Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/98265
標題: 利用集成學習分析牙周病屬性與預測類風濕性關節炎療效之相關性研究
A study on the correlation between features of periodontitis and predicting the efficacy of rheumatoid arthritis by using ensemble learning
作者: 黃嘉嘉
Chia-Chia Huang
關鍵字: 機器學習
類風溼性關節炎
牙周病
集成學習
隨機森林
袋裝方法
自適應增強方法
梯度提升決策樹
Machine learning
Rheumatoid arthritis
Periodontitis
Ensemble methods
Random forest
Bagging
Adaboost
Gradient boosting
引用: [1] R. C. Page, S. Offenbacher, H. E. Schroeder, G. J. Seymour, and K. S. Kornman, 'Advances in the pathogenesis of periodontitis: summary of developments, clinical implications and future directions,' Periodontology 2000, vol. 14, pp. 216-248, 1997. [2] F. DeStefano, R. F. Anda, H. S. Kahn, D. F. Williamson, and C. M. Russell, 'Dental disease and risk of coronary heart disease and mortality,' Bmj, vol. 306, pp. 688-691, 1993. [3] J. Beck, R. Garcia, G. Heiss, P. S. Vokonas, and S. Offenbacher, 'Periodontal disease and cardiovascular disease,' Journal of periodontology, vol. 67, pp. 1123-1137, 1996. [4] V. Haraszthy, J. Zambon, M. Trevisan, M. Zeid, and R. Genco, 'Identification of periodontal pathogens in atheromatous plaques,' Journal of periodontology, vol. 71, pp. 1554-1560, 2000. [5] B. Yalda, S. Offenbacher, and J. G. Collins, 'Diabetes as a modifier of periodontal disease expression,' Periodontology 2000, vol. 6, pp. 37-49, 1994. [6] C. O. Bingham III and M. Moni, 'Periodontal disease and rheumatoid arthritis: the evidence accumulates for complex pathobiologic interactions,' Current opinion in rheumatology, vol. 25, p. 345, 2013. [7] F. Mercado, R. I. Marshall, A. C. Klestov, and P. M. Bartold, 'Is there a relationship between rheumatoid arthritis and periodontal disease?,' Journal of clinical periodontology, vol. 27, pp. 267-272, 2000. [8] D. Aletaha, T. Neogi, A. J. Silman, J. Funovits, D. T. Felson, and C. O. Bingham III, '2010 rheumatoid arthritis classification criteria: an American College of Rheumatology/European League Against Rheumatism collaborative initiative,' Arthritis & Rheumatism, vol. 62, pp. 2569-2581, 2010. [9] B. Garcia-Zapirain, Y. Garcia-Chimeno, and H. Rogers, 'Machine Learning Techniques for Automatic Classification of Patients with Fibromyalgia and Arthritis,' International Journal of Computer Trends and Technology, vol. 25, 2015. [10] I. Kavakiotis, O. Tsave, A. Salifoglou, N. Maglaveras, I. Vlahavas, and I. Chouvarda, 'Machine learning and data mining methods in diabetes research,' Computational and structural biotechnology journal, vol. 15, pp. 104-116, 2017. [11] T. Araújo, G. Aresta, E. Castro, J. Rouco, P. Aguiar, and C. Eloy, 'Classification of breast cancer histology images using convolutional neural networks,' PloS one, vol. 12, p. e0177544, 2017. [12] C. Lin, E. W. Karlson, H. Canhao, T. A. Miller, D. Dligach, and P. J. Chen, 'Automatic prediction of rheumatoid arthritis disease activity from the electronic medical records,' PloS one, vol. 8, p. e69932, 2013. [13] H.-H. Chen, D.-Y. Chen, S.-Y. Lin, K.-L. Lai, Y.-M. Chen, and Y.-J. Chou, 'Exposição à periodontite no intervalo de um ano antes do tratamento antidiabético e risco de artrite reumatoide em pacientes com diabete mellitus: estudo de coorte populacional,' Revista Brasileira de Reumatologia, vol. 54, pp. 124-130, 2014. [14] Y.-Y. Chou, K.-L. Lai, D.-Y. Chen, C.-H. Lin, and H.-H. Chen, 'Rheumatoid arthritis risk associated with periodontitis exposure: a nationwide, population-based cohort study,' PloS one, vol. 10, p. e0139693, 2015. [15] S. Ibáñez, C. Ferreiro, A. Contreras, O. Valenzuela, N. Giadalah, and V. Jara, 'Frequency and severity of periodontitis among patients with rheumatoid arthritis,' Revista medica de Chile, vol. 143, pp. 1539-1545, 2015. [16] S. M. Lorenzo, R. Alvarez, E. Andrade, V. Piccardo, A. Francia, and F. Massa, 'Periodontal conditions and associated factors among adults and the elderly: findings from the first National Oral Health Survey in Uruguay,' Cadernos de saude publica, vol. 31, pp. 2425-2436, 2015. [17] H. Bawadi, Y. Khader, T. Haroun, M. Al‐Omari, and R. Tayyem, 'The association between periodontal disease, physical activity and healthy diet among adults in Jordan,' Journal of periodontal research, vol. 46, pp. 74-81, 2011. [18] N. Singla, S. Acharya, R. V. Prabhakar, K. Chakravarthy, D. Singhal, and R. Singla, 'The impact of lifestyles on the periodontal health of adults in Udupi district: A cross sectional study,' Journal of Indian Society of Periodontology, vol. 20, p. 330, 2016. [19] H. Chen, W. Chao, Y. Chen, and D. Chen, 'FRI0691 Association between periodontitis and the risk of palindromic rheumatism: a nationwide, population-based, case-control study,' Annals of the Rheumatic Diseases, vol. 76, p. 751, 2017. [20] L.