臺灣博碩士論文加值系統

子宮內膜癌發生率是近十年內成長速度最快的癌症，最常見的婦科癌症。診斷方法與技術的進步建立了一個有組織、有系統的方法來檢測早期癌症，促使癌症防治能獲得更大的進步。病患診斷及健康資料的儲存從傳統紙本病歷轉換成電子病歷，能在臨床應用、醫學教育、研究調查作為主要的醫療資訊來源。
目標：資料探勘技術已廣泛地應用於各項醫療研究上，可從資料中萃取關鍵資訊應用於醫療決策輔助。因此本研究目的為(一) 應用文字探勘技術，探勘出影響子宮內膜癌相關因素。(二)應用資料探勘技術建立子宮內膜癌的風險模型與風險指標之預測模式。
方法：本研究以2006-2015年嘉義市某大型區域級教學醫院撈取子宮內膜切片診斷紀錄計890名病例，其中ICD-9代碼【182】子宮內膜癌病例計148名，作為本次研究對象。以決策樹、支援向量機與邏輯斯迴歸三種分類技術建構出可用以預測子宮內膜癌之預測模式，並經由效能指標進行分類模式之效能評估，從中選取最佳效能之分類預測模型。
實驗結果：以支援向量機模式建構的預測模式，對於子宮內膜癌平均正確預測率為96.9%%，邏輯斯迴歸模式平均預測準確率為95.80%，而決策樹模式平均預測準確率平均為91.80%。並由決策樹整理出子宮內膜癌之風險樹分析。
結論：本研究利用醫療院所的文字紀錄，包括:病人主訴、體檢發現、超音波檢查、病理報告等，藉由文字探勘編輯、組織及分析的過程，進而利用資料探勘技術建立預測模型以供醫療臨床使用，可以彌補一般統計分析之不足之處，並且發現醫療記錄與罹患子宮內膜癌之間的關聯性，以協助臨床醫師在病患疾病評估時作為參考依據。

The incidence rate of endometrial cancer is the fastest growing cancer and most common gynecological cancer in the last decade. Diagnostic methods and technological improvement establish an organized and systematic approach , it could detect the early cancer and make greater progress in cancer prevention and control. Patient ' s diagnosis and health data storage transfer the traditional paper-based medical records into electronic medical records and serves as the main source of medical information in clinical applications, medical education and investigation .
Objectives: Data mining technology has been widely applied in various medical research and the key points from the data could be applied to medical decision making. Therefore, this study aims at (a) the use of Text mining technology to explore the impact of endometrial cancer-related factors. (b) To establish the forecasting endometrial cancer risk model and risk index by using Data mining technology.
Methods: In this study, 890 cases of endometrial biopsy were collected from a Regional Teaching Hospital in Chiayi City from 2006 to 2015. Among them,148 cases with ICD-9 code【182】of endometrial carcinoma were the case study. The forecasting model of endometrial cancer was constructed by Decision tree, Support vector machines and Logistic regression. The best performance classification model was evaluated by the performance index.
Results：The average accuracy prediction rates of endometrial cancer are as below: Support vector machines model is 96.9%, Logistic regression mode is 95.80% and Decision tree model is 91.80%, meanwhile, generalize the risk tree of endometrial cancer.
Conclusion: In this study, we used the records of medical institutions, including: patient’s complaints, physical examination findings, ultrasonography, pathological reports, etc,. By editing, organization and analysis process of Text mining, furthermore established the forecasting model for clinic medicine by the exploit of Data mining .It could make up for the inadequacies of the general statistical analysis and reveal the association between medical records and endometrial cancer, providing clinicians assistance in the assessment of patients as a reference.

目錄 I
表目錄 III
圖目錄 IV
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
1.4 研究流程 5
第2章 文獻探討 6
2.1 子宮內膜癌6
2.2 子宮內膜癌相關研究探討 13
2.3 資料探勘技術在癌症預測的應用 19
第3章 研究方法 21
3.1 資料收集 22
3.2 資料前處理22
3.3 研究變項定義 23
3.4 資料探勘技術 30
3.5 實驗設計與評估 35
第4章 實驗結果與分析 37
4.1 一般性統計分析 37
4.2 預測模式實驗結果 49
4.3 分析與評估 51
4.4 綜合討論 53
第5章 結論與建議 57
5.1 研究結論與貢獻 57
5.2 研究限制及建議 58
參考文獻 60
附錄1 65
附錄2 66

Anbarasi, M., Anupriya, E., & Iyengar, N. (2010). Enhanced prediction of heart disease with feature subset selection using genetic algorithm. International Journal of Engineering Science and Technology, 2(10), 5370-5376.
