隨著時代的變遷，資訊化在各領域中已成為必然的趨勢並促進著各產業的技術蓬勃發展。台灣衛生福利部於民國96年起開始「推動實施電子病歷」計畫，由政府擔任推廣的角色，使得全台醫院病歷電子化的程度大幅提升。雖然電子病歷系統已取代以往的紙本病歷紀錄，但醫院內不同科別對於病患的病歷都各自有著不同的需求，往往在新增及查詢病患病歷時耗費了過多的時間與人力，更是難以在龐大的病患病歷資料中，挖掘出符合醫護人員需求並隱藏在病患資料中有用且重要的資訊，若要進行統計與分析，還是需要由醫護人員收集並整理資料，再透過現成套裝軟體進行數據分析，過程相當繁雜且容易出錯，進而影響分析的結果與準確性。同時隨著國人年齡層逐漸的老化以及大眾飲食習慣的改變，罹患血管疾病的人口比例急遽升高，而其中的周邊動脈阻塞性疾病又以高年齡層為主要風險群，因此對於現今社會，此疾病為一不可忽視之疾病，且需長期做追蹤及治療，確保病情不再惡化。因此，本研究的目的為建置一套雲端臨床輔助診斷系統，為醫護人員設計符合周邊動脈阻塞性疾病需求之電子病歷，除去了繁雜且無用的病歷欄位，加強查詢的功能，減少查詢病歷時所耗費過多的時間、程序以及人力，更是增加了直接的分析功能，無需再透過其他軟體，直接使用系統選擇並分析病歷資料，找出隱藏在病歷中的資訊並提供給醫師做為輔助診斷的參考依據。藉此改善醫護人員整體的作業效率、分析正確率、方便度等，且透過無紙電子化，達到友善環境之福祉。

With the change of time, informationization has become an inevitable trend in various fields and promotes the vigorous development of technology in every industry. Taiwan Ministry of Health and Welfare began to promote "the implementation of electronic medical record" plan in 2007, the government assumed the office of promoter role, this make a high increasing rate of using electronic medical record all over Taiwan. Although the electronic medical record has replaced the paper record, the different divisions of hospital have their different needs in patient records, medical staff usually spend too much time and human resource to add or search patient’s medical record, it’s also very hard to find the hidden and usable patient information in such a huge hospital data that match the needs of medical staff. If medical staff is going to count and analyze patient records, they have to collect and sort out the data by themselves, then use the existing Clinical Study Information System(CSIM) to analyze the data, all the processes is miscellaneous and error-prone, these may affect the result and accuracy of the analysis. At the same time, along with the changing of public eating habits and the age group gradually aging, the proportion of people suffering from vascular disease increased sharply, high age group is the main risk group of the peripheral arterial occlusive disease, so for today's society, this disease is a disease that cannot be ignored, and need to do long-term tracking and treatment, ensure that the condition has not deteriorated. Thus, the purpose of this research is to build a Cloud Clinical Diagnostics Aid System, design a database and electronic medical record of peripheral arterial occlusive disease that not only meet the needs of medical staff, but also delete the complicate and useless data fields, strengthen the function of searching patient information to reduce the waste of time and human resource in searching patient records. Also adding the analyze function, no need to use other software, user can select and analyze the medical records by this system to find the hidden and usable information in patient electronic medical records, then provide to the doctors as a reference for diagnosis. To improve the overall efficiency of medical staff, the correct rate of electronic record, the accuracy rate of analysis, convenience, and the change of paperless which can be eco-friendly.

