肺癌患者存活時間與醫療費用之高斯貝式網路預測模型

簡易檢索 / 詳目顯示

回結果列表

研究生：	陳婉平 Wan-Ping Chen
論文名稱：	肺癌患者存活時間與醫療費用之高斯貝式網路預測模型 A diagnosis model for survivability and medical expenditure of lung cancer patient by Conditional Gaussian Bayesian networks
指導教授：	王孔政 Kung-Jeng Wang
口試委員:	胡國琦 Gwo-Chi Hu 歐陽超 Chao Ou-Yang
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：	2018
畢業學年度：	106
語文別：	中文
論文頁數：	正文42頁
中文關鍵詞：	高斯貝式網路、肺癌、存活預測、醫療費用
外文關鍵詞：	Conditional Gaussian Bayesian network, lung cancer, survivability, medical expenditure
相關次數：	點閱：216 下載：1
分享至:	分享至facebook 分享至twitter

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

衛生福利部指出肺癌為現今台灣癌症十大死因之首，據2016年統計每年約有10,000個肺癌新案例，並導致成7,000人死亡，其醫療成本又因伴隨著共病症造成龐大負擔。本研究採用1996年至2010年國民健康保險研究數據庫中確診的肺癌患者，並從中挑選85,745例作為實驗數據，透過Kaplan-Meier估計患者的剩餘壽命，並利用風險因素建立存活時間和醫療費用的條件高斯貝式網絡模型。結果顯示，存活時間預測的R-square在時期I為69.50％、時期II為73.75％，而醫療費用預測的R-square在時期I為93.95％、時期II為74.77％。本模型不僅可以預測存活時間和醫療費用，還能計算其他醫學相關的後驗概率。

In Taiwan, the statistics of the Ministry of Health and Welfare indicated lung cancer is the leading cause of cancer. About 10,000 new cases of lung cancer each year, which caused more than 7,000 people dead in 2016. In addition, lung cancer usually accompanied with comorbidity which was negatively associated with survival and leaded to medical financial burden. This study used National Health Insurance Research Database from 1996 to 2010 who diagnosed lung cancer, and 85,745 cases were selected as experiment data. By using Kaplan-Meier estimation to get residual life of patient and used risk factors to construct Conditional Gaussian Bayesian network model of survivability and medical expenditure. The prediction R-square of survivability in stage I is 69.50%, stage II is 73.75%. The prediction R-square of medical expenditure in stage I is 93.95%, stage II is 74.77%. And proposed model not only can predict survivability and medical expenditure, but also can calculate the posterior probability of variety of medical related query.

Contents
摘要        I
Abstract        II
Contents        III
Contents of Figure    V
Content of Table    VI
Chapter 1    Introduction    1
1.1    Research background    1
1.2    Research motivation    2
1.3    Research objective    3
1.4    Thesis structure    4
Chapter 2    Literature review    5
2.1    Risk adjustment factors    5
2.2    Lung cancer risk factors    9
2.3    Conditional Gaussian Bayesian Network    10
2.4    Kaplan-Meier estimation    12
Chapter 3    Model Development    13
3.1    Variables    14
3.2    Building graphical models    18
3.3    Study population and data processing    22
3.4    Definitions of death confirm    23
3.5    Residual Lifetime Evaluation    24
3.6    Two distinct stages of lung cancer patients    27
3.7    Summary    28
Chapter 4    Experiment and results    29
4.1    Survivability Estimation    29
4.2    Medical Expenditure Estimation    32
4.3    Inference for survivability and medical expenditure    33
4.4    Query in CGBN    35
Chapter 5    Conclusion and future research    40
5.1    Discussion and conclusion    40
5.2    Limitation    41
5.3    Future research    42
References    43
Appendix A: Resulting conditional probability table of site in stage I    50
Appendix B: Resulting conditional probability table of site in stage II    54
Appendix C: The probability of backstopping    58
Appendix D: Normality test by Kolmogorov-Smirnov    61
 