Antonsen, S. L., Ulrich, L., & Høgdall, C. (2012). Patients with atypical hyperplasia of the endometrium should be treated in oncological centers. Gynecol Oncol, 125(1), 124-128.
Ayer, T., Alagoz, O., Chhatwal, J., Shavlik, J. W., Kahn, C. E., & Burnside, E. S. (2010). Breast cancer risk estimation with artificial neural networks revisited. Cancer, 116(14), 3310-3321. doi:10.1002/cncr.25081
Barlin, J. N., Zhou, Q., Clair, C. M. S., Iasonos, A., Soslow, R. A., Alektiar, K. M., Abu-Rustum, N. R. (2013). Classification and regression tree (CART) analysis of endometrial carcinoma: seeing the forest for the trees. Gynecol Oncol, 130(3), 452-456.
Bellaachia, A., & Guven, E. (2006). Predicting breast cancer survivability using data mining techniques. Age, 58(13), 10-110.
Bellazzi, R., & Zupan, B. (2008). Predictive data mining in clinical medicine: current issues and guidelines. International Journal of Medical Informatics, 77(2), 81-97.
Beresford, S. A., Weiss, N. S., Voigt, L. F., & McKnight, B. (1997). Risk of endometrial cancer in relation to use of oestrogen combined with cyclic progestagen therapy in postmenopausal women. The Lancet, 349(9050), 458-461.
Bjørge, T., Stocks, T., Lukanova, A., Tretli, S., Selmer, R., Manjer, J., & Hallmans, G. (2010). Metabolic syndrome and endometrial carcinoma. American journal of epidemiology, kwq006.
Brinton, L. A., Berman, M. L., Mortel, R., Twiggs, L. B., Barrett, R. J., Wilbanks, G. D., Hoover, R. N. (1992). Reproductive, menstrual, and medical risk factors for endometrial cancer: results from a case-control study. American Journal of Obstetrics and Gynecology, 167(5), 1317-1325.
Burbos, N., Musonda, P., Crocker, S. G., Morris, E. P., Duncan, T. J., & Nieto, J. J. (2012). Outcome of investigations for postmenopausal vaginal bleeding in women under the age of 50 years. Gynecol Oncol, 125(1), 120-123. doi:http://dx.doi.org/10.1016/j.ygyno.2011.12.453
Cabena, P., Hadjinian, P., Stadler, R., Verhees, J., & Zanasi, A. (1998). Discovering data mining: from concept to implementation: Prentice-Hall, Inc.
Casey, P. M., Gallenberg, M. M., Kastner, T. M., Barrette, B. A., Chantigian, P. D. M., Shuster, L. T., Weaver, A. L. (2012). Outcomes in women age 40 years and older with cytologically benign endometrial cells. American Journal of Obstetrics and Gynecology, 207(5), 379.e371-379.e376. doi:http://dx.doi.org/10.1016/j.ajog.2012.08.018
Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine learning, 20(3), 273-297.
Costales, A. B., Schmeler, K. M., Broaddus, R., Soliman, P. T., Westin, S. N., Ramirez, P. T., & Frumovitz, M. (2014). Clinically significant endometrial cancer risk following a diagnosis of complex atypical hyperplasia. Gynecol Oncol, 135(3), 451-454. doi:http://dx.doi.org/10.1016/j.ygyno.2014.10.008
Cowles, T. A., Magrina, J. F., Masterson, B. J., & Capen, C. V. (1985). Comparison of Clinical and Surgical Staging in Patients With Endometrial Carcinoma. Obstetrics & Gynecology, 66(3), 413-416.
Creasman, W. T., Morrow, C. P., Bundy, B., Homesley, H. D., Graham, J., & Heller, P. (1987). Surgical pathologic spread patterns of endometrial cancer. A gynecologic oncology group study. Cancer, 60(8 Suppl), 2035-2041.
Delen, D., Walker, G., & Kadam, A. (2005). Predicting breast cancer survivability: a comparison of three data mining methods. Artificial Intelligence in Medicine, 34(2), 113-127.
Dick, R. S., Steen, E. B., & Detmer, D. E. (1997). The Computer-Based Patient Record:: An Essential Technology for Health Care: National Academies Press.
