跳到主要內容

臺灣博碩士論文加值系統

(44.192.94.177) 您好!臺灣時間:2024/07/21 17:37
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:周晉弘
研究生(外文):Chou, Jin-Hong
論文名稱:基於類神經網路之心臟衰竭檢測演算法設計與實作
論文名稱(外文):Design and Implementation of the RNN-based Heart Failure Detection Algorithm
指導教授:趙禧綠趙禧綠引用關係
指導教授(外文):Chao, Hsi-Lu
口試委員:伍紹勳宋思賢莊正彥趙禧綠
口試委員(外文):Wu, Sau-HsuanSung, Shih-HsienChuang, Cheng-YenChao, Hsi-Lu
口試日期:2021-12-23
學位類別:碩士
校院名稱:國立陽明交通大學
系所名稱:資訊科學與工程研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2022
畢業學年度:110
語文別:中文
論文頁數:43
中文關鍵詞:深度學習遷移式學習雙向長短期記憶模型心臟衰竭心電圖
外文關鍵詞:Deep LearningTransfer LearningBi-directional Long Short-Term MemoryHeart FailureElectrocardiography
相關次數:
  • 被引用被引用:0
  • 點閱點閱:187
  • 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
隨著高齡化社會的來臨,心臟衰竭對老年人所造成的死亡率非常高。但 如果有接受完善的治療,心臟衰竭的死亡率可以大幅下降。現今要診斷心臟 衰竭時,主要是透過心臟超音波的量測,但心臟超音波儀器測量一次需要花 費 15 至 20 分鐘的時間,且無法長時間對心肌收縮舒張進行狀態的監測。
本研究目的是想要使用少導極的心電訊號與心臟周圍震動的訊號,並利 用深度學習演算法進行運算,達到長時間的監測心臟衰竭的嚴重程度。因此 我們對成功辨識心臟衰竭病患結果的 Recall 較感興趣。本研究使用的模型 為雙向的長短期記憶模型,不僅考慮正向的時間相關性,還考慮反向的時間 相關性。且使用遷移式學習的方式,來解決資料量不足的問題。最後透過左 心室射血分率來區分病患是否為心臟衰竭。實驗結果顯示平均準確率可達 到 77.5%、特異性(Specificity)達到 76%、召回率(Recall)達到 79%、AUC 達 到 83.7%。而增加性別特徵後準確率與 Recall 也有更加的提升。
With the advent of an aging society, the death rate of heart failure to the elder is very high. But heart failure deaths can be decreased dramatically under a more advanced health treatment. When diagnosing heart failure, it’s mainly through the measurement of cardiac ultrasound. But it takes 15~20 minutes to perform a measurement with a cardiac ultrasound instrument, and it is impossible to monitor the state of myocardial contraction and relaxation for a long time.
The purpose of this research is to use the low-lead ECG signal and the vibration signal around the heart, and calculate the degree of the heart failure through deep learning. Therefore, we are more interested in Recall, which successfully recognizes the results of patients with heart failure. The model used the bi-directional Long Short-Term Memory model in this study, which not only considers the positive time correlation, but also the reverse time correlation. And using transfer learning to solve the problem of insufficient data. Finally, the left ventricular ejection fraction (LVEF) is used to distinguish whether the patient is heart failure. The experimental results show that the average accuracy rate is 77.5%, the specificity is 76%, the recall is 89%, and AUC is 83.7%. After adding ‘sex’ feature, the accuracy and recall are also improved.
摘要............i
Abstract............ii
誌謝............iii
目錄............iv
表目錄............v
圖目錄............vi
第1章 簡介............1
1.1 心電圖............1
1.2 動作感測器............4
1.3 研究動機............5
1.4 相關文獻............7
第2章 系統架構............11
2.1 心電圖裝置............11
2.2 無線心電圖醫療物聯網系統............13
第3章 演算法............16
3.1 問題定義............16
3.2 長短期記憶模型(Long Short-Term Memory, LSTM)............18
3.3 雙向長短期記憶模型(Bi-directional LSTM, BLSTM)............21
3.4 遷移式學習(Transfer Learning)............25
第4章 環境設定與實驗結果............29
4.1 資料來源與前處理............29
4.2 實驗結果............33
4.2.1 Case 1: 以 LVEF 40%區分............34
4.2.2 Case 2: 以 LVEF 50%區分............37
第5章 結論............40
參考文獻............41
[1] H. K. Chiang, C.-W. Chu, G.-Y. Chen, C.-D. Kuo, “A new 3-D display method for 12-lead ECG,” IEEE Transactions on Biomedical Engineering, vol. 48, pp. 1195-1202, Oct. 2001.
[2] S. Barold, “Willem Einthoven and the Birth of Clinical Electrocardiography a Hundred Years Ago,” Cardiac Electrophysiology Review, vol. 7, No. 1, pp. 99-104, Jan. 2003.
[3] H. M. Rai, A. Trivedi, S. Shukla, “ECG signal processing for abnormalities detection using multi-resolution wavelet transform and Artificial Neural Network classifier,” Measurement, vol. 46, no. 9, pp. 3238-3246, Nov. 2013.
[4] B. E. Jin, H. Wulff, J. H. Widdicombe, J. Zheng, D. M. Bers, J. L. Puglisi, “A simple device to illustrate the Einthoven triangle,” Physiology Education, vol. 36, pp. 319-324, Dec. 2012.
[5] C. Yang, N. Tavassolian, “Combined Seismo- and Gyro-Cardiography: A More Comprehensive Evaluation of Heart-Induced Chest Vibrations,” IEEE Journal of Biomedical and Health Informatics, vol. 22, no. 5, pp. 1466-1475, Sep. 2018.