Contents of Figure
Figure 1-1 Research process    4
Figure 3-1 CGBN estimation procedure    13
Figure 3-2 Constructed CGBN for survivability in different stages.    20
Figure 3-3 Constructed CGBN for medical expenditure in different stages.21
Figure 3-4 Data processing structure    23
Figure 3-5 Relative survival rate of lung cancer in each year    24
Figure 3-6 Different sex of residual life in period 2000-2003 year    25
Figure 3-7 Different sex of residual life in period 2004-2010 year    25
Figure 3-8 Different treatment of residual life in period 2000-2003    26
Figure 3-9 Different treatment of residual life in period 2004-2010    26
Figure 4-1 Survivability in different stages    30
Figure 4-2 Medical expenditure in different stages    33

Content of Table
Table 3-1 Considered chronic diseases    14
Table 3-2 Risk factor description    16
Table 3-3 Theoretical basis to build CGBN topology    18
Table 3-4 Medicine of lung cancer    27
Table 4-1 Two stages adjusted R-square of survivability in different methods.30
Table 4-2 Defined classification    31
Table 4-3 Two stages adjusted R-square of expenditure in different methods.33
Table 4-4 Query conditional probability in different stages.    39
Table C-1 The probability of chemotherapy    58
Table C-2 The probability of surgery    58
Table C-3 The conditional probability table of treatment    58
Table C-4 The conditional probability table of site    59
Table C-5 The conditional probability table of chronic diseases    59
Table C-6 The conditional probability of gender    60
Table D-1 Normality test in two stages    61


                                