Dunn, G. P., Bruce, A. T., Ikeda, H., Old, L. J., & Schreiber, R. D. (2002). Cancer immunoediting: from immunosurveillance to tumor escape. Nature immunology, 3(11), 991-998.ISO 690
Fayyad, U. M., Piatetsky-Shapiro, G., Smyth, P., & Uthurusamy, R. (1996). Advances in knowledge discovery and data mining.
Frawley, W. J., Piatetsky-Shapiro, G., & Matheus, C. J. (1992). Knowledge discovery in databases: An overview. AI magazine, 13(3), 57.
Folsom, A. R., Kaye, S. A., Potter, J. D., & Prineas, R. J. (1989). Association of incident carcinoma of the endometrium with body weight and fat distribution in older women: early findings of the Iowa Women's Health Study. Cancer Research, 49(23), 6828-6831.
Furberg, A. S., & Thune, I. (2003). Metabolic abnormalities (hypertension, hyperglycemia and overweight), lifestyle (high energy intake and physical inactivity) and endometrial cancer risk in a Norwegian cohort. International journal of cancer, 104(6), 669-676.
GALLUP, D. G., & STOCK, R. J. (1984). Adenocarcinoma of the endometrium in women 40 years of age or younger. Obstetrics & Gynecology, 64(3), 417-420.
Gambrell, R. D. (1979). The role of hormones in the etiology of breast and endometrial cancer. Acta Obstetricia et Gynecologica Scandinavica, 58(sup88), 73-81.
Garuti, G., Cellani, F., Centinaio, G., Sita, G., Nalli, G., & Luerti, M. (2006). Histopathologic behavior of endometrial hyperplasia during tamoxifen therapy for breast cancer. Gynecol Oncol, 101(2), 269-273. doi:http://dx.doi.org/10.1016/j.ygyno.2005.10.010
Giordano, G., Gnetti, L., Merisio, C., & Melpignano, M. (2007). Postmenopausal status, hypertension and obesity as risk factors for malignant transformation in endometrial polyps. Maturitas, 56(2), 190-197. doi:http://dx.doi.org/10.1016/j.maturitas.2006.08.002
Grady, D., Gebretsadik, T., Kerlikowske, K., Ernster, V., & Petitti, D. (1995). Hormone replacement therapy and endometrial cancer risk: a meta-analysis. Obstetrics & Gynecology, 85(2), 304-313.
Grattarola, R. (1978). Anovulation and increased androgenic activity as breast cancer risk in women with fibrocystic disease of the breast. Cancer research, 38(9), 3051-3054.
Han, J., & Kamber, M. (2001). Data mining: concept and technology. Publishing House of Mechanism Industry, 70-72.
Hippisley-Cox, J., & Coupland, C. (2015). Development and validation of risk prediction algorithms to estimate future risk of common cancers in men and women: prospective cohort study. BMJ Open, 5(3). doi:10.1136/bmjopen-2015-007825
Hoskins, W. J. (2005). Principles and practice of gynecologic oncology: Lippincott Williams & Wilkins.
Jayasurya, K., Fung, G., Yu, S., Dehing-Oberije, C., De Ruysscher, D., Hope, A., Dekker, A. (2010). Comparison of Bayesian network and support vector machine models for two-year survival prediction in lung cancer patients treated with radiotherapy. Medical physics, 37(4), 1401-1407.
Kennedy, R. (1997). Y. Lee, B. Van Roy, C. Reed, and RP Lippman. Solving Data Mining Problems with Pattern Recognition.
Kirby, T. O., Leath, C. A., & Kilgore, L. C. (2006). Surgical staging in endometrial cancer. Oncology, 20(1), 45-50.
Kourou, K., Exarchos, T. P., Exarchos, K. P., Karamouzis, M. V., & Fotiadis, D. I. (2015). Machine learning applications in cancer prognosis and prediction. Computational and Structural Biotechnology Journal, 13, 8-17. doi:http://dx.doi.org/10.1016/j.csbj.2014.11.005
Leitao Jr, M. M., Han, G., Lee, L. X., Abu-Rustum, N. R., Brown, C. L., Chi, D. S., Soslow, R. A. (2010). Complex atypical hyperplasia of the uterus: characteristics and prediction of underlying carcinoma risk. American Journal of Obstetrics and Gynecology, 203(4), 349.e341-349.e346. doi:http://dx.doi.org/10.1016/j.ajog.2010.05.004
Listgarten, J., Damaraju, S., Poulin, B., Cook, L., Dufour, J., Driga, A., Zanke, B. (2004). Predictive Models for Breast Cancer Susceptibility from Multiple Single Nucleotide Polymorphisms. Clinical Cancer Research, 10(8), 2725-2737. doi:10.1158/1078-0432.ccr-1115-03
Luk, J. M., Lam, B. Y., Lee, N. P. Y., Ho, D. W., Sham, P. C., Chen, L., Fan, S.-T. (2007). Artificial neural networks and decision tree model analysis of liver cancer proteomes. Biochemical and Biophysical Research Communications, 361(1), 68-73. doi:http://dx.doi.org/10.1016/j.bbrc.2007.06.172
MacMahon, B. (1974). Risk factors for endometrial cancer. Gynecologic oncology, 2(2), 122-129.
