The data warehouse enables users to discover knowledge hidden in the massive amounts. In the modern business, data warehousing has now become a key tool for competitive advantages. Healthcare organizations should certainly also benefit by data warehousing, including better administration, higher quality healthcare, effective cost control and great potential in biomedical research and education. Since current healthcare operational systems are not suitable for knowledge exploitation. Data warehousing provides an attractive method for solving these problems, but the process is very complicated. This study presents a methodology for effectively implementing a healthcare data warehouse, which describes general design principles and system architecture, and illustrate a data warehouse system established for surgical research.
The proposed strategy for the development of a healthcare data warehouse is basing on the methodologies of “rapid prototyping; (RP)” and “classification and regression tree; (CART).” RP is for overcoming the current development problems and effectively facilitates the development progress, and then a prototype system was established in a rapid manner. Afterward, CART provided series data mining analyses, and further modifies the system structure. Finally, the objective system was achieved. Additionally, CART also offered a number of data mining applications, which were for directly evaluate and prove the feasibility of the resulting system.
Our results clearly demonstrate the potential for the proposed strategy in the successful establishment of a healthcare data warehouse. The strategy can be modified and expanded to provide new services or support new application domains. The design patterns and modular architecture used in the framework will be useful in solving problems in different healthcare domains.

The data warehouse enables users to discover knowledge hidden in the massive amounts. In the modern business, data warehousing has now become a key tool for competitive advantages. Healthcare organizations should certainly also benefit by data warehousing, including better administration, higher quality healthcare, effective cost control and great potential in biomedical research and education. Since current healthcare operational systems are not suitable for knowledge exploitation. Data warehousing provides an attractive method for solving these problems, but the process is very complicated. This study presents a methodology for effectively implementing a healthcare data warehouse, which describes general design principles and system architecture, and illustrate a data warehouse system established for surgical research.
The proposed strategy for the development of a healthcare data warehouse is basing on the methodologies of “rapid prototyping; (RP)” and “classification and regression tree; (CART).” RP is for overcoming the current development problems and effectively facilitates the development progress, and then a prototype system was established in a rapid manner. Afterward, CART provided series data mining analyses, and further modifies the system structure. Finally, the objective system was achieved. Additionally, CART also offered a number of data mining applications, which were for directly evaluate and prove the feasibility of the resulting system.
Our results clearly demonstrate the potential for the proposed strategy in the successful establishment of a healthcare data warehouse. The strategy can be modified and expanded to provide new services or support new application domains. The design patterns and modular architecture used in the framework will be useful in solving problems in different healthcare domains.

ACKNOWLEDGEMENT I
ABSTRACT II
TABLE OF CONTENTS III
LIST OF FIGURES V
LIST OF TABLES VI
CHAPTER 1 INTRODUCTION 1
1.1 The brief of data warehouse 1
1.2 Problem description 2
1.3 Research objective 4
1.4 Dissertation outline 5
CHAPTER 2 RELATED WORK 6
2.1 General data warehousing 6
2.2 General data mining 8
2.3 Healthcare data warehousing 10
2.4 Healthcare data mining 12
CHAPTER 3 METHODOLOGY 14
3.1 The proposed strategy 14
3.2 The RP methodology 14
3.2.1 Conventional methodology 14
3.2.2 RP method 17
3.2.3 RP on healthcare data warehousing 20
3.3 The CART methodology 21
3.3.1 Classification and regression tree 21
3.3.2 Splitting criteria 22
3.3.3 Surrogate split 24
3.3.4 Classification quality 25
3.3.5 CART on healthcare data mining 26
CHAPTER 4 WAREHOUSING PROJECT DEFINITION 28
4.1 Warehousing objective 28
4.2 Development environment 28
4.2.1 Hardware and software environments 29
4.2.2 Users and participants 29
4.3 Prototype property 29
4.4 Tools selection 29
Chapter 5 SYSTEM PROTOTYPING 32
5.1 Workflow 32
5.1.1 Target data 33
5.1.2 Data locations 33
5.2 Warehouse architecture 34
5.2.1 Data source systems 34
5.2.2 Data preparation database 36
5.2.3 Data warehouse 37
5.3 User interface 37
CHAPTER 6 DATA MINING DEMONSTRATION 39
6.1 Prototype system modification 39
6.1.1 Target data analysis 39
6.1.2 Data structure modification 41
6.2 Data mining applications 41
6.2.1 Colorectal cancer staging 42
6.2.2 CART Settings 43
6.2.3 Mining results 44
6.2.4 Prediction model development 48
CHAPTER 7 DISCUSSION 51
7.1 Introduction to the problems 51
7.2 Validity 51
7.2.1 RP Validity 52
7.2.2 CART Validity 53
7.2.3 System validity 54
CHAPTER 8 CONCLUSIONS 55
8.1 Future directions 55
8.2 Final conclusions 55
REFERENCES 57
APPENDIXA GUI LAYOUT 62
APPENDIX B DATA ATTRIBUTE STATISTIC 64
APPENDIX C TARGET DATA 83

1. Adhikari, Richard, “Migrating legacy data,” Software Magazine, vol. 16, no. 1, pp.75 - 80, Jan., 1996.
2. Kador, John, “One on one,” Midrange Systems, vol. 8, no. 20, pp. 17, Oct. 1995.
3. Hackathorn, Richard, “Data warehouse energizes your enterprise,” Datamation, vol. 41, no. 2, pp. 38-45, Feb. 1995.
4. Francett, Barbara, “Decisions, decisions: Users take stock of data warehouse shelves,” Software Magazine, vol. 14, no. 8, pp. 63 - 70, Aug 1994.