References
Abdous, B., & Berred, A. (2005). Mean residual life estimation. Journal of Statistical Planning and Inference, 132(1–2), 3-19. doi:https://doi.org/10.1016/j.jspi.2004.06.01
Buczak, A. L., & Guven, E. (2016). A survey of data mining and machine learning methods for cyber security intrusion detection. IEEE Communications Surveys & Tutorials, 18(2), 1153-1176.
Chang, H. Y. (2009). Evaluation of alternative diagnosis-based risk adjustment models and morbidity trajectories for application in Taiwan. The Johns Hopkins University.
Chang, R.-E., & Lai, C.-L. (2004). Risk Adjuster: the Basis for Capitation Payment. Taiwan Journal of Public Health, 23(2), pp. 91-99.
Chen, W., Zheng, R., Baade, P. D., Zhang, S., Zeng, H., Bray, F., & He, J. (2016). Cancer statistics in China, 2015. CA: a cancer journal for clinicians, 66(2), 115-132.
Cheng, T. Y. D., Cramb, S. M., Baade, P. D., Youlden, D. R., Nwogu, C., & Reid, M. E. (2016). The international epidemiology of lung cancer: latest trends, disparities, and tumor characteristics. Journal of Thoracic Oncology, 11(10), 1653-1671.
Cheng, T.-M. (2015). Taiwan’s Health Care System: The Next 20 years. Taiwan-U.S. Quarterly Analysis(17). Retrieved from http://www.brookings.edu/research/opinions/2015/05/14-taiwan-national-healthcare-cheng
Cobb, B. R., Rumi, R., & Salmeron, A. (2007). Bayesian Network Models with Discrete and Continuous Variables. Advances in Probabilistic Graphical Models, Studies in Fuzziness and Soft Computing, 214, pp. 81-102.
Cruz-Ramírez, N., Acosta-Mesa, H. G., Carrillo-Calvet, H., Nava-Fernández, L. A., & Barrientos-Martínez, R. E. (2007). Diagnosis of breast cancer using Bayesian networks: A case study. Computers in Biology and Medicine, 37(11), 1553-1564.
Cuckow, P., & Brown, G. Using Machine Learning to Predict Personal Expenditure. (2014)
Dekker, A., Dehing-Oberije, C., De Ruysscher, D., Lambin, P., Komati, K., Fung, G., ... & Lievens, Y. (2009, December). Survival prediction in lung cancer treated with radiotherapy: Bayesian networks vs. support vector machines in handling missing data. In Machine Learning and Applications, 2009. ICMLA'09. International Conference on (pp. 494-497). IEEE.
Douillard, J. Y., Tribodet, H., Aubert, D., Shepherd, F. A., Rosell, R., Ding, K., & Stephens, R. (2010). Adjuvant cisplatin and vinorelbine for completely resected non-small cell lung cancer: subgroup analysis of the Lung Adjuvant Cisplatin Evaluation. Journal of thoracic oncology, 5(2), 220-228.
Ellis, K., Kerr, J., Godbole, S., Lanckriet, G., Wing, D., & Marshall, S. (2014). A random forest classifier for the prediction of energy expenditure and type of physical activity from wrist and hip accelerometers. Physiological measurement, 35(11), 2191.
Ferlay, J., Soerjomataram, I., Dikshit, R., Eser, S., Mathers, C., Rebelo, M., ... & Bray, F. (2015). Cancer incidence and mortality worldwide: sources, methods and major patterns in GLOBOCAN 2012. International journal of cancer, 136(5).
Fuch, V. R. (1968). The Growing Demand for Medical Care. The New England Journal of Medicine, 279, pp. 190-195.
Hämäläinen, W., & Vinni, M. (2006, June). Comparison of machine learning methods for intelligent tutoring systems. In International Conference on Intelligent Tutoring Systems (pp. 525-534). Springer, Berlin, Heidelberg.
Health Promotion Administration, Ministry of Health and Welfare. (2014). 2014 Health Promotion Administration Annual Report. Taipei: Health Promotion Administration, Ministry of Health and Welfare.
Howlader, N., Noone, A. M., Krapcho, M., Neyman, N., Aminou, R., & Waldron, W. (2014). SEER Cancer Statistics Review, 1975-2008 2011 Bethesda. MD National Cancer Institute.
Huang, H. L., Kung, P. T., Chiu, C. F., Wang, Y. H., & Tsai, W. C. (2014). Factors associated with lung cancer patients refusing treatment and their survival: a national cohort study under a universal health insurance in Taiwan. PloS one, 9(7), e101731.
Islam, K. M., Jiang, X., Anggondowati, T., Lin, G., & Ganti, A. K. (2015). Comorbidity and survival in lung cancer patients. Cancer Epidemiology and Prevention Biomarkers, 24(7), 1079-1085.
Jayasurya, K., Fung, G., Yu, S., Dehing‐Oberije, C., De Ruysscher, D., Hope, A., ... & Dekker, A. L. A. J. (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.
Jensen, F. V. (1996). An introduction to Bayesian networks (Vol. 210, pp. 1-178). London: UCL press.
Jiang Tianhua, Hu Ping, Zhang Qianshi, Xu Feng, Zhao Li, & Wang Xingcheng. (2017). Correlation between lung cancer risk and erythrocyte sedimentation rate and C-reactive protein. Hainan Medicine , 4 , 027.
Kao, J. H., Chen, H. I., Lai, F., Hsu, L. M., & Liaw, H. T. (2015). Decision Tree Approach to Predict Lung Cancer the Data Mining Technology. In Ubiquitous Computing Application and Wireless Sensor (pp. 273-282). Springer, Dordrecht.
