跳到主要內容

臺灣博碩士論文加值系統

(44.201.99.222) 您好!臺灣時間:2022/12/05 23:01
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:趙軒毫
研究生(外文):Chao, Hsuan-Hao
論文名稱:利用複雜度與機器學習辨識心臟衰竭心跳訊號
論文名稱(外文):Recognition of Heart Failure Heartbeat Signals by Complexity and Machine Learning
指導教授:徐琅
指導教授(外文):Hsu, Long
口試委員:祁甡林烜輝林柏霖王威劉明麗
口試委員(外文):Chi, SienLin, Shiuan-HueiLin, Po-LinWang, WilliamLiou, Ming-Li
口試日期:2019-11-13
學位類別:博士
校院名稱:國立交通大學
系所名稱:電子物理系所
學門:自然科學學門
學類:物理學類
論文種類:學術論文
論文出版年:2019
畢業學年度:108
語文別:中文
論文頁數:42
中文關鍵詞:心臟衰竭心率變異度複雜度狀態變化機率機器學習低維度窮舉法
外文關鍵詞:Heart FailureHeart Rate VariabilityComplexityState Change ProbabilityMachine LearningLow-Dimensional Exhaustive Search
相關次數:
  • 被引用被引用:0
  • 點閱點閱:88
  • 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
  心臟衰竭是一種常見的心血管疾病,年死亡率達10%。從心跳訊號中辨識心臟衰竭的諸多分析技術中,2002年提出的生理複雜度深具潛力。由於複雜度反映生理系統適應環境的能力,因此健康人的複雜度高於心臟衰竭病患的複雜度。複雜度指標包括多尺度熵(MSE)與熵之熵(EoE),通常用來分析20個不同時間長度之下的心跳訊號的複雜度資訊,提供多維度的特徵。然而,這些方法受訊號長度影響,也須對應微調參數。因此,本研究旨在發展一種新指標:狀態變化機率(SCP),以克服這些缺點。並比較SCP、MSE、與EoE三指標分析100跳(約1.5分鐘)、1,000跳(約15分鐘)、10,000跳(約2.4小時)心跳訊號的辨識度。
  此外,本研究引進人工智慧機器學習技術,以提升識別心臟衰竭病患的準確度。機器學習常用窮舉法、前向特徵選擇法、和後向特徵選擇法挑選最佳局部維度的特徵。再用線性判別分析法(LDA)和支援向量機(SVM)兩種分類器有效辨識健康人與病患。雖然窮舉法較準確,但耗時。因此,本研究提出一個新的低維度窮舉法,以大量節省運算時間。結果,SVM搭配5個維度的窮舉為最佳機器學習方案,可以節省98%運算時間。
  應用上述最佳方案於辨識心臟衰竭的研究中,結果顯示MSE只能用在10,000點的長數據,病患識別率將近85%、準確度為93%。EoE在三種長度的準確率相近(85~90%),但病患識別率皆低於80%。SCP之識別率和準確度在短數據分別約75%和86%;在中、長數據則分別約81~86%與92~93%,不論在哪種數據長度皆優於MSE和EoE。因此,SCP比MSE和EoE更具心臟衰竭快篩與即時監控的潛力。
  Heart failure (HF) is a common cardiac disease, which leads to 10% annual mortality. For recognition of heart failure, the biological complexity, proposed in 2002, is promising. The complexity reflects the adaptability of physiological systems. Thus, the complexity of healthy people is higher than that of HF patients. Two measures of complexity, multiscale entropy (MSE) and entropy of entropy (EoE), are usually utilized to analyze heartbeat signals at 20 temporal scales for feature extraction. However, the measures are dependent on data sizes and sensitive to parameters. Therefore, this study aims to develop a new measure, state change probability (SCP), to overcome the limitations. SCP is compared with MSE and EoE on recognizing the heartbeat signals from HF patients with data sizes of 100, 1,000, and 10,000 beats.
