Skip navigation

DSpace

機構典藏 DSpace 系統致力於保存各式數位資料(如:文字、圖片、PDF)並使其易於取用。

點此認識 DSpace
DSpace logo
English
中文
  • 瀏覽論文
    • 校院系所
    • 出版年
    • 作者
    • 標題
    • 關鍵字
  • 搜尋 TDR
  • 授權 Q&A
  • 幫助
    • 我的頁面
    • 接受 E-mail 通知
    • 編輯個人資料
  1. NTU Theses and Dissertations Repository
  2. 共同教育中心
  3. 智慧醫療與健康資訊碩士學位學程
請用此 Handle URI 來引用此文件: http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/94926
完整後設資料紀錄
DC 欄位值語言
dc.contributor.advisor林澤zh_TW
dc.contributor.advisorChe Linen
dc.contributor.author曾世傑zh_TW
dc.contributor.authorJefferson Sy Dionisioen
dc.date.accessioned2024-08-21T16:38:50Z-
dc.date.available2025-01-31-
dc.date.copyright2024-08-21-
dc.date.issued2024-
dc.date.submitted2024-08-08-
dc.identifier.citation[1] J. Engdahl, M. Holmberg, B. Karlson, R. Luepker, and J. Herlitz, “The epidemiology of out-of-hospital ‘sudden’cardiac arrest,” Resuscitation, vol. 52, no. 3, pp. 235–245, 2002.
[2] R. Geocadin, M. Buitrago, M. Torbey, N. Chandra-Strobos, M. Williams, and P. Kaplan, “Neurologic prognosis and withdrawal of life support after resuscitation from cardiac arrest,” Neurology, vol. 67, no. 1, pp. 105–108, 2006.
[3] E. Jørgensen and S. Holm, “The natural course of neurological recovery following cardiopulmonary resuscitation,” Resuscitation, vol. 36, no. 2, pp. 111–122, 1998.
[4] J. P. Nolan, C. Sandroni, B. W. Böttiger, A. Cariou, T. Cronberg, H. Friberg, C. Genbrugge, K. Haywood, G. Lilja, V. R. Moulaert et al., “European resuscitation council and European society of intensive care medicine guidelines 2021: post-resuscitation care,” Resuscitation, vol. 161, pp. 220–269, 2021.
[5] P. Sajda, A. Gerson, K.-R. Muller, B. Blankertz, and L. Parra, “A data analysis competition to evaluate machine learning algorithms for use in brain-computer interfaces,” IEEE Transactions on neural systems and rehabilitation engineering, vol. 11, no. 2, pp. 184-185, 2003.
[6] M. M. Ghassemi, B. E. Moody, L.-W. H. Lehman, C. Song, Q. Li, H. Sun, R. G. Mark, M. B. Westover, and G. D. Clifford, “You Snooze, You Win: the Physionet/Computing in Cardiology Challenge 2018,” in 2018 Computing in Cardiology Conference (CinC), vol. 45, 2018, pp. 1–4.
[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, and 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] M. A. Reyna, E. Amorim, R. Sameni, J. Weigle, A. Elola, A. B. Rad, S. Seyedi, H. Kwon, W.-L. Zheng, M. M. Ghassemi et al., “Predicting neurological recovery from coma after cardiac arrest: The George B. Moody Physionet Challenge 2023,” in 2023 Computing in Cardiology (CinC), vol. 50. IEEE, 2023, pp. 1–4.
[9] E. Amorim, W.-L. Zheng, M. M. Ghassemi, M. Aghaeeaval, P. Kandhare, V. Karukonda, J. W. Lee, S. T. Herman, A. Sivaraju, N. Gaspard et al., “The international cardiac arrest research consortium electroencephalography database,” Critical Care Medicine, vol. 51, no. 12, pp. 1802–1811, 2023.
