臺灣博碩士論文加值系統

現今在診斷睡眠呼吸中止症的儀器大多是使用睡眠呼吸多項生理監測儀（Polysomnography, PSG），但是在使用PSG診斷睡眠呼吸中止症，有許多麻煩的因素，比如費用過高(每次約為5000元)、過程繁瑣、睡眠檢查室不足以及過於依賴醫護人力，使睡眠呼吸中止症在診斷上非常麻煩。
本論文將採用血氧飽和度(oxygen saturation)和腦電圖訊訊號來判定是否發生阻塞性睡眠呼吸中止症。使用聖文森大學醫院/都柏林大學學院睡眠呼吸中止症資料庫，並使用特徵擷取、訊號處理技術，透過引入腦電圖來去除清醒時期訊號，本論文使用90秒中值濾波器來當作血氧飽和濃度的基線，分類器選用類神經網路人工智慧演算法來估測呼吸障礙指數AHI的嚴重程度。最後依據血氧濃度變化區分睡眠中止的嚴重程度。

The gold standard for diagnosis of sleep apnea is a formal sleep study established by the polysomnography(PSG). However the high cost and the complex steps of PSG makes a diagnosis of sleep apnea become evenmore difficult. Not to mention the shortage of devices and medical human resources.
In this thesis, we propose a sleep apnea detection algorithm based on ensemble machine learning model. By using only Electroencephalography(EEG) and Oximetry, we can significantly reduce the difficulty of diagnosis and the effort of medical persons. The experimental results show that the performance of our approach is comparable to other past works.

致謝辭 i
摘要 ii
Abstract iii
目錄 iv
圖目錄 vi
表目錄 vii
第一章 緒論 1
1.1 研究動機 1
1.2 研究目的 1
1.3 論文架構 2
第二章 理論背景與相關知識 3
2.1 睡眠呼吸中止症簡介 3
2.1.1 血氧飽和度介紹 4
2.1.2 血氧飽和度量測方法 5
2.1.3 多導睡眠生理儀簡介 6
2.1.4 睡眠呼吸中止症治療方法 7
2.2 相關研究 9
2.3 類神經網路 10
2.4 集成學習 13
2.5 聖文森大學醫院都柏林大學學院睡眠呼吸中止症資料庫 20
第三章 研究方法與架構 22
3.1 實驗架構概述 22
3.2 訓練預測模型 24
3.2.1 資料預處理 24
3.2.2 引入腦電圖訊號去除清醒時期 26
3.2.3 特徵擷取 30
3.2.4 Lempel-Ziv 複雜度 32
3.2.5 血氧基準值 36
3.2.6 類神經網路模型 36
3.3 集成學習模型 38
第四章 實驗結果 41
4.1 評斷標準 41
4.2 實驗結果 43
第五章 結論與未來展望 50
5.1 結論 50
5.2 未來展望 51
參考文獻 52