  This study utilized machine learning to improve the recognition. The exhaustive search, forward selection and backward selection are common methods to determine representative features. These features are then used for the recognition by means of linear discriminant analysis (LDA) or support vector machine (SVM). The exhaustive search can find the optimal features yet it is time-consuming. Thus, this study proposed low-dimensional exhaustive search to reduce computation. It was found that SVM with 5D exhaustive search was suited for the recognition with decreasing 98% computation.
  The results showed that MSE was only applicable to long heartbeat signals (10,000). The accuracy was 93% and sensitivity was about 85%. With respect to EoE, the accuracies for the three data sizes were similar (85~90%), yet the sensitivities were less than 80%. Comparatively, the accuracy and sensitivity of SCP were 75% and 86% for 100 beats, respectively. For longer heartbeat signals, the accuracy and sensitivity were 81~86% and 92~83%, respectively. The results indicate that SCP is better than MSE and EoE for different data sizes. Therefore, SCP is very promising on screening and monitoring heart failure.
中文摘要 ……………………………………………………………………… i
英文摘要 ……………………………………………………………………… ii
誌謝 ……………………………………………………………………… iii
目錄 ……………………………………………………………………… iv
表目錄 ……………………………………………………………………… vi
圖目錄 ……………………………………………………………………… vi
一、緒論 ……………………………………………………………………… 1
1.1 心臟衰竭 …………………………………………………………… 1
1.2 心率變異度 …………………………………………………………… 2
1.2.1 傳統心率變異度指標 ……………………………………… 3
1.2.2 複雜度指標MSE和EoE之簡介 …………………………… 4
1.2.3 複雜度指標MSE和EoE之限制 …………………………… 7
1.2.4 新複雜度指標SCP ……………………………………… 8
1.3 機器學習 …………………………………………………………… 9
1.4 文獻回顧 …………………………………………………………… 12
1.5 研究架構 …………………………………………………………… 13
二、狀態變化機率 …………………………………………………………… 14
2.1 概念與計算方式 ……………………………………………………… 14
2.2 統計假說檢定 ……………………………………………………… 15
三、方法數據處理、傳統複雜度指標 ………………………………… 17
3.1 數據處理 …………………………………………………………… 17
3.1.1 合成訊號 ……………………………………………………… 17
3.1.2 心跳訊號 ……………………………………………………… 17
3.2 MSE演算法 …………………………………………………………… 18
3.3 EoE演算法 …………………………………………………………… 19
四、方法機器學習 ……………………………………………………… 21
4.1 分類器 …………………………………………………………… 21
4.1.1 線性判別分析法(LDA) ……………………………………… 21
4.1.2 支援向量機(SVM) ……………………………………… 26
4.2 特徵選擇 …………………………………………………………… 28
4.2.1 無特徵選擇法 ……………………………………………… 28
4.2.2 前向累加法 ……………………………………………… 28
4.2.3 後向剔除法 ……………………………………………… 29
4.2.4 低維度窮舉法 ……………………………………………… 30
4.3 評價指標 …………………………………………………………… 31
五、結果與討論 ………………………………………………………………… 32
5.1 合成訊號之複雜度定性分析 ……………………………………… 32
5.2 心跳訊號之複雜度定性分析 ……………………………………… 34
5.3 機器學習方法比較 ………………………………………………… 35
5.4 心跳訊號識別能力評價 …………………………………………… 38
六、結論 ……………………………………………………………………… 39
參考文獻 ……………………………………………………………………… 40
1. McMurray, J.J.; Pfeffer, M.A. Heart failure. Lancet 2005, 365, 1877-1889.
2. In Chronic heart failure: National clinical guideline for diagnosis and management in primary and secondary care: Partial update, London, 2010.
3. Ponikowski, P.; Voors, A.A.; Anker, S.D.; Bueno, H.; Cleland, J.G.; Coats, A.J.; Falk, V.; Gonzalez-Juanatey, J.R.; Harjola, V.P.; Jankowska, E.A., et al. 2016 esc guidelines for the diagnosis and treatment of acute and chronic heart failure: The task force for the diagnosis and treatment of acute and chronic heart failure of the european society of cardiology (esc). Developed with the special contribution of the heart failure association (hfa) of the esc. Eur J Heart Fail 2016, 18, 891-975.
