臺灣博碩士論文加值系統

肝臟移植病患手術後最容易發生身體的免疫系統對新移植的肝臟產生排斥反應，嚴重的排斥反應除了可能造成肝功能衰竭外，也會對病患的生命安全造成進一步的威脅。理想上，病患排斥反應的嚴重程度應藉由穿刺切片檢查來進行判斷，但因為肝臟移植病患手術後多有凝血功能障礙等相關問題，因此醫護人員轉而透過生化檢驗與血液檢驗來判斷病患排斥反應的嚴重程度，並依此來調整免疫抑制劑的使用量與用藥時間。
本研究期望能建構出一個可於臨床上進行應用的預測模型，因此模型除了必須能即時的提供預測結果外，也必須具有一定的預測準確度與可解釋性的優點。本研究將以資料驅動的角度出發，使用病患發生排斥反應前一天的抽血檢驗資料並透過機器學習演算法來進行建模。在建模的過程中，為了使模型能夠挖掘出發生排斥反應時各個檢測項目數值的變化趨勢，因此將檢驗資料進行變化幅度與類別化等處理；同時為了使模型具有可解釋的特點，因此透過整體式學習之方法來選取發生急性排斥反應時所產生的潛在規則，最終經由醫護人員的專業經驗從中挑選出較符合臨床上進行診斷的規則並將這些規則轉換成資料的新特徵，以建構出最終的預測模型。
本論文考慮了模型解釋力以及預測能力，研究結果顯示，本研究在準確率與其他先進機器學習演算法差異不大的狀況下，還可提供較佳的解釋，同時由於本研究建構出的模型可直接呈現進行預測時的預測規則，因此本研究成功的建構出具有即時性、可有效正確預測發生排斥反應的病患與擁有可解釋性的模型。

Patients who receive the surgery of liver transplant are most likely to have rejection of the new transplanted liver from the body immune system. A serious rejection may causes of not only liver failure, but also a further life threat for patient. Ideally, the severity of the patient's rejection should be judged by puncture biopsy, but the liver transplant patients have more clotting dysfunction after surgery. Therefore, the medical staffs in turn use the biochemical tests and blood tests to determine the severity of the patient's rejection, and adjust the use of immunosuppressive agents and medication time.
The goal of this thesis is to construct a predictive model that can be applied clinically. Therefore, the model must provide the instant prediction results, and advantages of predictive accuracy and interpretability. This study proposes to use data-driven method to construct the model, using the day before the rejection of the patient's blood test data and through the machine learning algorithm to construct the model. To construct a model which can dig out the changes in the value of each test item when the rejection occurs, we propose to apply both amplitude of variation and the categorization to the test data. Meanwhile, to construct an interpretable model, we propose to use ensemble learning technique to select the potential rules of the acute rejection. Finally, with the help of the professional experience of health care workers, we select rules more in line with the clinical diagnosis and use these rules to form a new feature of the data to construct the final prediction model.
The experimental results indicate that the proposed model could achieve almost identical accuracy as compared with state-of-the-art algorithms. Besides accuracy, the proposed model could offer the practitioners high interpretation. Meanwhile, the constructed model can directly show the forecasting rule once the forecasting is completed, indicating that we successfully construct a real-time, interpretable, and effective model in predicting the rejection of patients.

