依據2017年美國腎臟登錄系統(United States Renal Data System, USRDS) 年報統計,2015年台灣末期腎臟病(End-stage renal disease, ESRD) 發生率(Incidence) 為476人/每百萬人口, 且透析(Dialysis) 盛行率(Prevalence) 為3,185人/每百萬人口, 此兩項指標皆為世界第一, 遠超過美國與日本等國家。
末期腎臟病病人因腎臟功能受損, 無法自行代謝血中廢物, 故需接受血液透析治療。
對長期血液透析病人而言, 廔管是重要的生命線, 故在透析前必須執行手術建立透析廔管。透析廔管是藉由外科手術將自身的動脈及靜脈接合, 使動脈血液衝向靜脈, 讓靜脈血管管腔膨脹, 且術後搭配握球訓練等, 約1-2個月讓血管成熟(maturation), 而管腔膨脹後的靜脈即為廔管。
廔管狹窄為血液透析的主要問題之一, 因廔管使用頻率高(每週三次), 導致部分病人的廔管容易造成狹窄, 目前評估狹窄的方式, 皆為發生一段時間後, 已經有臨床症狀才被發現, 或必須由專業人員以侵入性方式檢測廔管是否狹窄。若能有簡易且能事先預測廔管狹窄的方法, 病人即可事先安排經皮氣球血管擴張術(Percutaneous Transluminal Angioplasty,PTA) 疏通廔管, 確保於下次透析前完成疏通, 提升病人安全。
本研究以時域及頻域訊號定義31項關鍵因子, 並以類神經網路預測廔管是否狹窄。
單一因子預測, 以時域訊號特徵值TR(x2 (t′), a = 0.2, c = 0.9)、TR(x2t′ , c = 60)及頻域訊號特徵值F6為最主要的關鍵因子;兩個關鍵因子預測時, 在四次不同組合之預測中, 分別以(1)TR(x2 (t′), a = 0.2, c = 0.9)、F6 (2)TR(x2t′ , c = 70), F9 (3)TR(x2t′ , c = 80), F9(4)WER, F7 之準確率最高, 預測結果皆以整合時域及頻域訊號為佳。

According to the statistics in the 2017 United States Renal Data System Annual Report, the incidence rate of end-stage renal disease (ESRD) in Taiwan in 2015 was 476 per million people while the prevalence rate of dialysis was 3,185 per million people. Both indices were the highest in the world, way surpassing the figures for the US and Japan.
Due to their damaged renal functions, end-stage renal disease patients are unable to metabolize the waste in their blood and have to undergo hemodialysis. Such patients need areriovenous fistulas to stay alive. Therefore, creation of dialysis fistulas is necessary before patients start to receive dialysis. Hemodialysis fistulas are surgically created communications between the native artery and vein in an extremity to allow blood in the artery to run to the vein and expand the lumen diameter of the vein. After surgery and ball grasping training, blood vessel
maturation takes about 1-2 months and a vein with expanded lumen diameter finally can be used as a fistula.
Narrowness of fistulas is a major problem in hemodialysis. The high frequency of use of fistulas (three times a week) causes the fistulas of some patients to narrow down. So far, narrowing down of fistulas can be discovered only after it has happened for some time and clinical symptoms have appeared or after specialists
conduct invasive inspections to check whether fistulas have narrowed down. If there is an easier method to predict narrowing down of fistulas, arrangements can be made in advance for patients to undergo percutaneous transluminal angioplasty (PTA) to open up the fistula and make sure there is no blockage before the following dialysis treatment in order to protect the safety of patients.
In this study, 31 key factors associated with time domain and frequency domain signals are adopted in conjunction with an artificial neural network to predict stenosis of fistulas. The time domain signal eiganvalues TR(x2 (t′), a = 0.2, c = 0.9)
and TR(x2t′ , c = 60) and frequency domain signal eiganvalue F6 are the main key factors in single-factor forecasting. In two-factor forecasting, combining time and frequency domain factors produce good results. The key two-factor in four test are (1)TR(x2 (t′), a = 0.2, c = 0.9)、F6 (2)TR(x2t′ , c = 70), F9 (3)TR(x2t′ , c = 80), F9 (4)WER, F7.