4. Gottdiener, J.S.; McClelland, R.L.; Marshall, R.; Shemanski, L.; Furberg, C.D.; Kitzman, D.W.; Cushman, M.; Polak, J.; Gardin, J.M.; Gersh, B.J., et al. Outcome of congestive heart failure in elderly persons: Influence of left ventricular systolic function - the cardiovascular health study. Annals of Internal Medicine 2002, 137, 631-639.
5. Cleland, J.G.F.; Daubert, J.; Erdmann, E.; Freemantle, N.; Gras, D.; Kappenberger, L.; Tavazzi, L.; Cleland, J.G.F.; Daubert, J.C.; Erdmann, E., et al. The effect of cardiac resynchronization on morbidity and mortality in heart failure. New Engl J Med 2005, 352, 1539-1549.
6. Nolan, J.; Batin, P.D.; Andrews, R.; Lindsay, S.J.; Brooksby, P.; Mullen, H.; Baig, W.; Flapan, A.D.; Cowley, A.; Prescott, R.J., et al. Prospective study of heart rate variability and mortality in chronic heart failure - results of the united kingdom heart failure evaluation and assessment of risk trial (uk-heart). Circulation 1998, 98, 1510-1516.
7. Neubauer, S. Mechanisms of disease - the failing heart - an engine out of fuel. New Engl J Med 2007, 356, 1140-1151.
8. Lane, R.E.; Cowie, M.R.; Chow, A.W.C. Prediction and prevention of sudden cardiac death in heart failure. Heart 2005, 91, 674-680.
9. Curtis, J.P.; Sokol, S.I.; Wang, Y.F.; Rathore, S.S.; Ko, D.T.; Jadbabaie, F.; Portnay, E.L.; Marshalko, S.J.; Radford, M.J.; Krumholz, H.M. The association of left ventricular ejection fraction, mortality, and cause of death in stable outpatients with heart failure. J Am Coll Cardiol 2003, 42, 736-742.
10. Camm, A.J.; Malik, M.; Bigger, J.T.; Breithardt, G.; Cerutti, S.; Cohen, R.J.; Coumel, P.; Fallen, E.L.; Kennedy, H.L.; Kleiger, R.E., et al. Heart rate variability. Standards of measurement, physiological interpretation, and clinical use. European Heart Journal 1996, 17, 354-381.
11. Kleiger, R.E.; Stein, P.K.; Bigger, J.T., Jr. Heart rate variability: Measurement and clinical utility. Ann Noninvasive Electrocardiol 2005, 10, 88-101.
12. Stein, P.K.; Kleiger, R.E. Insights from the study of heart rate variability. Annu Rev Med 1999, 50, 249-261.
13. Stys, A.; Stys, T. Current clinical applications of heart rate variability. Clin Cardiol 1998, 21, 719-724.
14. Shannon, C.E. The mathematical theory of communication (reprinted). M D Comput 1997, 14, 306-317.
15. Pincus, S.M. Approximate entropy as a measure of system-complexity. P Natl Acad Sci USA 1991, 88, 2297-2301.
16. Richman, J.S.; Moorman, J.R. Physiological time-series analysis using approximate entropy and sample entropy. Am J Physiol-Heart C 2000, 278, H2039-H2049.
17. Chen, W.T.; Zhuang, J.; Yu, W.X.; Wang, Z.Z. Measuring complexity using fuzzyen, apen, and sampen. Medical engineering & physics 2009, 31, 61-68.
18. Bandt, C.; Pompe, B. Permutation entropy: A natural complexity measure for time series. Phys Rev Lett 2002, 88.
19. Costa, M.; Goldberger, A.L.; Peng, C.K. Multiscale entropy analysis of complex physiologic time series. Phys Rev Lett 2002, 89.
20. Costa, M.; Goldberger, A.L.; Peng, C.K. Multiscale entropy analysis of biological signals. Phys Rev E 2005, 71.
21. Hsu, C.F.; Wei, S.Y.; Huang, H.P.; Hsu, L.; Chi, S.; Peng, C.K. Entropy of entropy: Measurement of dynamical complexity for biological systems. Entropy-Switz 2017, 19.