目錄
摘要 I
Abstract II
目錄 III
圖目錄 V
表目錄 VI
第一章、 緒論 1
1.1 研究背景 1
1.2 研究動機與目的 2
1.3 研究貢獻 3
第二章、 文獻回顧 4
2.1 醫療預警系統 4
2.1.1 病況預警系統 4
2.1.2 肝臟移植病患手術後急性排斥預警研究 5
2.2 資料探勘 6
2.2.1 資料探勘簡介 6
2.2.2 醫療領域的資料特性 9
2.2.3 資料探勘於醫療領域的應用 10
2.3 資料不均 11
2.3.1 資料不均簡介 11
2.3.2 評估指標 13
第三章、 研究方法 15
3.1 資料前處理 18
3.1.1 抽血檢驗研究資料 18
3.1.2 病患手術後急性排斥反應判定 21
3.2 處理細節 23
3.2.1 研究資料格式 23
3.2.2 計算檢驗項目變化幅度 24
3.2.3 數值類別化 24
3.2.4 成本敏感學習法與抽樣方法 26
3.2.5 合併連續時間且相同生理項目的規則 27
第四章、研究結果 29
4.1第一階段研究結果 29
4.2第二階段研究結果 40
4.3第三階段研究結果 47
第五章、結論 49
參考文獻 50

[1] http://www.mohw.gov.tw/CHT/DOS/DisplayStatisticFile.aspx?d=56041
[2] http://tcr.cph.ntu.edu.tw/uploadimages/Y98-ALL.pdf
[3]Chen, C. L., &Concejero, A. M. (2010). Liver transplantation for hepatocellular carcinoma in the world: the Taiwan experience. Journal of hepato-biliary-pancreatic sciences, 17(5), 555-558.
[4] Adams, D. H., Sanchez-Fueyo, A., & Samuel, D. (2015). From immunosuppression to tolerance. Journal of Hepatology, 62(1), S170-S185.
[5] Bathgate, A. J., Hynd, P., Sommerville, D., & Hayes, P. C. (1999). The prediction of acute cellular rejection in orthotopic liver transplantation. Liver Transplantation and Surgery, 5(6), 475-479.
[6] Hillman, K. M., Bristow, P. J., Chey, T., Daffurn, K., Jacques, T., Norman, S. L., ... & Simmons, G. (2002). Duration of life-threatening antecedents prior to intensive care admission. Intensive care medicine, 28(11), 1629-1634.
[7] Goldhill, D. R., Worthington, L., Mulcahy, A., Tarling, M., & Sumner, A. (1999). The patient-at-risk team: identifying and managing seriously ill ward patients. ANAESTHESIA-LONDON-, 54, 853-860.
[8] Goldhill, D. R., White, S. A., & Sumner, A. (1999). Physiological values and procedures in the 24 h before ICU admission from the ward. Anaesthesia, 54(6), 529-534.
[9] Dogan, S., &Turkoglu, I. (2008). Diagnosing hyperlipidemia using association rules. Mathematical and Computational Applications, 13(3), 193-202.
[10] McGloin, H., Adam, S. K., & Singer, M. (1998). Unexpected deaths and referrals to intensive care of patients on general wards. Are some cases potentially avoidable?. Journal of the Royal College of Physicians of London, 33(3), 255-259.
[11] Subbe, C. P., Kruger, M., Rutherford, P., &Gemmel, L. (2001). Validation of a modified Early Warning Score in medical admissions. QJM: An International Journal of Medicine, 94(10), 521-526.
[12] McArthur‐Rouse, F. (2001). Critical care outreach services and early warning scoring systems: a review of the literature. Journal of advanced nursing, 36(5), 696-704.
[13] McQuillan, P., Pilkington, S., Allan, A., Taylor, B., Short, A., Morgan, G., ... & Smith, G. (1998). Confidential inquiry into quality of care before admission to intensive care. Bmj, 316(7148), 1853-1858.
[14] 陳德煊（2015）。建構肝臟移植病患術後急性排斥反應預警模型(碩士論文)
[15] McArthur‐Rouse, F. (2001). Critical care outreach services and early warning scoring systems: a review of the literature. Journal of advanced nursing, 36(5), 696-704.
[16] Duncan, H., Hutchison, J., &Parshuram, C. S. (2006). The Pediatric Early Warning System score: a severity of illness score to predict urgent medical need in hospitalized children. Journal of critical care, 21(3), 271-278.
[17] Zhang, W., Ma, D., & Yao, W. (2014). Medical Diagnosis Data Mining Based on Improved Apriori Algorithm. Journal of Networks, 9(5), 1339-1345.
[18] Tarassenko, L., Hann, A., & Young, D. (2006). Integrated monitoring and analysis for early warning of patient deterioration. British journal of anaesthesia,97(1), 64-68.