[10] J. E. Wennervirta, M. J. Ermes, S. M. Tiainen, T. K. Salmi, M. S. Hynninen, M. O. Särkelä, M. J. Hynynen, U.-H. Stenman, H. E. Viertiö-Oja, K.-P. Saastamoinen et al., “Hypothermia-treated cardiac arrest patients with good neurological outcome differ early in quantitative variables of EEG suppression and epileptiform activity,” Critical care medicine, vol. 37, no. 8, pp. 2427–2435, 2009.
[11] M. C. Cloostermans, F. B. van Meulen, C. J. Eertman, H. W. Hom, and M. J. van Putten, “Continuous electroencephalography monitoring for early prediction of neurological outcome in postanoxic patients after cardiac arrest: a prospective cohort study,” Critical care medicine, vol. 40, no. 10, pp. 2867–2875, 2012.
[12] L. R. Robinson, P. J. Micklesen, D. L. Tirschwell, and H. L. Lew, “Predictive value of somatosensory evoked potentials for awakening from coma,” Critical care medicine, vol. 31, no. 3, pp. 960–967, 2003.
[13] W.-L. Zheng, E. Amorim, J. Jing, O. Wu, M. Ghassemi, J. W. Lee, A. Sivaraju, T. Pang, S. T. Herman, N. Gaspard et al., “Predicting neurological outcome from electroencephalogram dynamics in comatose patients after cardiac arrest with deep learning,” IEEE transactions on biomedical engineering, vol. 69, no. 5, pp. 1813–1825, 2021.
[14] Y. Du, Y. Xu, X. Wang, L. Liu, and P. Ma, “EEG temporal–spatial transformer for person identification,” Scientific Reports, vol. 12, no. 1, p. 14378, 2022.
[15] J. Yan, J. Li, H. Xu, Y. Yu, and T. Xu, “Seizure prediction based on transformer using scalp electroencephalogram,” Applied Sciences, vol. 12, no. 9, p. 4158, 2022.
[16] J.-Y. Guo, Q. Cai, J.-P. An, P.-Y. Chen, C. Ma, J.-H. Wan, and Z.-K. Gao, “A transformer based neural network for emotion recognition and visualizations of crucial EEG channels,” Physica A: Statistical Mechanics and its Applications, vol. 603, p. 127700, 2022.
[17] M. Zeynali, H. Seyedarabi, and R. Afrouzian, “Classification of EEG signals using Transformer based deep learning and ensemble models,” Biomedical Signal Processing and Control, vol. 86, p. 105130, 2023.
[18] S. Lee, X. Zhao, K. A. Davis, A. A. Topjian, B. Litt, and N. S. Abend, “Quantitative EEG predicts outcomes in children after cardiac arrest,” Neurology, vol. 92, no. 20, pp. e2329–e2338, 2019.
[19] S. Butterworth et al., “On the theory of filter amplifiers,” Wireless Engineer, vol. 7, no. 6, pp. 536–541, 1930.
[20] M. C. Tjepkema-Cloostermans, C. da Silva Lourenço, B. J. Ruijter, S. C. Tromp, G. Drost, F. H. Kornips, A. Beishuizen, F. H. Bosch, J. Hofmeijer, and M. J. van Putten, “Outcome prediction in postanoxic coma with deep learning,” Critical care medicine, vol. 47, no. 10, pp. 1424–1432, 2019.
[21] S. B. Nagaraj, M. C. Tjepkema-Cloostermans, B. J. Ruijter, J. Hofmeijer, and M. J. van Putten, “The revised Cerebral Recovery Index improves predictions of neurological outcome after cardiac arrest,” Clinical neurophysiology, vol. 129, no. 12, pp. 2557–2566, 2018.
[22] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. u. Kaiser, and I. Polosukhin, “Attention is all you need,” in Advances in Neural Information Processing Systems, I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, Eds., vol. 30. Curran Associates, Inc., 2017.
