( 您好!臺灣時間:2024/07/23 09:33
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::


研究生(外文):Wu, Chia-Cheng
論文名稱(外文):Application of Machine Learning to Diagnosis of Periprosthetic Joint Infection: Comparison between Ensemble Meta Machine Learning and 2018 International Consensus Meeting Scoring System
指導教授(外文):Hu, Yuh-Jyh
口試委員(外文):Yang, WuuHuang, Chung-Yuan
外文關鍵詞:Explainable AIStacking
  • 被引用被引用:0
  • 點閱點閱:190
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
Machine learning has been widely applied in medicine, although little has been published regarding periprosthetic joint infection (PJI) diagnosis. Here, we evaluated machine learning feasibility for PJI diagnosis and compared its predictive performance with that of scoring criteria commonly used by clinicians. We addressed PJI diagnosis as an inductive learning problem, wherein each patient record is represented by a set of patient features. Rather than learning a single diagnosis model from a series of patient records, we propose combining multiple prediction models to achieve superior performance by utilizing the synergy of multiple predictors. We created a two-level meta stacking learner comprising four base classifiers and one meta-classifier. To resolve the comprehensibility issue of machine learning, we developed a surrogate-based explanation generator to provide understandable interpretations. To assess the meta learner’s performance, we cross-validated 323 Asian patients for comparison.We developed an ensemble meta learner for PJI prediction. It is suggested that machine learning is applicable and competitive for PJI diagnosis as compared with the currently widely accepted scoring criteria.
第一章、 緒論 1
1.1 研究背景與動機 1
1.2 研究目標 2
第二章、 相關方法與文獻 3
2.1 演算法 3
2.1.1 隨機森林 (Random Forest, RF) 3
2.1.2 羅吉斯回歸 (Logistic Regression, LR) 4
2.1.3  貝氏分類器 (Naïve Bayes, NB) 5
2.1.4 XGBoost (Extreme Gradient Boosting, XGB) 5
2.1.5 支持向量機 (Support Vector Machine, SVM) 7
2.1.6 Stacking 8
第三章、 實驗方法 9
3.1 研究對象與預測比較 9
3.2 效能評估 12
3.3 以PJI-AR預測作為歸納學習 14
3.4 集成元學習--堆疊泛化 15
3.5 可解釋的集成學習 17
3.6 PJI預測與解釋 ━ PJI-PI 20
第四章、 實驗結果 21
4.1 PJI預測的ML和ICM標準比較 21
4.2 PJI-PI模型解釋生成器 23
4.3 重要特徵 27
第五章、 討論 29
第六章、 結論 31
第七章、 參考文獻 32
附錄 36
[1] Zmistowski B, Karam JA, Durinka JB, Casper DS, Parvizi J. Periprosthetic joint infection increases the risk of one-year mortality. J Bone Joint Surg Am 2013;95:2177–84. https://doi.org/10.2106/JBJS.L.00789.
[2] Kunutsor SK, Beswick AD, Peters TJ, Gooberman-Hill R, Whitehouse MR, Blom AW, et al. Health care needs and support for patients undergoing treatment for prosthetic joint infection following hip or knee arthroplasty: a systematic review. PloS One 2017;12:e0169068. https://doi.org/10.1371/journal.pone.0169068.
[3] Workgroup Convened by the Musculoskeletal Infection Society. New definition for periprosthetic joint infection. J Arthroplasty 2011;26:1136–8. https://doi.org/10.1016/j.arth.2011.09.026.
[4] Parvizi J, Gehrke T, International consensus group on periprosthetic joint infection: definition of periprosthetic joint infection. J Arthroplasty 2014;29:1331. https://doi.org/10.1016/j.arth.2014.03.009.
[5] Parvizi J, Tan TL, Goswami K, Higuera C, Della Valle C, Chen AF, et al. The 2018 Definition of periprosthetic hip and knee infection: an evidence-based and validated criteria. J Arthroplasty 2018;33:1309–14.e2. https://doi.org/10.1016/j.arth.2018.02.078.
[6] Shohat N, Bauer T, Buttaro M, Budhiparama N, Cashman J, Della Valle CJ, et al. Hip and knee section, what is the definition of a periprosthetic joint infection (pji) of the knee and the hip? can the same criteria be used for both joints?: proceedings of international consensus on orthopedic infections. J Arthroplasty 2019;34:S325–7. https://doi.org/10.1016/j.arth.2018.09.045.