[19] Quarterman, C. P. J., Thomas, A. N., McKenna, M., & McNamee, R. (2005). Use of a patient information system to audit the introduction of modified early warning scoring. Journal of evaluation in clinical practice, 11(2), 133-138.
[20] Wiesner, R. H., Demetris, A. J., Belle, S. H., Seaberg, E. C., Lake, J. R., Zetterman, R. K., ... & Detre, K. M. (1998). Acute hepatic allograft rejection: incidence, risk factors, and impact on outcome. Hepatology, 28(3), 638-645.
[21] Wang, Y. C., Wu, T. J., Wu, T. H., Lee, C. F., Chou, H. S., Chan, K. M., & Lee, W. C. (2012, March). The risk factors to predict acute rejection in liver transplantation. In Transplantation proceedings (Vol. 44, No. 2, pp. 526-528). Elsevier.
[22] Melvin, D. G., Niranjan, M., Prager, R. W., Trull, A. K., & Hughes, V. F. (1997, September). Neurocomputing applications in post-operative liver transplant monitoring. In Neural Networks for Signal Processing [1997] VII. Proceedings of the 1997 IEEE Workshop (pp. 216-225). IEEE.
[23] Melvin, D. G., Niranjan, M., Prager, R. W., Trull, A. K., & Hughes, V. F. (2000). Neuro-computing versus linear statistical techniques applied to liver transplant monitoring: a comparative study. IEEE transactions on biomedical engineering, 47(8), 1036-1043.
[24] Chiu, K. W., Chen, Y. S., de Villa, V. H., Wang, C. C., Eng, H. L., Wang, S. H., ... & Chen, C. L. (2005). Characterizes of Liver Enzymes on Living Related Liver Transplantation Patients with Acute Rejection. Hepato-gastroenterology,52, 1825-1827.
[25] Rodríguez‐Perálvarez, M., Germani, G., Tsochatzis, E., Rolando, N., Luong, T. V., Dhillon, A. P., ... & Burroughs, A. K. (2012). Predicting severity and clinical course of acute rejection after liver transplantation using blood eosinophil count. Transplant International, 25(5), 555-563.
[26] Berry, M. J., & Linoff, G. (1997). Data mining techniques: for marketing, sales, and customer support. John Wiley & Sons, Inc..
[27] Jiawei, H., & Kamber, M. (2001). Data mining: concepts and techniques. San Francisco, CA, itd: Morgan Kaufmann, 5.
[28] Fayyad, U., Piatetsky-Shapiro, G., & Smyth, P. (1996). From data mining to knowledge discovery in databases. AI magazine, 17(3), 37.
[29] Kotsiantis, S. B., Zaharakis, I., & Pintelas, P. (2007). Supervised machine learning: A review of classification techniques.
[30] Hastie, T., Tibshirani, R., & Friedman, J. (2009). Unsupervised learning. In The elements of statistical learning (pp. 485-585). Springer New York.
[31] Han, J., Pei, J., & Kamber, M. (2011). Data mining: concepts and techniques. Elsevier.
[32] Agrawal, R., Imieliński, T., & Swami, A. (1993, June). Mining association rules between sets of items in large databases. In Acm sigmod record (Vol. 22, No. 2, pp. 207-216). ACM.
[33] Safavian, S. R., & Landgrebe, D. A. (1990, May). Predictive Density Approach To Parametric Classification. In Geoscience and Remote Sensing Symposium, 1990. IGARSS'90.'Remote Sensing Science for the Nineties'., 10th Annual International (pp. 2367-2370). IEEE.
[34] Rokach, L., & Maimon, O. (2014). Data mining with decision trees: theory and applications. World scientific.
[35] JRQuinlan, C4.5: Programs for Machine Learning, MorgenKaufmann, San Francisco,
1993
[36] Breiman, L., Friedman, J., Stone, C. J., & Olshen, R. A. (1984). Classification and regression trees. CRC press.
[37] Cios, K. J., & William Moore, G. (2002). Uniqueness of medical data mining.Artificial intelligence in medicine, 26(1), 1-24.