-G. Huang, G. Chen, D.-Y. Chen, and H.-H. Chen, 'Factors associated with the risk of gingival disease in patients with rheumatoid arthritis,' PloS one, vol. 12, p. e0186346, 2017. [21] I. Guyon and A. Elisseeff, 'An introduction to variable and feature selection,' Journal of machine learning research, vol. 3, pp. 1157-1182, 2003. [22] T. G. Dietterich, 'Ensemble methods in machine learning,' in International workshop on multiple classifier systems, 2000, pp. 1-15. [23] Z.-H. Zhou, Ensemble methods: foundations and algorithms: Chapman and Hall/CRC, 2012. [24] L. Rokach, 'Ensemble-based classifiers,' Artificial Intelligence Review, vol. 33, pp. 1-39, 2010. [25] J. A. Hanley and B. J. McNeil, 'The meaning and use of the area under a receiver operating characteristic (ROC) curve,' Radiology, vol. 143, pp. 29-36, 1982. [26] S. Chatterjee and A. S. Hadi, Regression analysis by example: John Wiley & Sons, 2015. [27] S. R. Safavian and D. Landgrebe, 'A survey of decision tree classifier methodology,' IEEE transactions on systems, man, and cybernetics, vol. 21, pp. 660-674, 1991. [28] S. Abe, 'Feature selection and extraction,' in Support Vector Machines for Pattern Classification, ed: Springer, 2010, pp. 331-341. [29] 林盈秀, '資料遺漏率, 補值法與資料前處理關係之研究; The relationship between missing value, imputation and data pre-processing,' 國立中央大學, 2013. [30] G. E. Batista and M. C. Monard, 'A Study of K-Nearest Neighbour as an Imputation Method,' HIS, vol. 87, p. 48, 2002. [31] K. Beyer, J. Goldstein, R. Ramakrishnan, and U. Shaft, 'When is 'nearest neighbor' meaningful?,' in International conference on database theory, 1999, pp. 217-235. [32] L. Breiman, 'Random forests,' Machine learning, vol. 45, pp. 5-32, 2001. [33] F. Ferri, P. Pudil, M. Hatef, and J. Kittler, 'Comparative study of techniques for large-scale feature selection,' in Machine Intelligence and Pattern Recognition. vol. 16, ed: Elsevier, 1994, pp. 403-413.
摘要: 近幾年機器學習在醫學診斷已廣泛運用,例如:預測腫瘤、癌症上都有良好的功效,而目前有些論文提出對於類風溼性關節炎與牙周病上之影響,但由於類風濕性關節炎的成因仍未清楚,所以本碩士論文利用機器學習中的集成方法,包含隨機森林、袋裝方法、自適應增強方法、梯度提升決策樹,四種演算法來預測牙周病與類風濕性關節炎之相關性,進而推導出預測類風濕性關節炎時,有哪些牙周病之臨床資料會影響其準確度。實驗結果得出,在眾多屬性下利用機器學習所得到的屬性例如性別、是否有抽煙、牙齦流血點個數,在其他論文中也都證實其與類風濕性關節炎或牙周病有正相關,然而,本篇論文類風溼性關節炎療效的預測可以達到八成以上的準確率,然而刪除其中牙周病之相關屬性時,準確率則降低至四成。由此可推導出牙周病確實對於類風濕性關節炎有很大的影響,本論文能透過使用本篇方法提升醫療準確性,並且達到最有效率的運用之餘,機器學習還能幫助醫生增加預測的準確度,減少誤判的機會,幫助我們提供更方便更好的醫療生活品質。
In recent years, machine learning has been widely used in medical diagnosis. For example, it has good efficacy in predicting tumors and cancer. At present, some thesis have proposed effects on rheumatoid arthritis and periodontal disease, but due to no infectious agent has been consistently linked with rheumatoid arthritis and there is no evidence of disease clustering to indicate its infectious cause, periodontitis has been consistently associated with rheumatoid arthritis. In this thesis, we use Ensemble methods including random forest, bagging, adaboost, gradient boosting to predict the positive correlation between the periodontitis and rheumatoid arthritis, and further the prediction the efficacy of rheumatoid arthritis, which features belong to periodontal disease will affect its accuracy. The experimental results show that using machine learning to find out the features such as gender, smoking, bleeding on Probing can confirm by other thesis. It has a positive correlation with rheumatoid arthritis and periodontal disease. Then, when predicting the efficacy of rheumatoid arthritis, there is an accuracy of more than 80%. When the relevant features of periodontal disease delete, the accuracy rate reduces to 40%. It can show that periodontal disease has a great impact in Rheumatoid arthritis. We hope to use this method to improve medical accuracy. This thesis proves to you that machine learning not only helps doctors increase the accuracy of predictions and reduces the misjudgment as possible, but also helps us provide for more convenient and better quality of medical life.
URI: http://hdl.handle.net/11455/98265
文章公開時間: 10000-01-01
Appears in Collections:資訊管理學系

文件中的檔案:

取得全文請前往華藝線上圖書館



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.