5. Parsons, Michael, “IS leads RDBMS venders to warehouse,” InfoWorld, vol. 17, no. 27, pp. 25, Jul. 1995.
6. White, Colin, “Data delivery,” Network World, vol. 12, no. 20, pp. 39 - 42, May 1995.
7. Carol Walter, “Scalable data warehousing on Microsoft Windows 2000?” A whitepaper from Teradata Inc., Feb. 2001.
8. “Data warehousing for healthcare: the greatest weapon in your competitive arsenal,” A whitepaper from Sybase, Inc., 2000.
9. Mehnaz Farishta, “Data mining for successful healthcare organizations,” A whitepaper from The Shams Group, Inc., 2002.
10. Young ST, Chang JS, “Implementation of a patient-centred and physician-oriented healthcare information system,” Med Inform (Lond), vol. 22, pp. 207—214, 1997.
11. Graves C, Scott M, Benkovich M, et al., “Professional SQL server 2000 data warehousing with analysis services,” Wrox Press, Birmingham, UK, 2001.
12. Srivastava J, Chen PY, “Warehouse creation ― a potential roadblock to data warehousing,” IEEE Trans Knowl Data Eng, vol. 11, pp. 118—126, 1999.
13. Sakaguchi T, Frolick MN, “A review of the data warehousing literature,” J Data Warehousing, vol. 2, pp. 34—54, 1997.
14. Wong ST, Hoo KS Jr, Knowlton RC, et al., “Design and applications of a multimodality image data warehouse framework,” J Am Med Inform Assoc, vol. 9, pp. 239—254, 2002.
15. Breen C, Rodrigues LM, “Implementing a data warehouse at Inglis Innovative Services,” J Healthc Inf Manag, vol. 15, pp. 87—97, 2001.
16. Shams K, Farishta M, “Data warehousing: toward knowledge management,” Top Health Inf Manage, vol. 21, pp. 24—32, 2001.
17. Stead WW, Miller RA, Musen MA, Hersh WR, “Integration and beyond: linking information from disparate sources and into workflow,” J Am Med Inform Assoc, vol. 7, pp. 135—145, 2000.
18. Silver M, Sakata T, Su HC, et al., “Case study: how to apply data mining techniques in a healthcare data warehouse,”" J Healthc Inf Manag, vol. 15, pp. 155—164, 2001.
19. Junger A, Benson M, Quinzio L, et al., “An anesthesia information management system (AIMS) as a tool for controlling resource management of operating rooms,” Methods Inf Med, vol. 41, pp. 81—85, 2002.
20. van der Lei J, “Closing the loop between clinical practice, research, and education: the potential of electronic patient records,” Methods Inf Med, vol. 41, pp. 51—54, 2002.
21. Frank McGuff, “The evolution of data warehousing and analytical applications,” A white paper from Telos Solutions, Inc., 2002.
22. Gray, Paul, Watson, Hugh J., “The new DSS: Data warehouses, OLAP, MDD, and KDD,” Proceedings of the Americas Conference on Information Systems, pp. 917-919, Aug. 1996.
23. Babcock, Charles, “Slice, dice & deliver,” Computerworld, vol. 29, no. 46, pp. 129 -132, Nov. 1995.
24. Gerri Furlow, “The Case for Building a Data Warehouse,” IT Pro, vol. 3, no. 4, pp. 31-34, Jul.-Aug. 2001.
25. Kristin B. DeGruy, “Healthcare applications of knowledge discovery in databases,” journal of healthcare information management, vol. 14, no. 2, pp 59-69, 2000.
26. Harding, Elizabeth U., “Parallel technology meets the warehouse,” Software Magazine, vol. 14, no. 11, pp. 19 - 20, Nov. 1994.
27. Hildebrand, Carol, “Form follows function,” CIO, vol. 9, no. 3, pp. 41-52, Nov. 1995.
28. Mark W. Isken, Steven J. Littig, Mark West, “A data mart for operations analysis,” journal of healthcare information management, vol. 15, no. 2, pp. 143-153, 2001.
29. Fayyad UM, “Advances in knowledge discovery and data mining,” Menlo Park, CA: AAAI Press: MIT Press, 1996.
30. “DataMines for DataWarehouses,” A whitepaper from Information discovery Inc., 2000.
31. Joseph L. Breault, Colin R. Goodall, Peter J. Fos, “Data mining a diabetic data warehouse,” Artificial Intelligence in Medicine, vol. 26, no. 1-2, pp. 37-54, 2002.