[38] Alghamdi, A. S. A. (2011). Efficient Implementation of FP Growth Algorithm-Data Mining on Medical Data. International Journal of Computer Science and Network Security, 11(12), 7-16.
[39] Huang, M. J., Chen, M. Y., & Lee, S. C. (2007). Integrating data mining with case-based reasoning for chronic diseases prognosis and diagnosis. Expert systems with applications, 32(3), 856-867.
[40] Kaur, H., & Wasan, S. K. (2006). Empirical study on applications of data mining techniques in healthcare. Journal of Computer science, 2(2), 194-200.
[41] 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.
[42] Doddi, Achla Marathe, SS Ravi, David C. Torney, S. (2001). Discovery of association rules in medical data. Medical informatics and the Internet in medicine, 26(1), 25-33.
[43] Creighton, C., & Hanash, S. (2003). Mining gene expression databases for association rules. Bioinformatics, 19(1), 79-86.
[44] Li, J., Fu, A. W. C., He, H., Chen, J., Jin, H., McAullay, D., ... & Kelman, C. (2005, August). Mining risk patterns in medical data. In Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining (pp. 770-775). ACM.
[45] Nahar, J., Imam, T., Tickle, K. S., & Chen, Y. P. P. (2013). Association rule mining to detect factors which contribute to heart disease in males and females. Expert Systems with Applications, 40(4), 1086-1093.
[46] Tanner, L., Schreiber, M., Low, J. G., Ong, A., Tolfvenstam, T., Lai, Y. L., ...&Ooi, E. E. (2008). Decision tree algorithms predict the diagnosis and outcome of dengue fever in the early phase of illness. PLoS neglected tropical diseases,2(3), e196.
[47] Lewis, R. J. (2000, May). An introduction to classification and regression tree (CART) analysis. In Annual Meeting of the Society for Academic Emergency Medicine in San Francisco, California (pp. 1-14).
[48] Vlahou, A., Schorge, J. O., Gregory, B. W., & Coleman, R. L. (2003). Diagnosis of ovarian cancer using decision tree classification of mass spectral data. BioMed Research
[49] Badriyah, T., Briggs, J. S., Meredith, P., Jarvis, S. W., Schmidt, P. E., Featherstone, P. I., ... & Smith, G. B. (2014). Decision-tree early warning score (DTEWS) validates the design of the National Early Warning Score (NEWS).Resuscitation, 85(3), 418-423.
[50] Chawla, N. V., Japkowicz, N., & Kotcz, A. (2004). Editorial: special issue on learning from imbalanced data sets. ACM Sigkdd Explorations Newsletter, 6(1), 1-6.
[51] Fawcett, T. (2006). An introduction to ROC analysis. Pattern recognition letters, 27(8), 861-874.
[52] Elkan, C. (2001, August). The foundations of cost-sensitive learning. In International joint conference on artificial intelligence (Vol. 17, No. 1, pp. 973-978). Lawrence Erlbaum Associates Ltd.
[53] Kubat, M., & Matwin, S. (1997, July). Addressing the curse of imbalanced training sets: one-sided selection. In ICML (Vol. 97, pp. 179-186).
[54] Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: synthetic minority over-sampling technique. Journal of artificial intelligence research, 16, 321-357.
[55] Liu, X. Y., Wu, J., & Zhou, Z. H. (2009). Exploratory undersampling for class-imbalance learning. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 39(2), 539-550.
[56] Japkowicz, N. (2000, June). The class imbalance problem: Significance and
strategies. In Proc. of the Int’l Conf. on Artificial Intelligence.
[57] Candy, J. C., & Temes, G. C. (1991, May). Oversampling methods for data conversion. In Communications, Computers and Signal Processing, 1991., IEEE Pacific Rim Conference on (pp. 498-502). IEEE.
[58] Ferri, C., Flach, P., & Hernández-Orallo, J. (2002, July). Learning decision trees using the area under the ROC curve. In ICML (Vol. 2, pp. 139-146).