Please use this identifier to cite or link to this item:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/93252Full metadata record
| ???org.dspace.app.webui.jsptag.ItemTag.dcfield??? | Value | Language |
|---|---|---|
| dc.contributor.advisor | 趙福杉 | zh_TW |
| dc.contributor.advisor | Fu-Shan Jaw | en |
| dc.contributor.author | 黃雅琳 | zh_TW |
| dc.contributor.author | Ya-Lin Huang | en |
| dc.date.accessioned | 2024-07-23T16:30:59Z | - |
| dc.date.available | 2024-07-24 | - |
| dc.date.copyright | 2024-07-23 | - |
| dc.date.issued | 2024 | - |
| dc.date.submitted | 2024-07-18 | - |
| dc.identifier.citation | [1] Wang et al. Contrast everything: A hierarchical contrastive framework for medical time-series. Advances in Neural Information Processing Systems, 36, 2024.
[2] Moridani et al. Heart rate variability as a biomarker for epilepsy seizure prediction. Clin. Study, 3(8):3–8, 2017. [3] van der Kruijs et al. Autonomic nervous system functioning associated with psychogenic nonepileptic seizures: Analysis of heart rate variability. Epilepsy & Behavior, 54:14–19, 2016. [4] Leal et al. Heart rate variability analysis for the identification of the preictal interval in patients with drug-resistant epilepsy. Scientific reports, 11(1):5987, 2021. [5] Bougouin et al. Characteristics and prognosis of sudden cardiac death in greater paris: population-based approach from the paris sudden death expertise center (paris —sdec). Intensive care medicine, 40:846–854, 2014. [6] Nolan et al. Post-cardiac arrest syndrome: epidemiology, pathophysiology, treatment, and prognostication: a scientific statement from the international liaison committee on resuscitation; the american heart association emergency cardiovascular care committee; the council on cardiovascular surgery and anesthesia; the council on cardiopulmonary, perioperative, and critical care; the council on clinical cardiology; the council on stroke. Resuscitation, 79(3):350–379, 2008. [7] Lazzarin et al. Post-cardiac arrest: mechanisms, management, and future perspectives. Journal of Clinical Medicine, 12(1):259, 2022. [8] Stub et al. Post cardiac arrest syndrome: a review of therapeutic strategies. Circulation, 123(13):1428–1435, 2011. [9] Beretta et al. Neurologic outcome of postanoxic refractory status epilepticus after aggressive treatment. Neurology, 91(23):e2153–e2162, 2018. [10] Vidyaratne et al. Real-time epileptic seizure detection using eeg. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 25(11):2146–2156, 2017. [11] Singh et al. Two-layer lstm network-based prediction of epileptic seizures using eeg spectral features. Complex & Intelligent Systems, 8(3):2405–2418, 2022. [12] Myers et al. Heart rate variability measurement in epilepsy: how can we move from research to clinical practice? Epilepsia, 59(12):2169–2178, 2018. [13] Ufongene et al. Electrocardiographic changes associated with epilepsy beyond heart rate and their utilization in future seizure detection and forecasting methods. Clinical Neurophysiology, 131(4):866–879, 2020. [14] Eggleston et al. Ictal tachycardia: the head–heart connection. Seizure, 23(7):496–505, 2014. [15] Bruno et al. Pre-ictal heart rate changes: a systematic review and meta-analysis. Seizure, 55:48–56, 2018. [16] Orrin Devinsky. Effects of seizures on autonomic and cardiovascular function. Epilepsy currents, 4(2):43–46, 2004. [17] Fujiwara et al. Epileptic seizure prediction based on multivariate statistical process control of heart rate variability features. IEEE Transactions on Biomedical Engineering, 63(6):1321–1332, 2015. [18] Billeci et al. Patient-specific seizure prediction based on heart rate variability and recurrence quantification analysis. PloS one, 13(9):e0204339, 2018. [19] Wiklund et al. Abnormal heart rate variability and subtle atrial arrhythmia in patients with familial amyloidotic polyneuropathy. Annals of Noninvasive Electrocardiology, 13(3):249–256, 2008. [20] Lan et al. Intra-inter subject self-supervised learning for multivariate cardiac signals. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 4532–4540, 2022. [21] Lin et al. Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision, pages 2980–2988, 2017. [22] Hochreiter et al. Long short-term memory. Neural computation, 9(8):1735–1780, 1997. [23] Ganin et al. Domain-adversarial training of neural networks. Journal of machine learning research, 17(59):1–35, 2016. [24] Yang et al. Patient-specific approach using data fusion and adversarial training for epileptic seizure prediction. Frontiers in Computational Neuroscience, 17:1172987, 2023. [25] Qi et al. Learning robust features from nonstationary brain signals by multiscale domain adaptation networks for seizure prediction. IEEE Transactions on Cognitive and Developmental Systems, 14(3):1208–1216, 2021. [26] Yuan et al. Ppi: Pretraining brain signal model for patient-independent seizure detection. Advances in Neural Information Processing Systems, 36, 2024. [27] Huang et al. The empirical mode decomposition and the hilbert spectrum for non-linear and non-stationary time series analysis. Proceedings of the Royal Society of London. Series A: mathematical, physical and engineering sciences, 454(1971):903-995, 1998. [28] Wang et al. Automatic epileptic seizure detection in eeg signals using multi-domain feature extraction and nonlinear analysis. Entropy, 19(6):222, 2017. [29] Camm et al. Heart rate variability: standards of measurement, physiological interpretation and clinical use. task force of the european society of cardiology and the north american society of pacing and electrophysiology. Circulation, 93(5):1043–1065, 1996. [30] Pan et al. A real-time qrs detection algorithm. IEEE transactions on biomedical engineering, (3):230–236, 1985. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/93252 | - |
| dc.description.abstract | 院外心跳停止的病患在恢復心跳自主循環後，大多數會出現心跳後停止症候群的症狀，其中以腦損傷引起的癲癇發作最為嚴重，常導致不良的治療結果。為了提高治療效果，需要預測癲癇的發生，以便及時施打抗癲癇藥物。本研究旨在讓病患在加護病房中能夠準確預測癲癇，使用心律變異特徵（Heart Rate Variability, HRV），並開發基於雙向長短期記憶網絡（Bi-LSTM）和領域對抗式學習神經網絡（DANN）的深度學習模型來進行預測。
本研究採用個體獨立型的模型訓練方式，使模型能夠快速預測從未見過的病患，並解決HRV特徵中的個體差異問題。研究結果顯示，模型在測試資料集中的最高精確度可達60%，能夠在癲癇發作前12.5到32.5分鐘進行預測，為醫護人員提供了充足的準備時間。 | zh_TW |
| dc.description.abstract | Patients who experience out-of-hospital cardiac arrest (OHCA) and subsequently regain spontaneous circulation often develop post-cardiac arrest syndrome. Among the various complications, brain injury leading to seizures can result in poor treatment outcomes. To improve these outcomes, it is essential to predict seizures promptly so that antiepileptic medications can be administered in a timely manner. This study aims to accurately predict seizures for patients in intensive care units (ICU) using heart rate variability (HRV) features and developing a deep learning model based on Bi-directional Long Short-Term Memory (Bi-LSTM) and Domain-Adversarial Neural Network (DANN).
This study employs an individual-independent model training approach, allowing the model to quickly predict seizures in previously unseen patients while addressing individual differences in HRV features. The results show that the model achieves a maximum accuracy of 60% on the test dataset and can predict seizures 12.5 to 32.5 minutes before onset, providing sufficient preparation time for healthcare professionals. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2024-07-23T16:30:59Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2024-07-23T16:30:59Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 致謝 i
