在本論文中，是以貝式網路的形式從有時序狀態轉換的工作流程紀錄中去發掘有用的知識。貝式網路是一種利用圖形來表現的模式，此圖形會包含每個相關連的變數的機率值，並且可以很簡單的去合併一個新的資料到貝式網路中，以維持貝式網路的資料始終是最新的。貝式網路的用途很多，它可以用來做預測、溝通、訓練及提供更多的選擇來做更好的決策。在本論文中，我們將會利用我們所提出來的分法應用在血液透析上，透過此方法來表達醫護人員的醫療處理與病患生理狀態轉換的關係，進而去發掘血液透析臨床路徑上的特徵，藉由這些特徵能提供醫護人員去預測病人可能的血液透析臨床路徑，以及血液透析機參數設定的參考。在未來，希望藉由此研究的結果，再加上實證上的研究，使得醫療人員在血液透析的知識管理上能有一個良好的互動結果。

In this thesis, we discover knowledge from workflow logs with temporal-state transitions in the form of Bayesian networks. Bayesian network is a graphical model that encodes probabilistic relationships among variables of interest, and easily incorporates with new instances to maintain rules up to date. The Bayesian networks can predict, communicate, train, and offer more alternatives to make better decisions. We demonstrate the proposed method in representing the causal relationships between medical treatments and transitions of patient’s physiological states in the Hemodialysis process. The discovery of clinical pathway patterns of Hemodialysis can be used for predicting possible paths for an admitted patient, and facilitating medical professionals to control the Hemodialysis machines during the Hemodialysis process. The reciprocal knowledge management can be extended from the results in future research.

致謝詞 I
ABSTRACT II
中文摘要 III
LIST OF FIGURES V
LIST OF TABLES VI
LIST OF TABLES VI
CHAPTER 1 INTRODUCTION 1
CHAPTER 2 LITERATURE REVIEW 3
2.1 THE HEMODIALYSIS 3
2.2 WHY BAYESIAN NETWORK IS CHOSEN 4
2.3 INTRODUCTION TO BAYESIAN NETWORK 5
CHAPTER 3 CONSTRUCTING BAYESIAN NETWORKS WITH TEMPORAL-STATE TRANSITIONS FROM WORKFLOW LOGS 11
3.1 SOME DEFINITIONS FOR CONSTRUCTING BAYESIAN NETWORKS 11
3.2 THE PROCESS OF CONSTRUCTING BAYESIAN NETWORKS WITH TEMPORAL-STATE TRANSITIONS 13
Step 1: Discretizing continuous variables 13
Step 2: Consolidating contiguous similar records 14
Step 3: Defining events and actions 14
Step 4: Specifying distinct states 14
Step 5: Constructing Bayesian networks with temporal-state transitions 14
3.3 INFERENCE IN BAYESIAN NETWORKS 16
3.4 PROPAGATION IN BAYESIAN NETWORKS 16
CHAPTER 4 THE APPLICATION OF BAYESIAN NETWORKS TO DISCOVERING THE CLINICAL PATHWAY PATTERNS OF HEMODIALYSIS 18
4.1 THE MODEL OF APPLYING BAYESIAN NETWORKS TO CLINICAL PATHWAYS OF HEMODIALYSIS 18
4.2 CONSTRUCTING THE CLINICAL PATHWAY PATTERNS OF HEMODIALYSIS USING BAYESIAN NETWORKS 22
4.3 POSSIBLE APPLICABLE SCENARIOS 27
CHAPTER 5 THE EMPIRICAL RESULTS AND DISCUSSIONS 29
5.1 THE GENERALIZATION OF TEMPORAL-STATE TRANSITION PATTERNS IN HEMODIALYSIS 29
5.2 THE PREDICTION OF TEMPORAL-STATE TRANSITIONS IN HEMODIALYSIS 31
5.3 DISCUSSIONS 34
5.3.1 On-site suggestions 35
5.3.2 Facilitating reciprocal learning cycle and organizational knowledge management 36
CHAPTER 6 CONCLUSIONS AND FUTURE RESEARCH 38
REFERENCES 40

Berry, Michael J. A. and Gordon Linoff, “Artificial neural networks,” in Data Mining Techniques: for Marketing, Sales, and Customer Support (Chapter 13), John Wiley & Sons, Inc. 1997.
Buntine, W., “A guide to the literature on learning probabilistic networks from data,” IEEE Transactions on Knowledge and Data Engineering, 8(2):195-210, 1996.
Charniak, “Bayesian networks without tears,” AI Magazine, 12(4):50-63, 1991.
De Dombal F.T., et al. “Computer-aided diagnosis of acute abdominal pain,” British Medical Journal ii: 9-13, 1972.
Heckerman, D., “Bayesian networks for knowledge representation and learning,” Advances in Knowledge Discovery and Data Mining, MIT Press, 1995.
Heckerman, D., “Bayesian networks for data mining,” Data Mining and Knowledge Discovery, 18(6):79-119, 1997.
Heckerman, D. and Shachter, R., “A definition and graphical representation for causality,” Uncertainty in Artificial Intelligence: Proc. Eleventh Conf., Montreal, 1995.
Hornberger J.C., “The Hemodialysis prescription and quality adjusted life expectancy,” J Am Soc Nephrol 4:pp.1004-1020, 1993.
Hornberger J.C., “The Hemodialysis prescription and cost effectiveness,” J Am Soc Nephrol 4: pp.1021-1027,1993.
Jensen, F.V. An Introduction to Bayesian Networks, London: UCL Press Ltd. 1996.
Lin, F.-R.; Chou, S.-C.; Pan, S.-M.; Chen, Y.-M., “Mining time dependency patterns in clinical pathways,” Proceedings of the 33rd Hawaii International Conference on System Sciences, 2000.
National Kidney Foundation, NKF-DOQI, “Clinical Practical Guidelines for Hemodialysis Adequacy,” American Journal of Kidney Diseases, Vol. 30, No 3, Suppl 2, pp.s17-66, September 1997.
Quinlan, J. R., “Induction of decision trees,” Machine Learning, 1: 81-106, 1986.