Chapter 1 Introduction...1
        1.1 Background...1
        1.2 Motivation...3
        1.3 Purpose...5
Chapter 2 Literature Review...7
        2.1 Big Data...7
          2.1.1 Concept of Big Data	7
          2.1.2 Applications of Big Data in Medical Field...9
        2.2 Data Mining...11
          2.2.1 Concept of Data Mining...11
          2.2.2 Knowledge Discovery in Databases (KDD)...14
          2.2.3 Applications of Data Mining in Medical Field...17
        2.3 Cloud Computing...24
          2.3.1 Definition and Characteristics of Cloud Computing...24
          2.3.2 Applications of Cloud Computing in Medical Field...26
        2.4 Peripheral Arterial Occlusive Disease (PAOD)...29
          2.4.1 Introduction of Peripheral Arterial Occlusive Disease...29
          2.4.2 Symptoms of Peripheral Arterial Occlusive Disease...29
          2.4.2 Diagnosis methods of Peripheral Arterial Occlusive Disease...30
          2.4.3 Treatment Methods of Peripheral Arterial Occlusive Disease...32
Chapter 3 Research Methods...34
        3.1 Research Process...34
        3.2 System Analysis and Design...36
        3.3 System Development Tools...40
        3.4 Database Design...41
        3.5 Auxiliary of XML...43
        3.6 Knowledge Discovery in Databases (KDD) Process...44
Chapter 4 System Establishment and Analysis Result...47
        4.1 System Establishment...47
        4.2 System Functions...59
          4.2.1 Add/Modify Function...60
          4.2.2 Search Function...63
          4.2.3 Analysis Function...68
          4.2.4 Export Function...75
        4.3 Patient Case Analysis Results...76
          4.3.1 Overall Data Analysis...76
          4.3.2 Pre/Post-op Tracking...89
Chapter 5 Conclusion and Future Perspectives...97
        5.1 Conclusion...97
        5.2 Future Perspective...101
Reference...103



List of Figures
Figure 1. The Flowchart of Knowledge Discovery in Databases...16
Figure 2. The Diagnosis Flowchart of Peripheral Arterial Occlusive Disease...31
Figure 3. Research Flowchart...35
Figure 4. Three-tier Web Architecture...36
Figure 5. Flowchart of User Operation...38
Figure 6. Work Breakdown Structure Figure...39
Figure 7. Database Diagram...42
Figure 8. XML Language...43
Figure 9. Knowledge Discovery in Databases (KDD) Process Steps Figure...46
Figure 10. User Login Interface...48
Figure 11. IsHasData_PAOD Table Design Figure...49
Figure 12. Patient Information System Interface (Partially displayed)...50
Figure 13. General History System Interface...52
Figure 14. Pre-op Evaluation System Interface...53
Figure 15. Op Data System Interface...54
Figure 16. Post-op Data System Interface (Partially displayed)...55
Figure 17. Lab Data System Interface (Pre-op tracking)...58
Figure 18. Peripheral Arterial Occlusive Disease System Architecture Diagram...59
Figure 19. Two Options of Add/Modify Function...60
Figure 20. Add/Modify Function Flowchart...60
Figure 21. Input History Number Manually...61
Figure 22. Input Report Date to Add Medical Record...61
Figure 23. Add Another Medical Record of Patient...61
Figure 24. List All History Numbers (Partially Displayed)...62
Figure 25. Add/Modify Function Interface (Partially Displayed)...62
Figure 26. Searching Function Flowchart...63
Figure 27. Input History Number Manually...64
Figure 28. Select Patient and Report Date...64
Figure 29. Patient Medical Record...64
Figure 30. Choose List All History Numbers Function...65
Figure 31. List All History Numbers...65
Figure 32. Two Times Report Search Function...66
Figure 33. Two Times Report of Patient...66
Figure 34. Condition Search Function...66
Figure 35. Specific Condition Select...67
Figure 36. Report Date Range Search...67
Figure 37. The Result of Report Date Range Search...67
Figure 38. Analysis Function Flowchart...68
Figure 39. The Choices of Overall Data Analysis Function...69
Figure 40. The Data Type of XML-Type 1(Value)...69
Figure 41. Select Analysis Condition Interface...70