[7] Kunutsor SK, Whitehouse MR, Blom AW, Beswick AD, INFORM team. patient-related risk factors for periprosthetic joint infection after total joint arthroplasty: a systematic review and meta-analysis. PloS One 2016;11:e0150866. https://doi.org/10.1371/journal.pone.0150866.
[8] Kallala RF, Vanhegan IS, Ibrahim MS, Sarmah S, Haddad FS. Financial analysis of revision knee surgery based on NHS tariffs and hospital costs: does it pay to provide a revision service? Bone Jt J 2015;97-B:197–201. https://doi.org/10.1302/0301-620X.97B2.33707.
[9] Kononenko I. Machine learning for medical diagnosis: history, state of the art and perspective. Artif Intell Med 2001;23:89–109. https://doi.org/10.1016/s0933-3657(01)00077-x.
[10] Cruz JA, Wishart DS. Applications of machine learning in cancer prediction and prognosis. Cancer Inform 2007;2:59–77.
[11] Hu Y-J, Ku T-H, Yang Y-H, Shen J-Y. Prediction of patient-controlled analgesic consumption: a multimodel regression tree approach. IEEE J Biomed Health Inform 2018;22:265–75. https://doi.org/10.1109/JBHI.2017.2668393.
[12] Deo RC. Machine learning in medicine. Circulation 2015;132:1920–30. https://doi.org/10.1161/CIRCULATIONAHA.115.001593.
[13] Samad MD, Ulloa A, Wehner GJ, Jing L, Hartzel D, Good CW, et al. Predicting survival from large echocardiography and electronic health record datasets: optimization with machine learning. JACC Cardiovasc Imaging 2019;12:681–9. https://doi.org/10.1016/j.jcmg.2018.04.026.
[14] Navarro SM, Wang EY, Haeberle HS, Mont MA, Krebs VE, Patterson BM, et al. Machine learning and primary total knee arthroplasty: patient forecasting for a patient-specific payment model. J Arthroplasty 2018;33:3617–23. https://doi.org/10.1016/j.arth.2018.08.028.
[15] Harris AHS, Kuo AC, Weng Y, Trickey AW, Bowe T, Giori NJ. Can machine learning methods produce accurate and easy-to-use prediction models of 30-day complications and mortality after knee or hip arthroplasty? Clin Orthop 2019;477:452–60. https://doi.org/10.1097/CORR.0000000000000601.
[16] Gabriel RA, Sharma BS, Doan CN, Jiang X, Schmidt UH, Vaida F. A predictive model for determining patients not requiring prolonged hospital length of stay after elective primary total hip arthroplasty. Anesth Analg 2019;129:43–50. https://doi.org/10.1213/ANE.0000000000003798.
[17] Karhade AV, Schwab JH, Bedair HS. Development of machine learning algorithms for prediction of sustained postoperative opioid prescriptions after total hip arthroplasty. J Arthroplasty 2019;34:2272–7.e1. https://doi.org/10.1016/j.arth.2019.06.013.
[18] Shohat N, Goswami K, Tan TL, Yayac M, Soriano A, Sousa R, et al. 2020 Frank Stinchfield Award: identifying who will fail following irrigation and debridement for prosthetic joint infection. Bone Jt J 2020;102-B:11–9. https://doi.org/10.1302/0301-620X.102B7.BJJ-2019-1628.R1.
[19] Handelman GS, Kok HK, Chandra RV, Razavi AH, Lee MJ, Asadi H. eDoctor: machine learning and the future of medicine. J Intern Med 2018;284:603–19. https://doi.org/10.1111/joim.12822.
[20] Obermeyer Z, Emanuel EJ. Predicting the future - big data, machine learning, and clinical medicine. N Engl J Med 2016;375:1216–9. https://doi.org/10.1056/NEJMp1606181.
[21] Shohat N, Tan TL, Della Valle CJ, Calkins TE, George J, Higuera C, et al. Development and validation of an evidence-based algorithm for diagnosing periprosthetic joint infection. J Arthroplasty 2019;34:2730–6.e1. https://doi.org/10.1016/j.arth.2019.06.016.
