated Evolutionary Search for Microcalcification Detection in Breast Cancer Diagnosis,” Artificial Intelligence in Medicine, Vol. 37, Issue. 1, pp. 43–53, 2006.
[38] Piatetsky-Shapiro, G., and Frawley, W.J., Knowledge Discovery in Databases, AAAI/MIT Press, pp. 229-238. 1991.
[39] Platt, J. C., Cristianini, N., and Shawe-Taylor, J., “Large Margin DAGs for Multiclass Classification,” Advances in Neural Information Processing Systems , Vol. 12, pp. 547-553, 2000.
[40] Quinlan, J. R., “Induction of Decision Tree,” Machine Learning, Vol. 1, pp. 81-106, 1986.
[41] Richard, J. R., and Michael, W. G., Data Mining a Tutorial-based Primer, 1st ed.,Addison Wesley,New York, pp. 4-27, 2002.
[42] Sainsbury, R., Rider, L., Smith, A., and MacAdam, A., “Does it Matter where You Live? Treatment Variation for Breast Cancer in Yorkshire,” Br J Cancer, Vol. 43, pp. 1275-1278, 1995.
[43] Silva, A., Cortez, P., Santos, M. F., Gomes, L., and Neves, J., “Mortality Assessment Inintensive Care Units Via Adverse Events Using Artificial Neural Networks,” Artificial Intelligence in Medicine, Vol. 36, pp. 223–234, 2006.
[44] Spensley, S., Hunter, R. D., Livsey, J. E., Swindell, R., and Davidson, S. E., “Clinical Outcome for Chemoradiotherapy in Carcinoma of the Cervix,” Clin Oncol. (Forthcoming)
[45] Souhami, L., Melo J. A. C., and Gonzalo Pareja, V., “The Treatment of Stage Ⅲ Carcinoma of the Uterine Cervix with Telecobalt Irradiation,” Gynecol Oncol, Vol. 28, pp. 262-267, 1987.
[46] Talb?ck, M., Stenbeck, M.,and Ros?n, M., “ Up-to-Date Long-Term Survival of Cancer Patients: An Evaluation of Period Analysis on Swedish Cancer Registry Data,” European Journal of Cancer, Vol. 40, Issue. 9. pp. 1361-1372, 2004.
[47] Vapnik, V., “The National of Statistical Learning Theory,” New York: Springer-Verlag, 1995.
[48] Wornjnowski, Z., Romejko, M., and Zielinski, J., “ Epidemiological Evaluation of the Efficiency of Treatment of Preinvasive Cervical Cancer in Warsaw, 1969-1988,” Eur J of Gynaecol Oncol, Vol. 14: Suppl, pp. 54-60, 1993.
[49] Yan, L., Verbel, D., and Saidi, O., “Predicting Prostate Cancer Recurrence Via Maximizing the Concordance Index,” Proceedings 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 479-485, 2004.