Figure 42. Input the Content of Condition...70
Figure 43. Select the Data...70
Figure 44. Generate/Update Chart Interface...71
Figure 45. The Data Type of XML-Type 2 or Type 3 (Option)...71
Figure 46. The Choices of Pre/Post-Op Tracking...72
Figure 47. The Result of Searching Patient Records...72
Figure 48. Individual Patient Analysis Interface...73
Figure 49. Overall Patient Analysis Interface...73
Figure 50. Overall Patient-Condition Analysis Interface (Select Condition)...74
Figure 51. Overall Patient-Condition Analysis Interface (Enter the Content)...74
Figure 52. The Flowchart of Exporting Function...75
Figure 53. Export Function (Six Tables)...75
Figure 54. Export to Excel File (Partially Displayed of General History)...75
Figure 55. Select Condition Interface (Select Gender)...76
Figure 56. Select the Content of Condition (Condition: Female, Male)...77
Figure 57. Select Data-(WBC)...78
Figure 58. Generate/Update Chart...78
Figure 59. WBC-AGE Association Chart (Scatter Diagram)...80
Figure 60. WBC-AGE Association Chart (Line Diagram)...81
Figure 61. WBC-AGE Association Chart (Bar Diagram)...82
Figure 62. Select Condition Interface (Select Gender)...83
Figure 63. Input the Content of Condition (Content: Female, Male)...84
Figure 64. Select Data (Lesion Site)...85
Figure 65. Generate/Update Chart...85
Figure 66. Lesion Site and Condition 1(Female) Option Analysis Pie Diagram...86
Figure 67. Lesion Site and Condition 2(Male) Option Analysis Pie Diagram...87
Figure 68. Select Condition Interface (Select Age)...89
Figure 69. Input The Content of Condition (1: 0~50 years old, 2: 51~110 years old)...90
Figure 70. Select Data-(WBC)...91
Figure 71. Generate/Update Chart...91
Figure 72. Pre/Post-op Tracking of WBC and Age (Line Diagram)...92
Figure 73. Pre/Post-op Tracking of WBC and Age (Bar Diagram)...93
Figure 74. Pre/Post-op Tracking of WBC and Age (Area Diagram)...94
Figure 75. Pre/Post-op Tracking of WBC and Age (Radar Diagram)...95



List of Tables
Table 1. Four Vs of Big Data...8
Table 2. The Applications of Big Data Analysis in Medical Field...17
Table 3. Data Mining Examples in the Medical Field...23
Table 4. Three Service Models...24
Table 5. Four Deployment Models...25
Table 6. Five Essential Characteristics...25
Table 7. The Sub-projects of Taiwan Health Cloud Overall Plan...27
Table 8. The Severity of PAOD Represented by 6P...30
Table 9. Fontaine Stage Classification...32
Table 10. Ankle-Brachial Index (ABI)...32
Table 11. Antiplatelet Drugs...33
Table 12. Three-tier web architecture...37
Table 13. System users...37
Table 14. System architecture...37
Table 15. The development tools used in this research...40
Table 16. Description of six main tables...41
Table 17. Five data types...42
Table 18. The information that XML record in this research...43
Table 19. Knowledge Discovery in Databases (KDD) Process of this research...46
Table 20. Membership table design...48
Table 21. IsHasData_PAOD table design...49
Table 22. Patient Information table design...50
Table 23. General History table design...51
Table 24. Pre-op Evaluation table design...53
Table 25. Op Data table design...54
Table 26. Post-op Data table design...55
Table 27. Lab Data table design...56
Table 28. FU_timing (Lab Data) tracking time record...57
Table 29. Introduction of Options...79

Reference
[1]財團法人佛教慈濟綜合醫院臺北分院，<周邊動脈阻塞性疾病>，網址: http://app.tzuchi.com.tw/file_tp/TPpage/HealthEdu/03-心血管系統/E8R0021360-F1-周邊動脈血管疾病.pdf，上網日期:2016年11月15日
[2]林玟玓，顏啟華，<周邊動脈疾病>，家庭醫學與基層醫療30卷2期，(2015/02)，頁:49-58
[3]S. Madden, "From Databases to Big Data," in IEEE Internet Computing, vol. 16, no. 3, pp. 4-6, May-June 2012.
[4]Wen-Kui Chang, “Positively admit the changing trend of the big data era.” Quality Magazine, Chinese Society for Quality, Vol. 49 No.11
[5]Laney, D. (2001). 3D Data management: Controlling data volume, velocity and variety. Meta Group. Accessed 16 Jan 2013.
[6]Feldman B, Martin EM, Skotnes T: Big data in healthcare hype and hope. Dr. Bonnie 360o. 2012.