Mantzoros, C., Petridou, E., Dessypris, N., Chavelas, C., Dalamaga, M., Alexe, D. M., & Trichopoulos, D. (2004). Adiponectin and breast cancer risk. The Journal of Clinical Endocrinology & Metabolism, 89(3), 1102-1107.
Mettlin, C., Jones, G., Averette, H., Gusberg, S., & Murphy, G. P. (1993). Defining and updating the american cancer society guidelines for the cancer‐related checkup: Prostate and endometrial cancers. CA: a cancer journal for clinicians, 43(1), 42-46.
Musonda, P., Burbos, N., Duncan, T. J., Crocker, S. G., Morris, E. P., & Nieto, J. J. (2011). Comparing the performance of two clinical models in estimating the risk of endometrial cancer in symptomatic postmenopausal women. European Journal of Obstetrics & Gynecology and Reproductive Biology, 159(2), 433-438. doi:http://dx.doi.org/10.1016/j.ejogrb.2011.09.005
Nagle, C. M., Marquart, L., Bain, C. J., O’Brien, S., Lahmann, P. H., Quinn, M., & Australian National Endometrial Cancer Study Group. (2013). Impact of weight change and weight cycling on risk of different subtypes of endometrial cancer. European Journal of Cancer, 49(12), 2717-2726.
Nicolaije, K. A., Ezendam, N. P., Vos, M. C., Boll, D., Pijnenborg, J. M., Kruitwagen, R. F., van de Poll-Franse, L. V. (2013). Follow-up practice in endometrial cancer and the association with patient and hospital characteristics: a study from the population-based PROFILES registry. Gynecol Oncol, 129(2), 324-331.
Orgéas, C. C., Hall, P., Wedrén, S., Dickman, P. W., & Czene, K. (2009). The influence of menopausal hormone therapy on tumour characteristics and survival in endometrial cancer patients. European Journal of Cancer, 45(17), 3064-3073. doi:http://dx.doi.org/10.1016/j.ejca.2009.05.012
Oztekin, A., Delen, D., & Kong, Z. J. (2009). Predicting the graft survival for heart–lung transplantation patients: An integrated data mining methodology. International Journal of Medical Informatics, 78(12), e84-e96.
Parazzini, F., La Vecchia, C., Negri, E., Bocciolone, L., Fedele, L., & Franceschi, S. (1991). Oral contraceptive use and the risk of ovarian cancer: an Italian case-control study. European Journal of Cancer and Clinical Oncology, 27(5), 594-598.
Patil, B. M., Joshi, R. C., Toshniwal, D., & Biradar, S. (2011). A new approach: role of data mining in prediction of survival of burn patients. Journal of medical systems, 35(6), 1531-1542.
Pettersson, F. (1994). FIGO Annual Report on the Results of Treatment in Gynecologic Cancer: Cancer of the Corpus Uteri 13,040 Patients Treated 1987-1989. Stockholm, Sweden, 22, 169-199.
Quinlan, J. R. (1992). Learning with continuous classes. Paper presented at the 5th Australian joint conference on artificial intelligence.
Reeves, K. W., Carter, G. C., Rodabough, R. J., Lane, D., McNeeley, S. G., Stefanick, M. L., & Paskett, E. D. (2011). Obesity in relation to endometrial cancer risk and disease characteristics in the Women's Health Initiative. Gynecol Oncol, 121(2), 376-382. doi:http://dx.doi.org/10.1016/j.ygyno.2011.01.027
Renehan, A. G., Tyson, M., Egger, M., Heller, R. F., & Zwahlen, M. (2008). Body-mass index and incidence of cancer: a systematic review and meta-analysis of prospective observational studies. The Lancet, 371(9612), 569-578.
