近年來全球人口結構持續朝向高齡化情形發展，以及民眾對健康與生活品質之日
趨重視，促成預防醫學的興起，對於需要照護的病患提供醫療照護相關產品或技術的
研究與發展，更是有其重要的意義與利基。針對心血管疾病患者，隨時留意其生理訊
號重要的變化，在病患發生重大病症之前及時提供警訊，能在最短時間內，進行合適
的病症處置或者緊急送醫的程序，對於挽救病患的寶貴生命及減少病症所造成的健康
損害將有極大之助益。
本論文設計了一套整合多種方法的資料探勘發病預測模組，以平台化的方式進行
資料處理分析，同時提供彈性化的擴充架構以便平台結合更多種不同的處理方法。本
研究以心血管疾病的資料作為實驗對象，讓醫生可以藉由此系統，判讀病患的心電圖
狀況，系統再根據病患所登錄的心電圖資訊，結合多種分類器來判定病患是否有異常
發生，進而可早期通知醫生該病患是否可能發生異常狀況。我們以心房早期顫動
(PAF)，長時間ST 型缺血性心臟病(LTST)，與分類病患年齡之資料(Fantasia Database)
多種資料來驗證正確度，經多次實驗結果顯示本系統可達成良好之心電準確率
(E-Precision)與心電涵蓋率(E-Recall)。實驗結果證明本系統相較於現存醫學角度之研
究，提供了不同方法的結果，並成功整合了多種資料探勘方法，同時也能穩定的判定
病患的心電圖異常的可能。
關

In recent years, the structure of global population keeps going towards highly-aged continuously. The development of a medical care system becomes important and meaningful since people paid a lot of attentions on patients. A medical care system is designed to provide alerts before the severe illnesses occurred and necessary procedures could be taken in short time to save one precious life.

In this thesis, we presented a data mining system for patient monitoring with applications on caring the cardiovascular patients. This system was established by integrating various methods into a platform-like architecture with high flexibility. By mining vital signs like ECG, the system could predict possible anomalies so that doctors can be informed to take early actions. The experimental results showed that our proposed system delivered good performance in terms of E-precision and E-recall under different datasets. Our studies showed that this system could integrate different methods and stably predict the anomaly from patients’ ECG data without coding of medical rules as done in other existing approaches.