誌謝i
摘要ii
英文摘要iii
目錄v
表目錄vi
圖目錄vi
第1 章緒論1
1.1 研究背景. . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.2 研究動機與目的. . . . . . . . . . . . . . . . . . . . . . . 2
1.3 研究流程與架構. . . . . . . . . . . . . . . . . . . . . . . 3
1.4 命名定義與數學符號. . . . . . . . . . . . . . . . . . . . . 4
1.5 論文架構. . . . . . . . . . . . . . . . . . . . . . . . . . 6
第2 章文獻探討7
2.1 血液透析廔管. . . . . . . . . . . . . . . . . . . . . . . . 7
2.1.1 血液透析廔管手術. . . . . . . . . . . . . .. . . . . . . . 7
2.1.2 血液透析廔管狹窄與疏通. . . . . . . . . . . . . . . . . . 8
2.2 訊號處理. . . . . . . . . . . . . . . . . . . . . . . . . . 9
2.2.1 傅立葉轉換. . . . . . . . . . . . . . . . . . . . . . . . 9
2.2.2 時域及頻域的意義. . . . . . . . . . . . . . . . . . . . . 10
2.3 分類與預測. . . . . . . . . . . . . . . . . . . . . . . . . 11
2.4 回顧與整合血管音資料. . . . . . . . . . . . . . . . . . . . 12
第3 章研究方法16
3.1 收集訊號位置及收音設備. . . . . . . . . . . . . . . .. . . . 16
3.2 資料前處理. . . . . . . . . . . . . . . . . . . . . . . . . 17
3.2.1 設計濾波器. . . . . . . . . . . . . . . . . . . . . . . . 17
3.2.2 訊號萃取. . . . . . . . . . . . . . . . . . . . . . . . . 18
3.2.3 時頻域轉換. . . . . . . . . . . . . . . . . . ... . . . . 19
第4 章研究結果20
4.1 探討影響血管音量測之顯著因子. . . . . . . . . . . .. . . . . 20
v
4.1.1 設計實驗因子表. . . . . . . . . . . . . . . . . . . . . . 20
4.1.2 因子實驗分析及結果. . . . . . . . . . . . . . . . . . . . 20
4.1.3 小結: 電腦種類顯著影響血管音訊號. . . . . . . . . .. . . . 21
4.2 預測廔管阻塞的關鍵因子. . . . . . . . . . . . . . . . . . . 22
4.2.1 定義31個可能的關鍵因子. . . . . . . . . . . . . . . . . . 22
4.2.2 類神經網路預測廔管阻塞結果. . . . . . . . . . . . . .. . . 25
4.2.3 小結: 最佳關鍵前2關鍵因子為整合時域及頻域訊號 . . . . . . . 32
第5 章結論與未來展望30
5.1 結論. . . . . . . . . . . . . . . . . . . . . . . . . . . 33
5.2 未來展望. . . . . . . . . . . . . . . . . . . . . . . . . 33
參考文獻35
附錄39

[1] USRDS, “2013 USRDS Annual Data Report", United States Renal Data System, (2013).
[2] D. C. Montgomery, JohnWiley and Sons, Design and Analysis of Experiments,New York. (6th ed.), (2005).
[3] R. A. Fisher, “The Use of Multiple Measurements in Taxonomic Problems",Annals of Eugenics, Vol. 7, No. 7, pp. 179-188, (1936).
[4] M. Kano, S. Tanaka, S. Hasebe, I. Hashimoto and H. Ohno, “Combined Multivariate Statistical Process Control, In proceedings of IFAC Symposium on Advanced Control of Chemical Plants", ADCHEM 2004, pp. 303-308,(2004).
[5] T. T. Shannon and J. McNames, “ICA Based Disturbance Specific Control Charts, In proceedings of the IEEE International Conference on Information Reuse and Integration", IRI 2007, pp. 251-256, (2007).
[6] A. Hyvärinen, “Fast and Robust Fixed-Point Algorithms for Independent Component Analysis". IEEE Transactions on Neural Networks, Vol. 10, No. 3, pp. 626-634, (1999).
[7] A. Hyvärinen, “Survey on Independent Component Analysis", Neural Computing Surveys, Vol. 2, pp. 94-128, (1999).
[8] A. Hyvärinen and E. Oja , “Independent Component Analysis: Algorithms and Applications", Neural Networks, Vol. 13, pp. 411-430, (2000).
[9] A. Hyvärinen, J. Karhunen and E. Oja, “Independent Component Analysis", Wiley-Interscience. (1st ed.), (2001).
[10]Dheeraj K. Rajan, Sarah Bunston, Sanjay Misra, et al., “Dysfunctional Autogenous Hemodialysis Fistulas: Outcomes after Angioplasty - Are There Clinical Predictors of Patency?" adiology, (2004).
[11]H. A. Mansy, S.J. Hoxie, N.H. Patel, R.H. Sandier, “Computerised analysis of auscultatory sounds associated with vascular patency of haemodialysis access", Med. Biol. Eng. Comput., pp. 56-62, (2005).
[12]MacroM. M., Pablo V. and Bengt M., “Characterisation of Arteriovenous Fistula’S Sound Recordings Using Principal Component Analysis", 31rd Annual International Conference of the IEEE EMBS, pp. 5661-5664, (2009).