[23] H. Wu, K. Meng, D. Fan, Z. Zhang, and Q. Liu, “Multistep short-term wind speed forecasting using transformer,” Energy, vol. 261, p. 125231, 2022.
[24] W. Lyu, X. Dong, R. Wong, S. Zheng, K. Abell-Hart, F. Wang, and C. Chen, “A multimodal transformer: Fusing clinical notes with structured EHR data for interpretable in-hospital mortality prediction,” in AMIA Annual Symposium Proceedings, vol. 2022. American Medical Informatics Association, 2022, p. 719.
[25] G. Siddhad, A. Gupta, D. P. Dogra, and P. P. Roy, “Efficacy of transformer networks for classification of EEG data,” Biomedical Signal Processing and Control, vol. 87, p. 105488, 2024.
[26] J. Liu, H. Wu, L. Zhang, and Y. Zhao, “Spatial-temporal transformers for EEG emotion recognition,” in Proceedings of the 6th International Conference on Advances in Artificial Intelligence, 2022, pp. 116–120.
[27] M. Rohr, T. Schilke, L. Willems, C. Reich, S. Dill, G. Güney, and C. H. Antink, “Transformer Network with Time Prior for Predicting Clinical Outcome from EEG of Cardiac Arrest Patients,” in 2023 Computing in Cardiology (CinC), vol. 50. IEEE, 2023, pp. 1–4.
[28] J. Pavlus, K. Pijackova, Z. Koscova, R. Smisek, I. Viscor, V. Travnicek, P. Nejedly, and F. Plesinger, “Using Embedding Extractor and Transformer Encoder for Predicting Neurological Recovery from Coma After Cardiac Arrest,” in 2023 Computing in Cardiology (CinC), vol. 50. IEEE, 2023, pp. 1–4.
[29] J. Dionisio, C. Lin, L.-Y. Lin, and W.-C. Wu, “Predicting Neurological Outcomes of Comatose Cardiac Arrest Patients Using Transformer Neural Networks with EEG Data,” in 2023 Computing in Cardiology (CinC), vol. 50. IEEE, 2023, pp. 1–4.
[30] M. Zabihi, A. C. Zar, P. Grover, and E. S. Rosenthal, “Hyperensemble learning from multimodal biosignals to robustly predict functional outcome after cardiac arrest,” in 2023 Computing in Cardiology (CinC), vol. 50. IEEE, 2023, pp. 1–4.
[31] M. N. Alam, M. I. Ibrahimy, and S. M. A. Motakabber, “Feature extraction of eeg signal by power spectral density for motor imagery based bci,” in 2021 8th International Conference on Computer and Communication Engineering (ICCCE), 2021, pp. 234–237.
[32] C. Kim, J. Sun, D. Liu, Q. Wang, and S. Paek, “An effective feature extraction method by power spectral density of eeg signal for 2-class motor imagery-based bci,” Medical & Biological Engineering & Computing, vol. 56, no. 9, p. 1645–1658, Mar. 2018.
[33] R. Wang, J. Wang, H. Yu, X. Wei, C. Yang, and B. Deng, “Power spectral density and coherence analysis of alzheimer’s eeg,” Cognitive Neurodynamics, vol. 9, no. 3, p. 291–304, Dec. 2014.
[34] O. Dressler, G. Schneider, G. Stockmanns, and E. F. Kochs, “Awareness and the EEG power spectrum: analysis of frequencies,” BJA: British Journal of Anaesthesia, vol. 93, no. 6, pp. 806–809, 09 2004.
[35] T. Hastie, R. Tibshirani, and J. Friedman, The elements of statistical learning: data mining, inference and prediction, 2nd ed. Springer, 2009.
[36] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. MIT Press, 2016.
[37] S. J. Prince, Understanding Deep Learning. The MIT Press, 2023.