[22] Breiman L. Random forests. Mach Learn 2001;45:5–32. https://doi.org/10.1023/A:1010933404324.
[23] Seber G, Lee AJ. Linear regression analysis. 2nd ed. New York: Wiley; 2003.
[24] Bhagya Shree SR, Sheshadri HS. Diagnosis of Alzheimer’s disease using naive bayesian classifier. Neural Comput Appl 2018;29:123–32. https://doi.org/10.1007/s00521-016-2416-3
[25] Chen T, Guestrin C. XGBoost: A Scalable Tree Boosting System. Proc 22nd ACM SIGKDD Int Conf Knowl Discov Data Min, New York: association for computing machinery; 2016;785–794. https://doi.org/10.1145/2939672.2939785
[26] Chang CC, Lin C-J. LIBSVM: A library for support vector machines. ACM Trans Intell Syst Technol 2011;2. https://doi.org/10.1145/1961189.1961199.
[27] Wolpert DH. Stacked generalization. Neural Netw 1992;5:241–59. https://doi.org/10.1016/S0893-6080(05)80023-1.
[28] Ting KM, Witten IH. Stacked generalization: when does it work? Hamilton: Department of Computer Science, University of Waik;1997:866–71. https://hdl.handle.net/10289/1066
[29] Gama J. Combining classifiers by constructive induction. In: Nédellec C, Rouveirol C, editors. European conference machine learning, Berlin: Springer Berlin Heidelberg; 1998, p. 178–89.
[30] Breiman L. Bagging Predictors. Mach Learn 1996;24:123–40. https://doi.org/10.1023/A:1018054314350.
[31] Schapire RE. The strength of weak learnability. Mach Learn 1990;5:197–227. https://doi.org/10.1007/BF00116037.
[32] Tulio Ribeiro M, Singh S, Guestrin C. “ Why Should I Trust You?”: explaining the predictions of any classifier. ArXiv 2016:arXiv:1602.04938. https://arxiv.org/abs/1602.04938
[33] Marco Tulio R, Singh S, Guestrin C. Anchors: high-precision model-agnostic explanations. AAAI 2018;1527–35. https://homes.cs.washington.edu/~marcotcr/aaai18.pdf
[34] Goodman B, Flaxman S. European Union Regulations on Algorithmic decision-making and a “right to explanation.” AI Mag 2017;38:50–7. https://doi.org/10.1609/aimag.v38i3.2741
[35] Merigó JM, Gil-lafuente AM. Using the OWA operator in the minkowski distance. Int J Econ Manag Eng 2008;2:1032–40. https://zenodo.org/record/1084486
[36] Shankaranarayana SM, Runje D. ALIME: autoencoder based approach for local interpretability. Int Conf Intell Data Eng Autom Learn. Springer. 2019;454–63. https://doi.org/10.1007/978-3-030-33607-3_49
[37] Taylor Paziuk , Alexander J Rondon , Karan Goswami , Timothy L Tan , Javad Parvizi. A Novel Adjunct Indicator of Periprosthetic Joint Infection: Platelet Count and Mean Platelet Volume. J Arthroplasty . 2020 Mar;35(3):836-839. https://doi.org/10.1016/j.arth.2019.10.012.
[38] Abdelaziz H, Rademacher K, Suero EM, Gehrke T, Lausmann C, Salber J, et al. The 2018 international consensus meeting minor criteria for chronic hip and knee periprosthetic joint infection: validation from a single center. J Arthroplasty 2020. https://doi.org/10.1016/j.arth.2020.03.014.
[39] Xu C, Wang Q, Kuo F-C, Goswami K, Tan TL, Parvizi J. The presence of sinus tract adversely affects the outcome of treatment of periprosthetic joint infections. J Arthroplasty 2019;34:1227-1232.e2. https://doi.org/10.1016/j.arth.2019.02.040.
[40] Chen JH, Asch SM. Machine learning and prediction in medicine - beyond the peak of inflated expectations. N Engl J Med 2017;376:2507–9. https://doi.org/10.1056/NEJMp1702071.
電子全文 電子全文(網際網路公開日期:20260113)
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
第一頁 上一頁 下一頁 最後一頁 top