[13]Macro M. M., Pablo V. and Bengt M., “Acoustical Detection of Venous Stenosis in Hemodialysis Patients Using Principal Component Analysis", 32nd Annual International Conference of the IEEE EMBS, pp. 3654-3657, (2010).
[14]Macro M. M. and Bengt M., “Analysis of The Vascular Sounds of The Arteriovenous Fistula’s Anastomosis", 33rd Annual International Conference of the IEEE EMBS, pp. 3784-3787, (2011).
[15]Pablo V., Macro M. M. and Bengt M., “Arteriovenous Fistula Stenosis Detection Using Wavelets and Support Vector Machines", 31rd Annual International Conference of the IEEE EMBS, pp. 1298-1301, (2009).
[16]Mikkel Grama, Jens Tranholm Olesena, Hans Christian Riisa, Maiuri Selvaratnama, Michalina Urbaniaka, “Stenosis detection algorithm for screening of arteriovenous fistulae", SEMCON conference paper 1-6, (2010).
[17]Masako Kawai and Akifumi Suzuki, “Analysis and Evaluation of Vascular Sounds in Hemodialysis", 35th Annual International Conference of the IEEE EMBS ,Osaka, Japan, 3 - 7 July, (2013).
[18]Chen W.L.,Lin C.H., Lin T.C., Chen P.J., Kan C.D., “Stenosis Detection using Burg Method with Autoregressive Model for Hemodialysis Patients", Journal of Medical and Biological Engineering, pp. 356-362, (2012).
[19]H. H. Yang and S. I. Amari, “Adaptive Online Learning Algorithms for Blind Separation: Maximum Entropy and Minimum Mutual Information", Neural Computation, Vol. 9, pp. 1457-1482, (1997).
[20]E. Miller and J. Fisher, “ICA Using Spacings Estimates of Entropy", In processings of the Furth International Workshop on Independent Component Analysis and Blind Signal Separation, pp. 1271-1295, (2003).
[21]K. Hild, D. Erdogmus and J. Principe, “Blind Source Separations Using Renyi’s Mutual Information", IEEE Signal Processing Letters, Vol. 8, No.6, pp. 174-176, (2001).
[22]N. Delfosse and P. Loubaton, “Adaptive Blind Separation of Independent Sources: A Deflation Approach", Signal processing, Vol. 45, pp. 59-83,(1996).
[23]C. Jutten and J. Herault, “Blind Separation of Sources, Part I: An Adaptive Algorithm Based on Neuromimetic Architecture", Signal Processing, Vol.24, pp. 1-10, (1991).
[24]G. H. Hardy, J. E. Littlewood and G. Polya, “Inequalities", Cambridge. (2nd ed.), (1952).
[25]B. Ans, J. Herault and C. Jutten, “Adaptive Neural Architectures: Detection of Primitives", In Proceedings of COGNITIVA’s 85, pp. 593-597, (1985).
[26]Baltimore, “Centers for Medicare Medicaid Services: 2003 Annual Report. End Stage Renal Disease Clinical Performance Measures Project.", (1985).
[27] Sehgal AR, Dor A, Tsai AC, “ Morbidity and cost implications of inadequate hemodialysis", Am J Kidney Dis 23:661–669, (1994).
[28] Feldman HI, Kobrin S, Wasserstein A, “ Hemodialysis vascular access morbidity", J Am Soc Nephrol 7:523–535, (1996).
[29] Rocco MV, Bleyer AJ, Burkart JM, “ Utilization of inpatient and outpatient resources for the management of hemodialysis access complications", Am J Kidney Dis 28:250–256, (1996).
[30] Aruny JE, Lewis CA, Cardella JF, et al, “Quality improvement guidelines for percutaneous management of the thrombosed or dysfunctional dialysis access", J Vasc Interv Radiol 14:S247–S253, (2003).
[31] Mu-Yang Hsieh, et al,“Deficiency of circulating progenitor cells associated with vascular thrombosis of hemodialysis patients", Nephrol Dial Transplant 32: 556–564, (2017).
[32]簡名儀, “以血流聲音時頻域特徵參數探究透析廔管之狹窄程度", 義守大學碩士論文, (2011).
[33]陳華緯, “動靜脈透析廔管血管音擷取裝置之改良與狹窄程度之分類", 義守大學碩士論文, (2012).
[34]江秀月, “創新的方法應用於廔管裝設與血管狹窄的血管音研究", 清華大學碩士論文, (2013).
[35]桑慧敏, 機率與推論統計原理, McGraw-Hill International. (第一版), (2007).
[36] 第二章盲訊號分離與方法介紹, http://waoffice.ee.kuas.edu.tw/, (2017).
[37]趙家馳, “廔管阻塞血管音之資料分析", 清華大學碩士論文, (2017).