[7]Fang R, Pouyanfar S, Yang Y, et al: Computational health informatics in the big data age: a survey. ACM Computing Surveys 2016; 49:12.
[8]Andreu-Perez J, Poon CCY, Merrifield RD, et al: Big data for health. IEEE J Biomed Health Inform 2015; 19:1193-208.
[9]衛生福利部統計處，互動式指標查詢，服務量統計，網址: http://iiqsw.mohw.gov.tw/olap/pivot.aspx?TID=C97FBD962F5E47B3&MTID=0FC980F68F840EAD&strGuid=e61e57f9-f3d6-47bb-a1fe-c6b5f0faf232，上網日期:2017年5月31日
[10]高翊瑋(YI-WEI KAO)、侯藹玲(AI-LING HOUR)、葉玲瓏(LING LONG YE)、姜葉飛(YE FEI JIANG)，'A brief introduction to Big data in healthcare,' Journal of Data Analysis；11卷5期(2016/10/01)，P1-11
[11]P. Adriaans and D. Zantinge, 'Data Mining', Addison Wesley Longman, 1996.
[12]Clifton, Christopher. Encyclopadia Britannica: Definition of Data Mining. 2010
[13]Han, Jiawei; Kamber, Micheline."Data mining: concepts and techniques," Morgan Kaufmann. 2001: 5. ISBN 978-1-55860-489-6.
[14]U Fayyad, G Piatetsky-Shapiro, P Smyth, "From data mining to knowledge discovery in databases," AI magazine, 1996
[15]U. Fayyad, "Data mining and knowledge discovery in databases: implications for scientific databases," Proceedings. Ninth International Conference on Scientific and Statistical Database Management (Cat. No.97TB100150), Olympia, WA, 1997, pp. 2-11.
[16]Brachman, R., and Anand, T. 1996. "The Process of Knowledge Discovery in Databases: A Human-Centered Approach," In Advances in Knowledge Discovery and Data Mining, 37–58, eds. U. Fayyad, G. Piatetsky- Shapiro, P. Smyth, and R. Uthurusamy. Menlo Park, Calif.: AAAI Press.
[17]Manyika J, Chui M, Brown B, et al: "Big data: The next frontier for innovation, competition, and productivity," New York: McKinsey Global Institute, 2011.
[18]Litaker et al. "Impact of sumatriptan on clinic utilization and costs of care in migraineurs," Headache 1996
[19]Back, Thomas (1996), "Evolutionary Algorithms in Theory and Practice, " Oxford University Press, New York.
[20]A.S. Fraser. "Simulation of genetic systems by automatic digital computers," VI. Epistasis. Australian Journal of Biological Science, 13:150-162, 1960.
[21]杜慶鳴，《應用遺傳基因演算法於最佳化健康檢查排程作業》，碩士論文，國立高雄第一科技大學-機械與自動化工程研究所，2010。
[22]Freeman, J. A. and D. M. Skapura, "Neural Networks Algorithms, Applications, and Programming Techniques", Addison-Wesley, Reading, Michigan (1992).
[23]Chauvin, Y. and Rumelhart, D.E. "Backpropagation: Theory, Architectures, and Applications,", Erlbaum, Mahwah, NJ,1995.
[24]Grosel j, C. (2002). "Data mining problems in medicine." In Computer-Based Medical Systems, 2002. (CBMS 2002). Proceedings of the 15th IEEE Symposium on (pp. 377-380). IEEE.
[25]陳世源，《資料採礦技術在病例與藥品關連性之研究》，國立中山大學資訊管理 研究所碩士論文，2000
[26]吳素英(2004)，《資料探勘技術應用於知識管理系統之建構以醫院疾病分類管理為例》，國立中正大學資訊管理研究所碩士論文，未出版。
[27]唐壽生(2004)，《資料探勘技術應用於肺結核病患完治的預測》，國立中正大學資訊管理研究所碩士論文，未出版。
[28]Shouman, M., Turner, T., & Stocker, R. (2012, March). "Using data mining techniques in heart disease diagnosis and treatment," In Electronics, Communications and Computers (JEC-ECC), 2012 Japan-Egypt Conference on (pp. 173-177). IEEE.
