簡易檢索 / 詳目顯示

研究生: 舒天緯
Tian - Wei Shu
論文名稱: 癌症轉移之多狀態半馬可夫鏈模型-以台灣健保資料庫為例
Multi-State Semi-Markov Modeling for Cancer Metastasis:A Case Study of NHIRD in Taiwan
指導教授: 王孔政
Kung-Jeng Wang
口試委員: 鄧乃嘉
none
喻奉天
Vincent F. Yu
學位類別: 碩士
Master
系所名稱: 管理學院 - 工業管理系
Department of Industrial Management
論文出版年: 2014
畢業學年度: 102
語文別: 英文
論文頁數: 68
中文關鍵詞: 多狀態半馬可夫鏈半馬可夫過程台灣健保資料庫比例風險模型癌症轉移
外文關鍵詞: Multi-State Semi-Markov chain, Semi-Markov process Cancer metastasis, Cox proportional regression model
相關次數: 點閱:255下載:20
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

根據資料統計,癌症在台灣名列十大死因已數十年。近幾年之研究大多在探討有關癌症死亡率、存活率潛在因子之影響情形,然而癌症轉移方面的研究相對甚少。癌症轉移與否,常被視作癌症患者病程嚴重程度以及治療效果的指標。本研究將探討癌症轉移間轉移時間、病患特徵、慢性疾病、治療效果之潛在因子影響情形。
本研究使用台灣健保資料庫癌症檔進行資料之建構與蒐集,台灣健保資料庫涵蓋近二十年就診資料且包含百分之九十九健保制度國民。前段在台灣健保資料庫癌症檔獲取影響癌症轉移之潛在因子後,透過R軟體工具探討多狀態下半馬可夫過程在不同潛在因子影響下癌症轉移情形。
多狀態半馬可夫鏈模型探討在不同潛在因子下癌症轉移情形,其中針對癌症轉移時間隱含指數分配、韋伯分配、指數化韋伯分配。多狀態半馬可夫鏈無記憶性的基本假設:呈現轉移矩陣中本期只與前期有關;在轉移時間機率分配明確設定情況下,多狀態半馬可夫鏈中即符合基本假設且存在離散狀態(癌症)以及連續時間(癌症轉移時間)。本模型結合比例風險模型配適三種模型分別為:基礎模型、單一共變量模型、複合共變量並且分析半馬可夫過程危險函數變化情形以及癌症轉移間不同潛在因子下相對危險性;另一階段為了解癌症轉移之間時間比例,透過半馬可夫過程模型計算各狀態轉移間平均時間的變化。本研究結合半馬可夫過程以及比例風險模型,透過台灣健保資料庫找尋相關潛在因子探討癌症轉移間半馬可夫過程危險函數的變化。最終得到癌症轉移間轉移時間比例、不同潛在因子下半馬可夫鏈過程危險函數、相對危險性之比較。


According to statistics in Taiwan, cancer is the most serious and been in the reason of death many decades. In recent years, most of study discussed on different characteristic effect on cancer mortality or incidence, but seldom investigated on cancer metastasis. The severity of cancer patient and treatment effect treats as the indicator. Our research investigated impact of hidden factor on metastasis time (sojourn time), characteristic, chronic diseases, and treatment effect.
National Health Insurance Research Database which has been launched twenty years and resulting database covers 99% of 23 million populations. After pre-processing the National Health Insurance (NHI) Research Database to obtain the hidden factors, an R software package constructed Multi-State Semi-Markov (MSSM) model provided useful and relevant tool for observing the impact of cancer metastasis under different hidden factors.
Multi-State Semi-Markov (MSSM) model represented the impact on cancer metastasis under different hidden factors (covariates) and the metastasis time (sojourn time) involved exponential distribution, weibull distribution, and exponentiated weibull distribution. The MSSM model assumed that the process is independent from the time spent in the state (memoryless); in MSSM model can be considered with the discrete state (cancer state) and continuous time (sojourn time). The MSSM model incorporated the cox proportional regression model to fit three final model: based-model, single-covariate model, and multi-covariate model. Final model provided to calculate the relative risk (RR) of sojourn time but consider the hazard function of Semi-Markov process (SMP) under different hidden factors.
Our research incorporated the concept of Semi-Markov process and cox proportional regression model. Hidden factors (covariates) built from National Health Insurance research database like chronic diseases, individual characteristic, treatments. Eventually, this study will have the proportion of time from Semi-Markov process (SMP), state transfer relative risk (RR), and the hazards function of Semi-Markov process (SMP) with different covariates.