22. Peng, C.K.; Costa, M.; Goldberger, A.L. Adaptive data analysis of complex fluctuations in physiologic time series. Adv Adapt Data Anal 2009, 1, 61-70.
23. Goldberger, A.L.; Amaral, L.A.; Hausdorff, J.M.; Ivanov, P.; Peng, C.K.; Stanley, H.E. Fractal dynamics in physiology: Alterations with disease and aging. Proc Natl Acad Sci U S A 2002, 99 Suppl 1, 2466-2472.
24. Goldberger, A.L.; Peng, C.K.; Lipsitz, L.A. What is physiologic complexity and how does it change with aging and disease? Neurobiology of Aging 2002, 23, 23-26.
25. Lipsitz, L.A.; Goldberger, A.L. Loss of complexity and aging - potential applications of fractals and chaos theory to senescence. Jama-J Am Med Assoc 1992, 267, 1806-1809.
26. Pincus, S.M.; Goldberger, A.L. Physiological time-series analysis - what does regularity quantify. Am J Physiol 1994, 266, H1643-H1656.
27. Yu, S.N.; Lee, M.Y. Bispectral analysis and genetic algorithm for congestive heart failure recognition based on heart rate variability. Comput Biol Med 2012, 42, 816-825.
28. Chen, Y.; Yang, H. A comparative analysis of alternative approaches for quantifying nonlinear dynamics in cardiovascular system. Ieee Eng Med Bio 2013, 2599-2602.
29. Hua, Z.C.; Chen, C.; Zhang, R.Q.; Liu, G.Y.; Wen, W.H. Diagnosing various severity levels of congestive heart failure based on long-term hrv signal. Appl Sci-Basel 2019, 9.
30. Narin, A.; Isler, Y.; Ozer, M. Investigating the performance improvement of hrv indices in chf using feature selection methods based on backward elimination and statistical significance. Comput Biol Med 2014, 45, 72-79.
31. Chao, H.H.; Yeh, C.W.; Hsu, C.F.; Hsu, L.; Chi, S. Multiscale entropy analysis with low-dimensional exhaustive search for detecting heart failure. Appl Sci-Basel 2019, 9.
32. Costa, M.; Healey, J.A. Multiscale entropy analysis of complex heart rate dynamics: Discrimination of age and heart failure effects. Comput Cardiol 2003, 30, 705-708.
33. Liu, C.Y.; Gao, R. Multiscale entropy analysis of the differential rr interval time series signal and its application in detecting congestive heart failure. Entropy-Switz 2017, 19.
34. Awan, I.; Aziz, W.; Shah, I.H.; Habib, N.; Alowibdi, J.S.; Saeed, S.; Nadeem, M.S.A.; Shah, S.A.A. Studying the dynamics of interbeat interval time series of healthy and congestive heart failure subjects using scale based symbolic entropy analysis. Plos One 2018, 13.
35. Goldberger, A.L.; Amaral, L.A.N.; Glass, L.; Hausdorff, J.M.; Ivanov, P.C.; Mark, R.G.; Mietus, J.E.; Moody, G.B.; Peng, C.K.; Stanley, H.E. Physiobank, physiotoolkit, and physionet - components of a new research resource for complex physiologic signals. Circulation 2000, 101, E215-E220.
36. Zhao, L.N.; Wei, S.S.; Zhang, C.Q.; Zhang, Y.T.; Jiang, X.G.; Liu, F.; Liu, C.Y. Determination of sample entropy and fuzzy measure entropy parameters for distinguishing congestive heart failure from normal sinus rhythm subjects. Entropy-Switz 2015, 17, 6270-6288.
37. Li, P.; Liu, C.Y.; Li, K.; Zheng, D.C.; Liu, C.C.; Hou, Y.L. Assessing the complexity of short-term heartbeat interval series by distribution entropy. Med Biol Eng Comput 2015, 53, 77-87.
38. Lake, D.E.; Richman, J.S.; Griffin, M.P.; Moorman, J.R. Sample entropy analysis of neonatal heart rate variability. Am J Physiol-Reg I 2002, 283, R789-R797.
連結至畢業學校之論文網頁點我開啟連結
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!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