[6] A. Nainwal, Y. Kumar, B. Jha, “Morphological changes in congestive heart failure ECG,” International Conference on Advances in Computing, Communication, & Automation (ICACCA), pp. 1-4, Sep. 2016.
[7] A. L. Goldberger, L. A. Amaral, L. Glass, J. M. Hausdorff, P. C. Ivanov, R. G. Mark, J. E. Mietus, G. B. Moody, C.-K. Peng, H. E. Stanley, “PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals,” Circulation, vol. 101, no. 23, pp. e215-e220, 2000.
[8] D. S. Baim, W. S. Colucci, E. S. Monrad, H. S. Smith, R. F. Wright, A. Lanoue, D. F. Gauthier, B. J. Ransil, W. Grossman, E. Braunwald, “Survival of Patients With Severe Congestive Heart Failure Treated With Oral Milrinone,” Journal of the American College of Cardiology, vol. 7, no. 3, pp. 661-670, Mar. 1986.
[9] G.C.Brooks,E.Vittinghoff,S.Iyer,D.Tandon,P.Kuhar,K.A.Madsen,G. M. Marcus, M. J. Pletcher, J. E. Olgin, “Accuracy and Usability of a Self- Administered 6-Minute Walk Test Smartphone Application,” Circulation: Heart Failure, vol. 8, no. 5, pp. 905-913, Sep. 2015.
[10]O. T. Inan, M. B. Pouyan, A. Q. Javaid, S. Dowling, M. Etemadi, A. Dorier, J. A. Heller, A. O. Bicen, S. Roy, T. D. Marco, L. Klein, “Novel Wearable Seismocardiography and Machine Learning Algorithms Can Assess Clinical Status of Heart Failure Patients,” Circulation: Heart Failure, vol. 11, no. 1, Jan. 2018.
[11]M. J. Tadi, E. Lehtonen, A. Saraste, J. Tuominen, J. Koskinen, M. Teräs, J. Airaksinen, M. Pänkäälä, T. Koivisto, “Gyrocardiography: A New Non- invasive Monitoring Method for the Assessment of Cardiac Mechanics and the Estimation of Hemodynamic Variables,” Scientific Reports, vol. 7, no. 1, Dec. 2017.
[12]Z. Attia, S. Kapa, F. Lopez-Jimenez, P. M. McKie, D. J. Ladewig, G. Satam, P. A. Noseworthy, T. M. Munger, S. J. Asirvatham, C. G. Scott, R. E. Carter, and P. A. Friedman, “Screening for cardiac contractile dysfunction using an artificial intelligence–enabled electrocardiogram,” Nature Medicine, vol. 25, pp. 70-74, Jan. 2019.
[13]B. Bozkurt, A. J. Coats, H. Tsutsui, M. Abdelhamid, S. Adamopoulos, N. Albert, S. D. Anker, J. Atherton, M. Böhm, J. Butler, M. H. Drazner, G. M. Felker, G. Filippatos, G. C. Fonarow, M. Fiuzat, J. Gomez-Mesa, P. Heidenreich, T. Imamura, J. Januzzi, E. A. Jankowska, P. Khazanie, K. Kinugawa, C. S. P. Lam, Y. Matsue, M. Metra, T. Ohtani, M. F. Piepoli, P. Ponikowski, G. M. C. Rosano, Y. Sakata, P. SeferoviĆ, R. C. Starling, J. R. Teerlink, O. Vardeny, K. Yamamoto, C. Yancy, J. Zhang, S. Zieroth, “Universal Definition and Classification of Heart Failure: A Report of the Heart Failure Society of America, Heart Failure Association of the European Society of Cardiology, Japanese Heart Failure Society and Writing Committee of the Universal Definition of Heart Failure,” Journal of cardiac failure, vol. 27, no. 4, pp. 387-413, Mar. 2021.
[14]S. Hochreiter, J. Schmidhuber, “Long short-term memory,” Neural Computataion, vol. 9, no. 8, pp. 1735-1780, Dec.1997.
[15]A. Graves, J. Schmidhuber, “Framewise Phoneme Classification with Bidirectional LSTM Networks,” Neural Networks, vol. 4, no. 5-6, pp. 602- 610, Jul. 2005.
[16]A. Graves, A. Mohamed, G. Hinton, “Speech recognition with deep recurrent neural networks,” IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6645-6649, May 2013.
[17]S. J. Pan, Q. Yang, “A Survey on Transfer Learning,” IEEE Transactions on Knowledge and Data Engineering, vol. 22, no. 10, pp. 1345-1359, Oct. 2010. [18]J. Yosinski, J. Clune, Y. Bengio, H. Lipson, “How transferable are features in deep neural networks? ,” Neural Information Processing Systems, vol. 2,
pp. 3320-3328, Dec 2014.
[19]M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, M. Devin, S.
Ghemawat, G. Irving, M. Isard, M. Kudlur, J. Levenberg, R. Monga, S. Moore, D. G. Murray, B. Steiner, P. Tucker, V. Vasudevan, P. Warden, M. Wicke, Y. Yu, X. Zheng, “TensorFlow: A system for large-scale machine learning,” 12th USENIX Symposium on Operating Systems Design and Implementation, pp. 265-283, 2016.
[20]K. Zou, A. Malley, L. Mauri, “Receiver-operating characteristic analysis for evaluating diagnostic tests and predictive models.” Circulation, vol. 115, no. 5, pp. 654-657, Feb 2007.
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