[38] V. Nair and G. E. Hinton, “Rectified linear units improve restricted boltzmann machines,” in Proceedings of the 27th International Conference on Machine Learning, ser. ICML’10. Madison, WI, USA: Omnipress, 2010, p. 807–814.
[39] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Dropout: a simple way to prevent neural networks from overfitting,” The journal of machine learning research, vol. 15, no. 1, pp. 1929–1958, 2014.
[40] S. Ioffe and C. Szegedy, “Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift,” in Proceedings of the 32nd International Conference on Machine Learning, ser. Proceedings of Machine Learning Research, F. Bach and D. Blei, Eds., vol. 37. Lille, France: PMLR, 07–09 Jul 2015, pp. 448–456.
[41] J. L. Ba, J. R. Kiros, and G. E. Hinton, “Layer normalization,” arXiv preprint arXiv:1607.06450, 2016.
[42] I. Sutskever, O. Vinyals, and Q. V. Le, “Sequence to sequence learning with neural networks,” Advances in neural information processing systems, vol. 27, 2014.
[43] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770–778.
[44] A. P. Bradley, “The use of the area under the ROC curve in the evaluation of machine learning algorithms,” Pattern Recognition, vol. 30, no. 7, pp. 1145–1159, 1997.
[45] K. Boyd, K. H. Eng, and C. D. Page, “Area under the Precision-Recall Curve: Point Estimates and Confidence Intervals,” in Machine Learning and Knowledge Discovery in Databases, H. Blockeel, K. Kersting, S. Nijssen, and F. Železný, Eds. Berlin, Heidelberg: Springer Berlin Heidelberg, 2013, pp. 451–466.
[46] Z. C. Lipton, C. Elkan, and B. Naryanaswamy, “Optimal Thresholding of Classifiers to Maximize F1 Measure,” in Machine Learning and Knowledge Discovery in Databases, T. Calders, F. Esposito, E. Hüllermeier, and R. Meo, Eds. Berlin, Heidelberg: Springer Berlin Heidelberg, 2014, pp. 225–239.
[47] B. Jennett and M. Bond, “Assessment of outcome after severe brain damage: a practical scale,” The Lancet, vol. 305, no. 7905, pp. 480–484, 1975.
[48] L.-T. Ho, B. M. F. Serafico, C.-E. Hsu, Z.-W. Chen, T.-Y. Lin, C. Lin, L.-Y. Lin, M.-T. Lo, and K.-L. Chien, “Preserved Electroencephalogram Power and Global Synchronization Predict Better Neurological Outcome in Sudden Cardiac Arrest Survivors,” Frontiers in Physiology, vol. 13, p. 866844, 2022.
[49] J. Hofmeijer, T. M. Beernink, F. H. Bosch, A. Beishuizen, M. C. Tjepkema-Cloostermans, and M. J. van Putten, “Early EEG contributes to multimodal outcome prediction of postanoxic coma,” Neurology, vol. 85, no. 2, pp. 137–143, 2015.
[50] B. J. Ruijter, M. C. Tjepkema-Cloostermans, S. C. Tromp, W. M. van den Bergh, N. A. Foudraine, F. H. Kornips, G. Drost, E. Scholten, F. H. Bosch, A. Beishuizen et al., “Early electroencephalography for outcome prediction of postanoxic coma: a prospective cohort study,” Annals of neurology, vol. 86, no. 2, pp. 203–214, 2019.
[51] L. Sondag, B. J. Ruijter, M. C. Tjepkema-Cloostermans, A. Beishuizen, F. H. Bosch, J. A. van Til, M. J. van Putten, and J. Hofmeijer, “Early EEG for outcome prediction of postanoxic coma: prospective cohort study with cost-minimization analysis,” Critical care, vol. 21, pp. 1–8, 2017.
[52] A. Gramfort, M. Luessi, E. Larson, D. A. Engemann, D. Strohmeier, C. Brodbeck, R. Goj, M. Jas, T. Brooks, L. Parkkonen, and M. S. Hämäläinen, “MEG and EEG data analysis with MNE-Python,” Frontiers in Neuroscience, vol. 7, no. 267, pp. 1–13, 2013.