[1] F. Alonso, J. P. Caraca-Valente, L. Martinez, C.Montes, “Discovering Similar Patterns for Characterizing Time Series in a Medical Domain,” in Proc. of IEEE International Conference on Data Mining, 2001.
[2] E. Bauer, R. Kohavi, ”An Empirical Comparison of Voting Classification Algorithms: Bagging, Boosting, and Variants,” Machine Learning, 1999.
[3] L. Breiman, ” Bagging Predictors,” Machine Learning, 1994.
[4] J. R. Chen, ”Making Subsequence Time Series Clustering Meaningful,” in Proc. of IEEE International Conference on Data Mining, 2005.
[5] E. Frank, M. A. Hall, G. Holmes, R. Kirkby, B. Pfahringer, “Weka - A Machine Learning Workbench for Data Mining,” Springer, 2005.
[6] Y. Freund, R. E. Schapire, “A Decision-theoretic Generalization of On-line Learning and an Application to Boosting,” Computational Learning Theory: Second European Conference, 1995.
[7] N. Friedman, D. Geiger, M. Goldszmidt, ”Bayesian Network Classifiers,” Machine Learning, 1997.
[8] R. Jafari, F. Dabiri, P. Brisk, M. Sarrafzadeh, ”Reconfigurable Fabric Vest for Fatal Heart Disease Prevention,” Embedded Computing,2005.
[9] E. Keogh, J. Lin, W. Truppel, “Clustering of Time Series Subsequences is Meaningless: Implication for Previous and Future Research,” Knowledge and Information Systems, 2005.
[10] P. Langley, E. J. Bowers, J. Wild, M. J. Drinnan, J. Allen, A. Sims, N. Brown, A. Murray, “An Algorithm to Distinguish Ischaemic and Non Ischaemic ST Changes in the Holter ECG,” in Proc. of Computers in Cardiology, 2003.
[11] H. G. Lee, K. Y. Noh, H. K. Park, K. H. Ryu, “Predicting Coronary Artery Disease from Heart Rate Variability Using Classification and Statistical Analysis,” International Conference in Computer and Information Technology, 2007.
[12] F. Y. Lin, S. McClean, “A Data Mining Approach to the Prediction of Corporate Failure,” Knowledge-Based Systems, 2001.
[13] J. N. McNames, A. M. Fraser, “Obstructive Sleep Apnea Classification Based on Spectrogram Patterns in the Electrocardiogram,” in Proc. of Computers in Cardiology, 2000.
[14] T. Nguyen, I. Bass, M. Li, I. K. Sethi, “Investigation of Combining SVM and Decision Tree for Emotion Classification,” in Proc. of IEEE International Symposium on Multimedia, 2005.
[15] T. L. Pao, C. S. Chien, Y. T. Chen, J. H. Yeh, Y. M. Cheng, W. Y. Liao, “Combination of Multiple Classifiers for Improving Emotion Recognition in Mandarin Speech,” Intelligent Information Hiding and Multimedia Signal Processing, 2007.
[16] T. Penzel, J. McNames, A. Murray, P. de Chazal, G. Moody, B. Raymond, ”Systematic Comparison of Different Algorithms for Apnoea Detection Based on Electrocardiogram Recordings,” Medical and Biological Engineering and Computing, 2002.
[17] S. Petrutiu, A. V. Sahakain, J. Ng, S. Swiryn, “Analysis of the Surface Electrocardiogram to Predict Termination of Atrial Fibrillation: The 2004 Computers in Cardiology/PhysioNet Challenge,” in Proc. of Computers in Cardiology, 2004.
[18] R. J. Povinelli, ”Towards the Prediction of Transient ST Changes,” in Proc. of Computers in Cardiology, 2005.
[19] B. Puers, W. Sansen, K. U. Leuven, ”Patient Monitoring Systems,” VLSI and Microelectronic Applications in Intelligent Peripherals and their Interconnection Networks, 1989.
[20] J. R. Quinlan, “Induction of Decision Trees,” Machine Learning, 1986.
[21] J. R. Quinlan, “C4.5: Programs for Machine Learning,” Morgan Kaufmann Publishers, 1993.
[22] T. Thong, “Prediction of Paroxysmal Atrial Fibrillation by Analysis of Atrial Premature Complexes,” in IEEE Transactions on Biomedical Engineering, 2004.
[23] R. Watrous, G. Towell, “A Patient Adaptive Neural Network ECG Patient Monitoring Algorithm,” in Proc. of Computers in Cardiology,1995.
[24] M. Wiggins, A. Saad, B. Litt, G. Vachtsevanos, “Evolving a Bayesian Classifier for ECG-based Age Classification in Medical Applications,” Applied Soft Computing, 2008.
[25] J. G. Wolff, “Medical Diagnosis as Pattern Recognition in a Framework of Information Compression by Multiple Alignment, Unification and Search,” Decision Support Systems, 2005.
[26] M. W. Zimmerman, R. J. Povinelli, ”On Improving the Classification of Myocardial Ischemia Using Holter ECG Data,” in Proc. of Computers in Cardiology, 2004.
[27] W. Zong, R. Mukkamala, R. G. Mark, “A Methodology for Predicting Paroxysmal Atrial Fibrillation Based on ECG Arrhythmia Feature Analysis,” in Proc. of Computers in Cardiology, 2001.
[28] 馬芳資,林我聰, “決策樹形式知識之線上預測系統架構,” Library and Information Science,2003.
[29] Computers in Cardiology Challenge 2001 Top Scores, http://www.physionet.org/challenge/2001/top-scores.shtml
[30] The Long-Term ST Database, http://www.physionet.org/physiobank/database/ltstdb/
[31] Fantasia Database, http://www.physionet.org/physiobank/database/fantasia/
[32] PAF Database, http://www.physionet.org/physiobank/database/afpdb/
[33] PhysioNet, http://www.physionet.org/