32. Son Dao, Brad Perry, “Applying a data miner to heterogeneous schema integration.” First International Conference on Knowledge Discovery and Data Mining (KDD''95), August 1995.
33. M. Ganesh, Eui-Hong (Sam) Hany, Vipin Kumar, Shashi Shekhar, Jaideep Srivastava, “Visual data mining─framework and algorithm development,” Technical Report 96-021, Dept. of Computer & Information Sciences, University of Minnesota.
34. Edward M. Russo, “E-Healthcare data warehousing,” journal of healthcare information management, vol. 15, no. 2, pp. 85-86,2001.
35. Jonathan S. Einbinder, Kenneth W. Scully, Robert D. Pates, Jane R. Schubart, Robert E. Reynolds, “Case study: a data warehouse for an academic medical center,” journal of healthcare information management, vol. 15, no. 2, pp. 165-175, 2001.
36. Saji Salam, “Data warehousing in healthcare,” Express healthcare management, Issue 16-31, Apr. 2001.
37. “The eleventh annual himss leadership survey,” sponsored by IBM, 2000, http://www.himss.org/survey/2000/survey2000.html.
38. Carol Mulder, Mark Mycyk and Andrew Roberts, “Data Warehousing and More,” March 2003 - Healthcare Informatics online. http://www.healthcare-informatics.com/issues/2003/03_03/casereport.htm
39. Lavrac N, Kononenko I, Keravnou E, Kukar M, Zupan B, “Intelligent data analysis for medical diagnosis: using machine learning and temporal abstraction,” AI Communications, vol. 11, pp. 191-218, 1998.
40. Lavrac, N., “Selected techniques for data mining in medicine,” Artificial Intelligence in Medicine, vol. 16, no. 1, pp. 3-23, May 1999.
41. McDonald JM, Brossette S, Moser SA, “Pathology information systems: data mining leads to knowledge discovery,” Arch Pathol Lab Med, vol. 122, pp. 409-411, 1998.
41. Michael Silver, Taiki Sakata, Hua-Ching Su, Charles Herman, Steven B. Dolins, Michael J. O’Shea, “Case study: how to apply data mining techniques in a healthcare data warehouse,” journal of healthcare information management, vol. 15, no. 2, pp. 155-164,2001.
42. American Society for Testing and Materials, “E1340-96 Standard guide for rapid prototyping of computerized systems,” West Conshohocken, PA, pp. 1—11, 1996.
43. W.H. Inmon, R.D. Hackathorn, “Using the Data Warehouse,” John Wiley & Sons, New York, 1994.
44. “SAS rapid warehousing methodology,” A whitepaper from SAS Inc., 2000.
45. Kaplan B, “Culture counts: how institutional values affect computer use,” MD Comput, vol. 17, pp. 23—26, 2000.
46. Breiman, L., Friedman, J. H., Olshen, R. A., & Stone, C. J., “Classification and regression trees,” Belmont, CA: Wadsworth International Group, 1984.
47. Astler VB, Coller FA, “The prognostic significance of direct extension of carcinoma of the colon and rectum,” Ann Surg, vol. 139, pp. 846-851, 1954.
48. “Colon and rectum,” In: American Joint Committee on Cancer: AJCC Cancer Staging Manual. Philadelphia: Lippincott-Raven Publishers, 5th ed, 1997:83.
49. Rosch T, “The new TNM classification in gastroenterology,” Endoscopy, vol. 30, pp. 649-658, 1998.
50. “TNM classification of malignant tumours.International,” Union Against Cancer, 4th ed., Berlin: Springer-Verlag, 1987.
51. “Colon and rectum,” In: Beahrs OH, Henson DE, Hutter RV, Myers MH, eds., Manual for staging of cancer, 3rd ed., Philadelphia: JB Lippincott, American Joint Committee on Cancer, 1988.
52. Hastie, T., Tibshirani, R., & Friedman, J. H., “The elements of statistical learning: data mining, inference, and prediction,” Springer, New York, 2001.
53. Vassilacopoulos G, Chrissikopoulos V, Alexandris N, Tsouroplis A, “Participative HIS development: an approach and a case study,” J Med Syst, vol. 20, pp. 157—165, 1996.
54. Adelhard K, Holzel D, Uberla, K, “Design elements for a computerized patient record,” Methods Inf Med, vol. 38, pp. 187—193, 1999.
55. Kay S, “Towards relevant medical information systems,” Med Inform (Lond), vol. 15, pp. 327—331, 1990.
56. Lorenzi NM, Riley RT, “Managing change: an overview,” J Am Med Inform Assoc, vol. 7, pp. 116—124, 2000.
57. Dugas M, Schauer R, Volk A, Rau H, “Interactive decision support in hepatic surgery,” BMC Med Inform Decis Mak, vol. 2, pp. 5, 2002.
58. Kinzie MB, Cohn WF, Julian MF, Knaus WA, “A user-centered model for web site design: needs assessment, user interface design, and rapid prototyping,” J Am Med Inform Assoc, vol. 9, pp. 320—330, 2002.