[53] A. V. Oppenheim, A. S. Willsky, and S. H. Nawab, Signals & systems (2nd ed.). USA: Prentice-Hall, Inc., 1996.
[54] C. E. Shannon, “A mathematical theory of communication,” The Bell System Technical Journal, vol. 27, no. 3, pp. 379–423, 1948.
[55] P. Welch, “The use of fast Fourier transform for the estimation of power spectra: a method based on time averaging over short, modified periodograms,” IEEE Transactions on audio and electroacoustics, vol. 15, no. 2, pp. 70–73, 1967.
[56] D. Yao, “A method to standardize a reference of scalp EEG recordings to a point at infinity,” Physiological Measurement, vol. 22, no. 4, p. 693–711, Oct. 2001.
[57] A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison, A. Kopf, E. Yang, Z. DeVito, M. Raison, A. Tejani, S. Chilamkurthy, B. Steiner, L. Fang, J. Bai, and S. Chintala, “Pytorch: An imperative style, high-performance deep learning library,” in Advances in Neural Information Processing Systems, H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alché-Buc, E. Fox, and R. Garnett, Eds., vol. 32. Curran Associates, Inc., 2019.
[58] C. R. Harris, K. J. Millman, S. J. van der Walt, R. Gommers, P. Virtanen, D. Cournapeau, E. Wieser, J. Taylor, S. Berg, N. J. Smith, R. Kern, M. Picus, S. Hoyer, M. H. van Kerkwijk, M. Brett, A. Haldane, J. F. del Río, M. Wiebe, P. Peterson, P. Gérard-Marchant, K. Sheppard, T. Reddy, W. Weckesser, H. Abbasi, C. Gohlke, and T. E. Oliphant, “Array programming with NumPy,” Nature, vol. 585, no. 7825, pp. 357–362, Sep. 2020.
[59] A. Maćkiewicz and W. Ratajczak, “Principal components analysis (PCA),” Computers & Geosciences, vol. 19, no. 3, pp. 303–342, 1993.
[60] P. Comon, “Independent component analysis, A new concept?” Signal Processing, vol. 36, no. 3, pp. 287–314, 1994, higher Order Statistics.
[61] I. Daubechies, “The wavelet transform, time-frequency localization and signal analysis,” IEEE Transactions on Information Theory, vol. 36, no. 5, pp. 961–1005, 1990.
[62] Y. Zou, V. Nathan, and R. Jafari, “Automatic Identification of Artifact-Related Independent Components for Artifact Removal in EEG Recordings,” IEEE Journal of Biomedical and Health Informatics, vol. 20, no. 1, pp. 73–81, 2016.
[63] I. Winkler, S. Haufe, and M. Tangermann, “Automatic Classification of Artifactual ICA-Components for Artifact Removal in EEG Signals,” Behavioral and Brain Functions, vol. 7, no. 1, p. 30, 2011.
[64] J. Gao, Y. Yang, J. Sun, and G. Yu, “Automatic Removal of Various Artifacts From EEG Signals Using Combined Methods,” Journal of Clinical Neurophysiology, vol. 27, no. 5, p. 312–320, Oct. 2010.
[65] Y. Ma, Y. Song, and F. Gao, “A novel hybrid CNN-Transformer model for EEG Motor Imagery classification,” in 2022 International Joint Conference on Neural Networks (IJCNN), 2022, pp. 1–8.
[66] H. Dose, J. S. Møller, H. K. Iversen, and S. Puthusserypady, “An end-to-end deep learning approach to MI-EEG signal classification for bcis,” Expert Systems with Applications, vol. 114, p. 532–542, Dec. 2018.