摘要 ii Abstract iii 目次 iii 圖次 vii 表次 vii 符號列表 ix 第一章 緒論 1 1.1 研究背景 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.1.1 院外心跳停止 (Out-of-hospital cardiac arrest, OHCA) . . . . . . . 1 1.1.2 癲癇及其臨床判斷方式 . . . . . . . . . . . . . . . . . . . . . . . 2 1.1.3 腦電圖 (Electroencephalography,EEG) . . . . . . . . . . . . . . . 2 1.2 癲癇的偵測、預測與其在急診醫學的難題 . . . . . . . . . . . . . . 3 1.2.1 腦電圖在急診醫學上的限制以及解決方案 . . . . . . . . . . . . 3 1.2.2 心律變異特徵與癲癇之間的關聯 . . . . . . . . . . . . . . . . . . 3 1.2.3 心律變異特徵應用於癲癇偵測與預測的研究 . . . . . . . . . . . 4 1.2.4 本實驗室過去的研究 . . . . . . . . . . . . . . . . . . . . . . . . 5 1.3 研究面臨的挑戰以及研究目的 . . . . . . . . . . . . . . . . . . . . . 5 第二章 研究方法與材料 8 2.1 深度學習方法 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 2.1.1 長短期記憶網路 (Long Short-Term Memory, LSTM) . . . . . . . 10 2.2 領域自適應 (Domain adaptation) . . . . . . . . . . . . . . . . . . . . 12 2.2.1 領域對抗式學習神經網路 (Domain-Adversarial Training of Neural Networks, DANN) . . . . . . . . . . . . . . . . . . . . . . . . . 13 2.2.2 領域自適應應用於癲癇偵測與預測的研究 . . . . . . . . . . . . 14 2.3 資料集、資料前處理、資料分析 . . . . . . . . . . . . . . . . . . . . 15 2.3.1 院外心跳停止患者資料集 . . . . . . . . . . . . . . . . . . . . . . 15 2.3.2 腦電圖分析: 初步篩選癲癇事件、標註癲癇起始時間 . . . . . . 16 2.3.2.1 Hilbert-Huang 轉換中的經驗模態分解 (EMD) . . . . 16 2.3.3 近似熵（Approximate Entropy, ApEn） . . . . . . . . . . . . . . 18 2.3.4 標註癲癇事件 . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 2.3.5 心電圖分析: 心律變異特徵 (HRV) 及其分析 . . . . . . . . . . . 20 2.3.5.1 心電圖前處理 . . . . . . . . . . . . . . . . . . . . . . 20 2.3.5.2 HRV 分析: 遞歸圖 (Recurrence plot) . . . . . . . . . 22 2.4 建立模型的實作流程 . . . . . . . . . . . . . . . . . . . . . . . . . . 22 2.4.1 資料集劃分 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22 2.4.2 模型架構、訓練與測試 . . . . . . . . . . . . . . . . . . . . . . . 23 2.4.3 最佳模型選擇與測試 . . . . . . . . . . . . . . . . . . . . . . . . 23 第三章 研究結果 25 3.1 心律不整的癲癇患者對於 HRV 造成的影響 . . . . . . . . . . . . . . 25 3.2 比較不同組別的表現 . . . . . . . . . . . . . . . . . . . . . . . . . . 26 3.3 測試結果 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28 第四章 討論 31 4.1 模型限制與未來展望 . . . . . . . . . . . . . . . . . . . . . . . . . . 31 4.2 資料集限制 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 32 第五章 結論 33 參考文獻 34 | - |
| dc.language.iso | zh_TW | - |
| dc.subject | 領域自適應 | zh_TW |
| dc.subject | 癲癇預測 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | 心電圖 | zh_TW |
| dc.subject | Domain adaptation | en |
| dc.subject | ECG | en |
| dc.subject | Deep learning | en |
| dc.subject | Seizure prediction | en |
| dc.title | 使用心律變異特徵預測院外心跳停止病人癲癇發作深度學習模型 | zh_TW |
| dc.title | A deep learning model predicting epileptic seizures in out-of-hospital cardiac arrest patients using heart rate variability features | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 112-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.coadvisor | 謝建興;宋之維 | zh_TW |
| dc.contributor.coadvisor | Jiann-Shing Shieh;Chih-Wei Sung | en |
| dc.contributor.oralexamcommittee | 曾乙立;高瑀絜 | zh_TW |
| dc.contributor.oralexamcommittee | Yi-Li Tseng;Yu-Chieh Kao | en |
| dc.subject.keyword | 癲癇預測,領域自適應,心電圖,深度學習, | zh_TW |
| dc.subject.keyword | Seizure prediction,Domain adaptation,ECG,Deep learning, | en |
| dc.relation.page | 37 | - |
| dc.identifier.doi | 10.6342/NTU202401878 | - |
| dc.rights.note | 未授權 | - |
| dc.date.accepted | 2024-07-19 | - |
| dc.contributor.author-college | 工學院 | - |
| dc.contributor.author-dept | 醫學工程學系 | - |
| Appears in Collections: | 醫學工程學研究所 | |
Files in This Item:
| File | Size | Format | |
|---|---|---|---|
| ntu-112-2.pdf Restricted Access | 2.89 MB | Adobe PDF |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.