Rowlands, I. J., Nagle, C. M., Spurdle, A. B., & Webb, P. M. (2011). Gynecological conditions and the risk of endometrial cancer. Gynecol Oncol, 123(3), 537-541. doi:http://dx.doi.org/10.1016/j.ygyno.2011.08.022
Siegel, R., Naishadham, D., & Jemal, A. (2012). Cancer statistics, 2012. CA: a cancer journal for clinicians, 62(1), 10-29.
Simoudis, E. (1996). Reality check for data mining. IEEE Intelligent Systems(5), 26-33.
Smith, J. A., & Todd, P. E. (2001). Reconciling conflicting evidence on the performance of propensity-score matching methods. American Economic Review, 112-118.
Soni, J., Ansari, U., Sharma, D., & Soni, S. (2011). Predictive data mining for medical diagnosis: An overview of heart disease prediction. International Journal of Computer Applications, 17(8), 43-48.
Soria, D., Garibaldi, J. M., Biganzoli, E., & Ellis, I. O. (2008). A comparison of three different methods for classification of breast cancer data. Paper presented at the Machine Learning and Applications, 2008. ICMLA'08. Seventh International Conference on.
Stambolic, V., Tsao, M. S., Macpherson, D., Suzuki, A., Chapman, W. B., & Mak, T. W. (2000). High incidence of breast and endometrial neoplasia resembling human Cowden syndrome in pten+/− mice. Cancer Research, 60(13), 3605-3611.
Stojadinovic, A. M. D., Nissan, A. M. D., Eberhardt, J. B. A., Chua, T. C. B. M., Pelz, J. O. W. M. D., & Esquivel, J. M. D. (2011). Development of a Bayesian Belief Network Model for Personalized Prognostic Risk Assessment in Colon Carcinomatosis. The American Surgeon, 77(2), 221-230. doi:10.1093/jncimonographs/lgj007
Sullivan, D. (2001). Document warehousing and text mining: techniques for improving business operations, marketing, and sales: John Wiley & Sons, Inc.
Trentham-Dietz, A., Nichols, H. B., Hampton, J. M., & Newcomb, P. A. (2006). Weight change and risk of endometrial cancer. International journal of epidemiology, 35(1), 151-158.
Vanneschi, L., Farinaccio, A., Mauri, G., Antoniotti, M., Provero, P., & Giacobini, M. (2011). A comparison of machine learning techniques for survival prediction in breast cancer. BioData mining, 4(1), 12.
Waddell, M., Page, D., & John Shaughnessy, J. (2005). Predicting cancer susceptibility from single-nucleotide polymorphism data: a case study in multiple myeloma. Paper presented at the Proceedings of the 5th international workshop on Bioinformatics, Chicago, Illinois.
Waddell, M., Page, D., & Shaughnessy Jr, J. (2005). Predicting cancer susceptibility from single-nucleotide polymorphism data: a case study in multiple myeloma. Paper presented at the Proceedings of the 5th international workshop on Bioinformatics.
Wartko, P., Sherman, M. E., Yang, H. P., Felix, A. S., Brinton, L. A., & Trabert, B. (2013). Recent changes in endometrial cancer trends among menopausal-age US women. Cancer Epidemiology, 37(4), 374-377. doi:http://dx.doi.org/10.1016/j.canep.2013.03.008
Webb, P. M. (2006). Commentary: weight gain, weight loss, and endometrial cancer. International journal of epidemiology, 35(1), 166-168.
Weiderpass, E., Persson, I., Adami, H. O., Magnusson, C., Lindgren, A., & Baron, J. A. (2000). Body size in different periods of life, diabetes mellitus, hypertension, and risk of postmenopausal endometrial cancer (Sweden). Cancer Causes & Control, 11(2), 185-192.
Yurkovetsky, Z., Ta'asan, S., Skates, S., Rand, A., Lomakin, A., Linkov, F., Lokshin, A. (2007). Development of multimarker panel for early detection of endometrial cancer. High diagnostic power of prolactin. Gynecol Oncol, 107(1), 58-65. doi:http://dx.doi.org/10.1016/j.ygyno.2007.05.041
Zhu, F., Patumcharoenpol, P., Zhang, C., Yang, Y., Chan, J., Meechai, A., Shen, B. (2013). Biomedical text mining and its applications in cancer research. Journal of Biomedical Informatics, 46(2), 200-211. doi:http://dx.doi.org/10.1016/j.jbi.2012.10.007
Ziel, H. K., & Finkle, W. D. (1975). Increased risk of endometrial carcinoma among users of conjugated estrogens. New England journal of medicine, 293(23), 1167-1170.