[67] Z. Wan, M. Li, S. Liu, J. Huang, H. Tan, and W. Duan, “EEGformer: A transformer–based brain activity classification method using EEG signal,” Frontiers in Neuroscience, vol. 17, Mar. 2023.
[68] W. Y. Peh, P. Thangavel, Y. Yao, J. Thomas, Y.-L. Tan, and J. Dauwels, “Six-Center Assessment of CNN-Transformer with Belief Matching Loss for Patient-Independent Seizure Detection in EEG,” International Journal of Neural Systems, vol. 33, no. 03, p. 2350012, 2023.
-
dc.identifier.urihttp://tdr.lib.ntu.edu.tw/jspui/handle/123456789/94926-
dc.description.abstract突發性心臟驟停(SCA)患者通常因缺氧時間過長而陷入昏迷,醫師需提供神經系統預後,協助臨床決策。本研究旨在利用早期腦電圖(EEG)數據訓練Transformer模型,預測SCA昏迷患者的神經系統預後。Transformer模型利用自注意力機制從長序列中學習模式。我們利用完整的小時級EEG序列,將其分割為5分鐘的時段,使模型能夠捕捉長距離的時間序列模式。通過將每個EEG序列視為訓練樣本,我們增加了數據樣本量,提高了模型學習特定記錄模式的能力。預測結果按患者進行了整合評估。專注於EEG數據的模型展現出了良好的預測性能,在保留測試集上的AUROC為0.82,AUPRC為0.90,在外部測試集上的AUROC為0.73,AUPRC為0.93。本研究凸顯了注意力機制在識別EEG序列中時間模式方面的潛力,提升了對SCA患者預後的能力。zh_TW
dc.description.abstractSurviving sudden cardiac arrest (SCA) patients often remain in a coma due to a prolonged lack of oxygen, requiring physicians to provide prognoses on neurological outcomes to aid in clinical decisions. This study aims to predict neurological outcomes in SCA coma patients using early electroencephalogram (EEG) data to train a Transformer model, which leverages self-attention to learn patterns from lengthy sequences. We utilized full hours of EEG sequences, subdividing them into 5-minute epochs, allowing the model to capture long-distance time series patterns. By treating each individual EEG sequence as a training sample, we increased our data sample size and improved the model's ability to learn recording-specific patterns. Predictions were aggregated for patient-wise evaluation. Focusing exclusively on EEG data, our model demonstrated promising predictive performance, with an AUROC of 0.82 and an AUPRC of 0.90 on the holdout test set, and an AUROC of 0.73 and an AUPRC of 0.93 on an external test set. This study underscores the potential of attention mechanisms to discern temporal patterns in EEG sequences, enhancing SCA patient prognosis.en
dc.description.provenanceSubmitted by admin ntu (admin@lib.ntu.edu.tw) on 2024-08-21T16:38:49Z
No. of bitstreams: 0
en
dc.description.provenanceMade available in DSpace on 2024-08-21T16:38:50Z (GMT). No. of bitstreams: 0en
dc.description.tableofcontents誌謝 ii
Acknowledgements iii
摘要 iv
Abstract v
Contents vii
List of Figures x
List of Tables xiii
Abbreviation xiv
Chapter 1 Introduction 1
1.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.2 Related Works . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
1.3 Problem Statement . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
1.4 Objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
1.5 Thesis Organization . . . . . . . . . . . . . . . . . . . . . . . . . . 9
Chapter 2 Background 10
2.1 Deep Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10
2.1.1 Machine Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . 10
2.1.2 Deep Neural Networks . . . . . . . . . . . . . . . . . . . . . . . . 11
2.1.3 Activation Function . . . . . . . . . . . . . . . . . . . . . . . . . . 14