[29]Rajmohan, K., Paramasivam, I., & Sathyanarayan, S. (2014, February). "Prediction and Diagnosis of Cardio Vascular Disease-A Critical Survey," In Computing and Communication Technologies (WCCCT), 2014 World Congress on (pp. 246-251). IEEE.
[30]Sankaranarayanan.S., Dr Pramananda Perumal.T. (2014). "Diabetic Prognosis through Data Mining Methods and Techniques," International Conference on Intelligent Computing Applications. IEEE.
[31]Dass, M. V., Rasheed, M. A., Ali, M. M. (2014, January). "Classification of lung cancer subtypes by data mining technique, " In Control, Instrumentation, Energy and Communication (CIEC), 2014 International Conference on (pp. 558-562). IEEE.
[32]Xu, T., Zhou, J., Gong, J., Sun, W., Fang, L., & Li, Y. (2012, May). "Improved SOM based data mining of seasonal flu in mainland China," In Natural Computation (ICNC), 2012 Eighth International Conference on (pp. 252-255). IEEE.
[33]林志杰(2005)，《應用資料探勘技術建立中西醫腦中風診斷模型之研究》，Doctoral dissertation，長庚大學。
[34]維基百科，<雲端運算(英語:Cloud Computing)>，網址:https://zh.wikipedia.org/zh-tw/%E9%9B%B2%E7%AB%AF%E9%81%8B%E7%AE%97，上網日期:2017年4月19日
[35]Mell P and Grance T (2009). "The NIST Definition of Cloud Computing," National Institute of Standards and Technology, Information Technology Laboratory, Version 15, 10-7-09
[36]衛生福利部，<台灣健康雲入口網:認識健康雲>，網址：http://healthcloud.mohw.gov.tw/OverView.aspx?FuncCode=OverView
[37]王佩麟、向慧芬、李韻雯、謝逸中、靖永潔、蕭淑代，<住院病房雲端照護系統－科技、效率、安全與護理友善>，新臺北護理期刊；15卷1期(2013/ 03/01)，P1-10，網址:http://dx.doi.org/10.6540%2fNTJN.2013.1.001
[38]邱玟逸、林柔君、羅貽豪，<下肢周邊動脈疾病>，臺灣老誌，第8卷第4 期
[39]Anand S, Yusuf S, "Oral anticoagulant and antiplatelet therapy and peripheral arterial disease," N Engl J Med 2007; 357: 217-27.
[40]李秋妹、楊素貞、葉東峰、邱冠明、洪冠予，<血液透析病患併周邊動脈阻塞性疾病:並力報告與文獻回顧>，台灣腎臟護理學會雜誌，第3卷 第2期
[41]Rockson, S.G., & Cookie, J.P. (1998). "Peripheral arterial insufficiency: Mechanisms, natural history, and therapeutic options," Advances in Internal Medicine, 43, 253-277.
[42]Novo, S. (2002). "Classification, epidemiology, risk factors, and natural history of peripheral arterial disease," Diabetes, Obesity & Metabolism, 4(2),1-6.
[43]Eggers, P. W., & Gohdes, J. (1999). "Nontraumatic lower extremity amputations in Medicare end-stage renal disease population," Kidney Internal, 56, 1524-1533.
[44]Emile R Mohler, III, MD, "Noninvasive diagnosis of peripheral arterial disease," In: Up To-Date (16.3) Oct. 2008.
[45]William R. Hiatt, M.D., "Medical Treatment of Peripheral Arterial Disease and Claudication," NEJM 2001; 344: 1608-1621.
[46]Carman TL, Fernandez BB, "A primary care approach to the patient with claudication," Am Fam Physician 2000; 61: 1027-36.
[47]Christopher White, M.D., "Intermittent Claudication," NEJM 2007, 356: 1241-1250.
[48]Rooke TW, Hirsch AT, Misra S, "2011 ACCF/AHA Focused Update of the Guideline for the Management of Patients with Peripheral Artery Disease (updating the 2005 guideline): a report of the American College of Cardiology Foundation/American Heart Association Task Force on Practice Guidelines," J Am Coll Cardiol 2011; 58: 2020-45.