摘要 I ABSTRACT II TABLE OF CONTENTS IV LIST OF TABLES V LIST OF FIGURES VI Chapter 1 Introduction 1 1.1 Research background and motivation 1 1.2 Research purpose 2 1.3 Research structure 3 Chapter 2 Literature Review 4 2.1 Cancer and Cancer Metastasis 4 2.2 Cancer cohort study of NHI database in Taiwan 5 2.3 Multi-State Semi-Markov Model (MSSM model) 8 Chapter 3 Modeling 10 3.1 Data description 10 3.1.1 Criterion and definition 11 3.1.2 Pre-processing of NHI research database 14 3.2 Modeling Multi-State Semi-Markov Model 17 3.2.1 Survival function, Sojourn time distribution, Hazard function 17 3.2.2 Transition Semi-Markov process 19 3.2.3 Cox proportional regression model 20 3.3 Semi-Markov process 21 Chapter 4 Experimental Results 23 4.1 Modeling procedure 23 4.2 Model description 25 4.3 Application to cancer metastasis data 25 4.3.1 Experiment summary 28 4.3.2 Lung cancer brain metastasis (Transition 12) 35 4.3.3 Liver cancer lung metastasis (Transition 31) 41 Chapter 5 Markov process 46 5.1 The Makov process: The stationary probability for cancer metastasis 46 5.2 The semi-Makov process: The proportion of time for cancer metastasis 47 Chapter 6 Conclusion and Future Research 51 6.1 Conclusion 51 6.2 Future research 52 REFERENCE 53 APPENDIX 56 A. Parameter estimation: based-model 56 B. Parameter estimation: Multi-covariate model 56 C. Parameter estimation: single-covariate model 57 D. Hazard function of SMP 58

Adami, H.-O., Chow, W.-H., Nyren, O., Berne, C., Linet, M. S., Ekbom, A., . . . Fraumeni, J. F. (1996). Excess risk of primary liver cancer in patients with diabetes mellitus. Journal of the National Cancer Institute, 88(20), 1472-1477.
Alioum, A., Leroy, V., Commenges, D., Dabics, F., & Salmon, R. (1998). Effect of gender, age, transmission category, and antiretroviral therapy on the progression of human immunodeficiency virus infection using multistate Markov models. Epidemiology, 9(6), 605-612.
Bagdonavicius, V., & Nikulin, M. (2001). Accelerated life models: modeling and statistical analysis: CRC Press.
Brenner, D. R., Boffetta, P., Duell, E. J., Bickeboller, H., Rosenberger, A., McCormack, V., . . . Brueske-Hohlfeld, I. (2012). Previous lung diseases and lung cancer risk: a pooled analysis from the International Lung Cancer Consortium. American journal of epidemiology, 176(7), 573-585.
Brenner, D. R., McLaughlin, J. R., & Hung, R. J. (2011). Previous lung diseases and lung cancer risk: a systematic review and meta-analysis. PLoS One, 6(3), e17479.
Chap, Y.-m. Y., Lai, Y.-M., & Gau, B.-S. (1994). A comparative study of health care for children with cancer in 1981 and 1991 in Taiwan.
Chen, M.-C., Huang, W.-C., Chan, C. H., Chen, P.-T., & Lee, K.-D. (2010). Impact of second primary esophageal or lung cancer on survival of patients with head and neck cancer. Oral oncology, 46(4), 249-254.
Chuang, S. C., Scelo, G., Tonita, J. M., Tamaro, S., Jonasson, J. G., Kliewer, E. V., . . . Tracey, E. (2008). Risk of second primary cancer among patients with head and neck cancers: a pooled analysis of 13 cancer registries. International Journal of Cancer, 123(10), 2390-2396.
Clapp, R., Howe, G., & Lefevre, M. J. (2005). Environmental and occupational causes of cancer. Lowell Center for Sustainable Production.
Combescure, C., Chanez, P., Saint-Pierre, P., Daures, J., Proudhon, H., & Godard, P. (2003). Assessment of variations in control of asthma over time. European Respiratory Journal, 22(2), 298-304.
Cox, D. R. (1972). Regression models and life-tables. Journal of the Royal Statistical Society. Series B (Methodological), 187-220.
Department of Health, E. Y. (2010). Department of Health, Executive Yuan, R.O.C TAIWAN.
Foucher, Y., Mathieu, E., Saint‐Pierre, P., Durand, J. F., & Daures, J. P. (2005). A Semi‐Markov Model Based on Generalized Weibull Distribution with an Illustration for HIV Disease. Biometrical Journal, 47(6), 825-833.
Ghalanos, A., Theussl, S., & Ghalanos, M. A. (2011). Package ‘Rsolnp’.
Gilbert, P. (2011). numDeriv: Accurate Numerical Derivatives. R package Version 2010.11-1.
Hedeker, D., & Gibbons, R. D. (2006). Longitudinal data analysis (Vol. 451): John Wiley & Sons.
Hsiao, F., Yang, C., Huang, Y., & Huang, W. (2007). Using Taiwan's national health insurance research databases for pharmacoepidemiology research. Journal of Food and Drug analysis, 15(2), 99.
Hwang, C. Y., Chen, Y. J., Lin, M. W., Chen, T. J., Chu, S. Y., Chen, C. C., . . . Liu, H. N. (2012). Cancer risk in patients with allergic rhinitis, asthma and atopic dermatitis: a nationwide cohort study in Taiwan. International Journal of Cancer, 130(5), 1160-1167.
Jackson, C. H., Sharples, L. D., Thompson, S. G., Duffy, S. W., & Couto, E. (2003). Multistate Markov models for disease progression with classification error. Journal of the Royal Statistical Society: Series D (The Statistician), 52(2), 193-209.
Jemal, A., Bray, F., Center, M. M., Ferlay, J., Ward, E., & Forman, D. (2011). Global cancer statistics. CA: a cancer journal for clinicians, 61(2), 69-90.
Ko, Y.-C., Lee, C.-H., Chen, M.-J., Huang, C.-C., Chang, W.-Y., Lin, H.-J., . . . Chang, P.-Y. (1997). Risk factors for primary lung cancer among non-smoking women in Taiwan. International journal of epidemiology, 26(1), 24-31.
Kumar, V., Abbas, A. K., Fausto, N., & Aster, J. C. (2009). Robbins and Cotran Pathologic Basis of Disease, Professional Edition: Expert Consult-Online: Elsevier Health Sciences.
Lai, S.-W., Liao, K.-F., Chen, P.-C., Tsai, P.-Y., Hsieh, D. P. H., & Chen, C.-C. (2012). Antidiabetes drugs correlate with decreased risk of lung cancer: a population-based observation in Taiwan. Clinical lung cancer, 13(2), 143-148.
Lai, S.-W., Muo, C.-H., Liao, K.-F., Sung, F.-C., & Chen, P.-C. (2011). Risk of acute pancreatitis in type 2 diabetes and risk reduction on anti-diabetic drugs: a population-based cohort study in Taiwan. The American journal of gastroenterology, 106(9), 1697-1704.
Liang, J.-A., Sun, L.-M., Yeh, J.-J., Sung, F.-C., Chang, S.-N., & Kao, C.-H. (2011). The association between malignancy and end-stage renal disease in Taiwan. Japanese journal of clinical oncology, 41(6), 752-757.
Lin, H.-F., Li, Y.-H., Wang, C.-H., Chou, C.-L., Kuo, D.-J., & Fang, T.-C. (2012). Increased risk of cancer in chronic dialysis patients: a population-based cohort study in Taiwan. Nephrology Dialysis Transplantation, 27(4), 1585-1590.
Listwon, A., & Saint-Pierre, P. (2013). SemiMarkov: An R Package for Parametric Estimation in Multi-State Semi-Markov Models.
Listwon A, Saint-Pierre P (2013). SemiMarkov: Multi-States Semi-Markov Models. R package version 1.3.