Kapur, K., Young, A. S.,& Murata, D.(2000). Risk Adjustment for High Utilization of Public Mental Health Care. The Journal of Mental Health Policy and Economics, 3(3), pp. 129-137.
Lang, H.-C., & Wu, S.-L. (2012). Lifetime Costs of the Top Five Cancers in Taiwan. The European Journal of Health Economics, 13(3), pp. 347-353.
Lauritzen, S. L. (1992). Propagation of Probabilities, Means, and Variances in Mixed Graphical Association Models. Journal of the American Statistical Association, 87(420), pp. 1098-1108.
Lauritzen, S. L., & Jensen, F. (2001). Stable Local Computation with Conditional Gaussian Distributions. Statistics and Computing, 11, pp. 191
Lauritzen, S. L., & Wermuth, N. (1989). Graphical Models for Associations between Variables, some of which are Qualitative and some Quantitative. The Annals of Statistics, 17(1), pp. 31
Layton, T. J. (2017). Imperfect risk adjustment, risk preferences, and sorting in competitive health insurance markets. Journal of health economics, 56, 259-280.
Li Hui, Wang Hongxia, Meng Dongrui, Cui Xiaojun, & Liu Jinhua. (2017). Analysis of related factors and diagnostic markers for coal workers' pneumoconiosis complicated with lung cancer in Hebei Province. Chinese Journal of Preventive Medicine , 35 (A02), 5-7.
Lin, W., Chang, R. E., Hsieh, C. J., Yaung, C. L., & Chiang, T. L. (2003). Development of a risk-adjusted capitation model based on principal inpatient diagnoses in Taiwan. Journal of the Formosan Medical Association= Taiwan yi zhi, 102(9), 637-643.
López‐Campos, José Luis, Wan Tan, and Joan B. Soriano. "Global burden of COPD." Respirology 21, no. 1 (2016): 14-23.
Lucas, P. J., & Abu-Hanna, A. (2004). Bayesian networks in biomedicine and health-care.
Lucena-Moya, P., Brawata, R., Kath, J., Harrison, E., ElSawah, S., & Dyer, F. (2015). Discretization of continuous predictor variables in Bayesian networks: an ecological threshold approach. Environmental Modelling & Software, 66, 36-45.
Luo, H., Ge, H., Cui, Y., Zhang, J., Fan, R., Zheng, A., ... & Sun, Y. (2018). Systemic Inflammation Biomarkers Predict Survival in Patients of Early Stage Non-Small Cell Lung Cancer Treated With Stereotactic Ablative Radiotherapy-A Single Center Experience. Journal of Cancer, 9(1), 182.
Mitsudomi, T., Morita, S., Yatabe, Y., Negoro, S., Okamoto, I., Tsurutani, J., & Asami, K. (2010). Gefitinib versus cisplatin plus docetaxel in patients with non-small-cell lung cancer harbouring mutations of the epidermal growth factor receptor (WJTOG3405): an open label, randomised phase 3 trial. The lancet oncology, 11(2), 121-128.
Omachi, T. A., Gregorich, S. E., Eisner, M. D., Penaloza, R. A., Tolstykh, I. V., Yelin, E. H., ... & Blanc, P. D. (2013). Risk adjustment for health care financing in chronic disease: what are we missing by failing to account for disease severity?. Medical care, 51(8), 740.
Pope, G. C., Ellis, R. P., Ash, A. S., Liu, C. F., Ayanian, J. Z., Bates, D. W., ... & Ingber, M. J. (2000). Principal inpatient diagnostic cost group model for Medicare risk adjustment. Health
Samet, J. M., Tang, E. A., Boffetta, P., Hannan, L. M. , Marston, S. O., Thun, M. J., & Ruding, C. M. (2009). Lung cancer in never smokers: clinical epidemiology and environmental risk factors. Clinical Cancer Research, 15(18), pp. 5626-5645.
Sesen, M. B., Nicholson, A. E., Banares-Alcantara, R., Kadir, T., & Brady, M. (2013). Bayesian networks for clinical decision support in lung cancer care. PloS one, 8(12), e82349.
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.
Thun, M. J., Lally, C. A., Calle, E. E., Heath Jr, C. W., Flannery, J. T., & Flanders, W. D. (1997). Cigarette smoking and changes in the histopathology of lung cancer. Journal of the National Cancer Institute, 89(21), 1580-1586.
Uusitalo, L. (2007). Advantages and Challenges of Bayesian Networks in Environmental Modelling. Ecological Modeling, 203, pp. 312-318.
Van Veen, S. H. C. M., Van Kleef, R. C., Van de Ven, W. P. M. M., & Van Vliet, R. C. J. A. (2015). Improving the prediction model used in risk equalization: cost and diagnostic information from multiple prior years. The European Journal of Health Economics, 16(2), 201-218.
Wynand, P. M. M., De Ven, V., & Ellis, R. P. (2000). Risk adjustment in competitive health plan markets. In Handbook of health economics (Vol. 1, pp. 755-845). Elsevier.
Zang, E. A., & Wynder, E. L. (1996). Differences in lung cancer risk between men and women: examination of the evidence. JNCI: Journal of the National Cancer Institute, 88(3-4), 183-192.
Zhou, C., Wu, Y. L., Chen, G., Feng, J., Liu, X. Q., Wang, C., & Lu, S. (2011). Erlotinib versus chemotherapy as first-line treatment for patients with advanced EGFR mutation-positive non-small-cell lung cancer (OPTIMAL, CTONG-0802): a multicentre, open-label, randomised, phase 3 study. The lancet oncology, 12(8), 735-742.

簡易檢索 / 詳目顯示

相關論文