2.1.4 Regularizer . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
2.2 The Transformer Model . . . . . . . . . . . . . . . . . . . . . . . . 15
2.3 Evaluation Metrics . . . . . . . . . . . . . . . . . . . . . . . . . . . 21
2.4 Model Selection . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23
2.5 PhysioNet Challenge 2023 Dataset . . . . . . . . . . . . . . . . . . . 23
2.6 NTUH Dataset . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28
Chapter 3 Methods 30
3.1 Study Design . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30
3.2 Signal Processing and Feature Extraction . . . . . . . . . . . . . . . 34
3.3 Preparation of EEG Time-Series Data . . . . . . . . . . . . . . . . . 37
3.4 Model Training . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39
3.5 Experimental Setup . . . . . . . . . . . . . . . . . . . . . . . . . . . 43
Chapter 4 Results and Discussions 45
4.1 Experiments Using 80% Training Set . . . . . . . . . . . . . . . . . 45
4.1.1 Main Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 45
4.1.2 Model Evaluation at Different Hour Windows . . . . . . . . . . . . 47
4.1.3 Model Evaluation per Hospital . . . . . . . . . . . . . . . . . . . . 49
4.2 Recording-wise vs. Patient-wise Samples . . . . . . . . . . . . . . . 51
4.3 Full Hour vs. 5-minute EEG Samples . . . . . . . . . . . . . . . . . 52
4.4 Ablation Study with Pooling Layer . . . . . . . . . . . . . . . . . . 54
4.5 Training with Entire PhysioNet Dataset . . . . . . . . . . . . . . . . 56
4.5.1 Evaluation with NTUH Dataset . . . . . . . . . . . . . . . . . . . . 56
4.5.2 Baseline Comparisons . . . . . . . . . . . . . . . . . . . . . . . . . 60
4.6 Visualizing the Model . . . . . . . . . . . . . . . . . . . . . . . . . 62
4.7 Analyzing Patient-wise EEG . . . . . . . . . . . . . . . . . . . . . . 67
4.8 Limitations . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 68
Chapter 5 Conclusion 73
Ethics Statement 75
Bibliography 76
-
dc.language.isoen-
dc.title注意力深度學習方法應用於時間序列腦電波圖針對心跳停止後腦神經損傷的預後預測zh_TW
dc.titleAn Attention-Based Deep Learning Approach of Using Time-Series EEG for Predicting Neurological Outcomes in Cardiac Arresten
dc.typeThesis-
dc.date.schoolyear112-2-
dc.description.degree碩士-
dc.contributor.oralexamcommittee林亮宇;田中聰久;劉子毓;曹昱zh_TW
dc.contributor.oralexamcommitteeLian-Yu Lin;Toshihisa Tanaka;Joyce Tzu-Yu Liu;Yu Tsaoen
dc.subject.keyword腦電圖分類,心臟驟停,多頭注意力機制,結果預測,時間序列數據,變壓器,zh_TW
dc.subject.keywordEEG classification,cardiac arrest,multi-head attention,outcome prediction,time series data,Transformer,en
dc.relation.page86-
dc.identifier.doi10.6342/NTU202403906-
dc.rights.note同意授權(全球公開)-
dc.date.accepted2024-08-12-
dc.contributor.author-college共同教育中心-
dc.contributor.author-dept智慧醫療與健康資訊碩士學位學程-
dc.date.embargo-lift2025-01-31-
顯示於系所單位:智慧醫療與健康資訊碩士學位學程

文件中的檔案:
檔案 大小格式 
ntu-112-2.pdf8.64 MBAdobe PDF檢視/開啟
顯示文件簡單紀錄


系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。

社群連結
聯絡資訊
10617臺北市大安區羅斯福路四段1號
No.1 Sec.4, Roosevelt Rd., Taipei, Taiwan, R.O.C. 106
Tel: (02)33662353
Email: ntuetds@ntu.edu.tw
意見箱
相關連結
館藏目錄
國內圖書館整合查詢 MetaCat
臺大學術典藏 NTU Scholars
臺大圖書館數位典藏館
本站聲明
© NTU Library All Rights Reserved