Liu, W. S., Chang, Y. J., Lin, C. L., Liang, J. A., Sung, F. C., Hwang, I. M., & Kao, C. H. (2014). Secondary primary cancer in patients with head and neck carcinoma: the differences among hypopharyngeal, laryngeal, and other sites of head and neck cancer. European journal of cancer care, 23(1), 36-42.
Mauskopf, J. (2000). Meeting the NICE requirements: a Markov model approach. Value in Health, 3(4), 287-293.
McDonald, S., Haie, C., Rubin, P., Nelson, D., & Divers, L. D. (1989). Second malignant tumors in patients with laryngeal carcinoma: diagnosis, treatment, and prevention. International Journal of Radiation Oncology* Biology* Physics, 17(3), 457-465.
Monteiro, A., Smirnov, G. V., & Lucas, A. (2006). Nonparametric estimation for non-homogeneous semi-Markov processes: an application to credit risk: Tinbergen Institute Discussion Paper.
National Cancer Institute. (2008). Metastatic Cancer: Questions and Answers.
National Comprehensive Cancer Network. (2013). What is Metastasized Cancer?
Porta, M. (2008). A dictionary of epidemiology: Oxford University Press.
Ripley, B., Hornik, K., Gebhardt, A., & Firth, D. (2012). MASS: support functions and datasets for Venables and Ripley’s MASS. R package version, 7.3-17.
Ross, S. M. (2010). Introduction to Probability Models.
Saint‐Pierre, P., Combescure, C., Daures, J., & Godard, P. (2003). The analysis of asthma control under a Markov assumption with use of covariates. Statistics in Medicine, 22(24), 3755-3770.
Sankaranarayanan, R., Black, R., Swaminathan, R., & Parkin, D. (1998). An overview of cancer survival in developing countries. IARC scientific publications, 135-157.
Tammemagi, C. M., Neslund‐Dudas, C., Simoff, M., & Kvale, P. (2003). Impact of comorbidity on lung cancer survival. International Journal of Cancer, 103(6), 792-802.
Team, R. C. (2012). R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria, 2012.
Vaamonde, P., Martin, C., Del Rio, M., & Labella, T. (2003). Second primary malignancies in patients with cancer of the head and neck. Otolaryngology--Head and Neck Surgery, 129(1), 65-70.
Weng, P.-H., Hung, K.-Y., Huang, H.-L., Chen, J.-H., Sung, P.-K., & Huang, K.-C. (2011). Cancer-specific mortality in chronic kidney disease: longitudinal follow-up of a large cohort. Clinical Journal of the American Society of Nephrology, 6(5), 1121-1128.
Wu, C. Y., Hu, H. Y., Pu, C. Y., Huang, N., Shen, H. C., Li, C. P., & Chou, Y. J. (2011). Pulmonary tuberculosis increases the risk of lung cancer. Cancer, 117(3), 618-624.

QR CODE