[1]陳濘宏，阻塞型睡眠呼吸中止症候群，台灣醫學9卷3期，May 2005
[2]Zamarron C., Gude F., Barcala J., Rodriguez J.R., Romero P.V., 2003, “Utility of oxygen saturation and heart rate spectral analysis obtained from pulse oximetric 90 recordings in the diagnosis of sleep apnea syndrome,”
[3]American Academy of Sleep Medicine Task Force Report. “Sleep-related breathing disorders in adults: recommendations for syndrome definition and measurement techniques in clinical research.” Sleep,Vol. 22, no. 5, pp. 667-689, 1999.
[4]Sleep apnea https://en.wikipedia.org/wiki/Sleep_apnea
[5]Ulysses JM, Jacek D, Sateesh V, Azmi D, M. Jeffery M, Ali E, and Brydon J. B. G, 2003, “Prediction of the Apnea-Hypopnea Index From Overnight Pulse Oximetry,” Chest, vol. 124, pp. 1694-1701.
[6]Magalang U.J., Dmochowski J., Veeramachaneni S., Draw A., Mador M.J., EI-Solh A., Grant B.J.B., 2003, “Prediction of the apnea-hypopnea index from overnight pulse oximetry,”
[7]Zamarron C., Romero P.V., Rodriguez J.R., Gude F., 1999, “Oximetry spectral analysis in the diagnosis of obstructive sleep apnea,”
[8]Moody GB, Mark RG, Bump MA, Weinstein JS, Berman AD, Mietus JE, Goldberger AL. Clinical validation of the ECG-derived respiration (EDR) technique. In Computers in Cardiology 1986. Washington, DC: IEEE Computer Society Press, 1987; 507–510.
[9]Magalang U.J., Dmochowski J., Veeramachaneni S., Draw A., Mador M.J., EI-Solh A., Grant B.J.B., 2003, “Prediction of the apnea-hypopnea index from overnight pulse oximetry,”
[10]B. Xie and H. Minn, “Real time sleep apnea detection by classifier combination,” IEEE Transactions on Information Technology in Biomedicine, vol. 15, no. 3, pp. 469-477, May 2012.
[11]B. Koley and D. Dey, “Real-time adaptive apnea and hypopnea event detection methodology for portable sleep apnea monitoring devices,” IEEE Transactions on Biomedical Engineering, Vol. 60 no. 12, pp. 3354-3363, Sep. 2013.
[12]T. Kao, J. Wang, C. Lin, Y. Yang, and F.. Juang, “Using Bootstrap AdaBoost with KNN for ECG-based Automated Obstructive Sleep Apnea Detection,” International Joint Conference on Neural Networks, pp. 1-5, 2012.
[13]P. De Chazal, C. Heneghan, E. Sheridan, R. Reilly, P. Nolan, and M. O’Malley, “Automated processing of the single-lead electrocardiogram for the detection of obstructive sleep apnoea,” IEEE Transactions on Biomedical Engineering, vol. 50, no. 6, pp. 686-696, 2003.
[14]陳志金, “睡眠呼吸中止症候群的診斷與治療”
[15]T.G. Dietterich, “Ensemble Methods in Machine Learning,” Lecture Notes in
Computer Science, Berlin: Springer, pp. 1-15, 2000.
[16]Y. Freund and R.E. Schapire, “A decision-theoretic generalization of on-line
learning and an application to boosting,” Journal of Computer and System
Sciences, vol. 55, pp. 119–139, 1997.
[17]L. Hyafil and R.L. Rivest, “Constructing optimal binary decision trees is NP- complete,” Information Processing Letters , Vol. 5, No. 1, Pages 15–17, May 1976.
[18]L. Breiman, Machine Learning, Vol. 24, No. 2, p. 123-140, 1996.
[19]M. Kearns, “Thoughts on Hypothesis Boosting, ” Machine Learning class
project, December 1988
[20]莊永裕, “整體學習(Ensemble Learning)入門”
[21]St. Vincent’s University Hospital/University College Dublin Sleep ApneaDatabase. http://www.physionet.org/pn3/ucddb/
[22]E. Fornasa, A. Accardo, R. Zotti, A. De Felice, and G. D’Addio, “Relationships between Linear and Nonlinear Indexes of Heart Rate Variability in Obstructive Sleep Apnea Syndrome,” 8th Conference of the European Study Group on Cardiovascular Oscillations, pp 103-104, May 2014.
[23]劉勝義, “臨床睡眠檢查學”
[24]王人鋒, “使用新基線定義與腦波清醒資訊改善血氧濃度特徵對呼吸暫止症的預測”,博士論文,2009
[25]Ruby,Electroencephalogram EEG
[26]Zhang X.S., Roy R.J., and Jensen E.W., 2001, “EEG complexity as a measure of depth of anesthesia for patients,” IEEE Transactions on Biomedical Engineering, Vol.48, No.12, pp.1424-1433.
[27]WEKA(Waikato Environment for Knowledge Analysis)http://www.cs.waikato.ac.nz/ml/weka/
[28]Ayappa I., Rappaport B.S., Norman R.G., Rapoport D.M., 2005, “Immediate consequences of respiratory events in sleep disordered breathing,” Sleep Medicine, Vol.6, pp.123-130.
[29]Polysomnography ,https://en.wikipedia.org/wiki/Polysomnography
[30]H. Al-Angari and A. Sahakian, “Automated Recognition of Obstructive Sleep Apnea Syndrome Using Support Vector Machine Classifier,” IEEE Transactions on Information Technology in Biomedicine, Vol. 16, no. 3, pp. 463-468, 2012.
[31]R. Hornero, D. Alvarez, D. Abasolo, F. del Campo, and C. Zamarron, “Utility of approximate entropy from overnight pulse oximetry data in the diagnosis of the obstructive sleep apnea syndrome,” IEEE Trans. Biomed. Eng., vol. 54, no. 1, pp. 107–113, Jan. 2007.
[32]蘇木春、張孝得，”機器學習：類神經網路、模糊系統以及基因演算法
則”，全華科技圖書股份有限公司出版，1997 年12 月