醫療照護相關感染是健康照護的重要指標，更是導致病患罹病以及死亡的重大原因，造成醫療品質降低與增加醫療成本。本研究根據台灣衛生福利部疾病管制署規定的醫療照護相關感染的定義與標準，建立了泌尿道感染與血流感染的判定感染規則與監測系統，並提出了預測模型來預測檢體抗藥性，透過監測系統可以更早發現醫療照護相關感染的異常現象，並為感染管控人員提供檢查與輔助決策的資訊。實驗結果顯示，透過預測模型可以確定感染的重要特徵。模型預測抗藥性的準確度也相當高，並能讓感染管控人員了解現況，減少擴大感染的機會，提升抗生素的有效性。

Healthcare-Associated Infections (HAI) are important quality indicators of healthcare, a leading cause of mortality and morbidity worldwide, and contributors to lower medical quality and increases in medical costs. Based on the definition and determining criteria of healthcare-related infections stipulated by Taiwan’s Centers for Disease Control, Department of Health, this study created a program for an HAI determining rule, as well as an HAI monitoring system environment and proposed the HAI prediction model to predict antimicrobial resistance (AR). By using the developed system, we can discover healthcare-related infection abnormalities earlier and provide infection control professionals with the ability to check on and conduct pre-decision analyses. Prediction model experimental result shows that identified by cluster analysis of the important characteristics of HAI including sex, ward classification, department etc. Other the proposed prediction model AR with relatively satisfactory accuracy. In this study, the data mining approach for HAI control not only predicts, but also hopes to contribute a sense of control officers to immediately grasp the situation and reduce the chances of expanding infection and enhance the validity of antibiotics.

Contents
Contents	IV
List of Figures	V
List of Tables	VII
Chapter 1 Introduction	1
Chapter 2 Related Works	4
2.1 Healthcare - Associated Infections	4
2.2 Healthcare Information Technology	12
2.3 Data Mining	20
2.4 Development of HAI Indicators	40
Chapter 3 Intelligent Infection Surveillance System	45
3.1 Infection Monitoring	46
3.2 Indicator	49
3.3 System Interface	60
Chapter 4 Surveillance Models	64
4.1 Data Pre-processing and Conversion	65
4.2 Cluster Analysis	68
4.3 Data Mining	70
Chapter 5 Conclusion	87
References	89

List of Figures
Fig 1 Conceptual Framework	3
Fig 2 Clustering	21
Fig 3 SOM Topological Map	25
Fig 4 Bayesian network	33
Fig 5 ROC curves of the two classifiers	38
Fig 6 ROC curves of the two classifiers are very close or rugged	38
Fig 7 System development approach	40
Fig 8 Flowchart for HAI evaluation indicator development	41
Fig 9 Aggregated indexes with dashboard	44
Fig 10 Flowchart for infection control operating	45
Fig 11 System automatic monitoring process	47
Fig 12 Time analysis dimension	52
Fig 13 Department ward analysis dimension	53
Fig 14 HAI system architecture	54
Fig 15 BSI monitoring rule	55
Fig 16 UTI monitoring rule	58
Fig 17 Example code of Decision tree	59
Fig 18 Report sheet	60
Fig 19 Statistic Chart	61
Fig 20 Dashboard for infection trends	62
Fig 21 Distribution of infected patients	63
Fig 22 Model structure	65
Fig 23 Medical database	66
Fig 24 Proportion of each clusters.	69
Fig 25 Bayesian network for each clusters of drug-resistance	82
Fig 26 ROC curve for clusters-1	84
Fig 27 ROC curve for clusters-2	84
Fig 28 ROC curve for clusters-3	85
Fig 29 ROC curve for clusters-4	85

List of Tables
Table 1 Neural network algorithms [57-60]	30
Table 2 Formula for Calculating Sensitivity and Specificity	39
Table 3 The most common bacteria species in BSI and UTI in ICU	43
Table 4 Infection rate of each part in hospital	50
Table 5 Infection density of each part in hospital	51
Table 6 Selected prediction variables	67
Table 7 Selected variables used in the cluster analysis	68
Table 8 Interviewee factors of each clusters	69
Table 9 Variable and target value of resistant bacteria	70
Table 10 The significant values of the variable relationships	72
Table 11 The variables in clusters-1 and clusters-2 of resistant bacteria	75
Table 12 The variables in clusters-3 and clusters-4 of resistant bacteria	76
Table 13 ANOVA for each clusters of drug-resistance	77
Table 14 Classification results	80

[1]	D. W. Bates, M. Cohen, L. L. Leape, J. M. Overhage, M. M. Shabot, and T. Sheridan, “Reducing the frequency of errors in medicine using information technology,” Journal of the American Medical Informatics Association, vol. 8, no. 4, pp. 299-308, Jul-Aug, 2001.
[2]	D. Liu, and N. G. Castle, “Health Information Technology in Nursing Homes,” Journal of Applied, vol. 28, no. 1, pp. 38-58, 2009.
[3]	Mei-Yu Wu , and Wen-Yen Huang, “WSN-based Health Care Management Platform for Long-Term Care Institutions,” JCIT: Journal of Convergence Information Technology, vol. 7, no. 7, pp. 303-311, 2012.
[4]	B. A. Hamilton, Evaluation design of the business case of health information technology in long-term care : Final report, 2006.
[5]	C. Zhan, and M. R. Miller, “Excess length of stay, charges, and mortality attributable to medical injuries during hospitalization,” Journal of the American Medical Informatics Association, vol. 290, no. 14, pp. 1868-1874, Oct 8, 2003.
[6]	S. K. Fridkin, S. F. Welbel, and R. A. Weinstein, “Magnitude and prevention of nosocomial infections in the intensive care unit,” Infectious Disease Clinics of North America, vol. 11, no. 2, pp. 479-496, 1997.
[7]	B. Chaudhry, J. Wang, S. Wu, M. Maglione, W. Mojica, E. Roth, S. C. Morton, and P. G. Shekelle, “Systematic review: impact of health information technology on quality, efficiency, and costs of medical care,” Annals of Internal Medicine, vol. 144, no. 10, pp. 742-752, May 16, 2006.
[8]	R. S. Evans, R. A. Larsen, J. P. Burke, R. M. Gardner, F. A. Meier, J. A. Jacobson, M. T. Conti, J. T. Jacobson, and R. K. Hulse, “Computer surveillance of hospital-acquired infections and antibiotic use,” Journal of the American Medical Informatics Association, vol. 256, no. 8, pp. 1007-1011, Aug 22-29, 1986.
[9]	Brossette S. E., Sprague A. P., Jones W. T., and Moser S. A., “A data mining system for infection control surveillance,” Methods of Information in Medicine, vol. 39, no. 4-5, pp. 303-310, Dec, 2000.
[10]	W. E. Trick, B. M. Zagorski, J. I. Tokars, M. O. Vernon, S. F. Welbel, M. F. Wisniewski, C. Richards, and R. A. Weinstein, “Computer algorithms to detect bloodstream infections,” Emerging Infectious Diseases, vol. 10, no. 9, pp. 1612-1620, Sep, 2004.
[11]	H. M. Glenister, L. J. Taylor, C. L. Bartlett, E. M. Cooke, J. A. Sedgwick, and C. A. Mackintosh, “An evaluation of surveillance methods for detecting infections in hospital inpatients,” Journal of Hospital Infection, vol. 23, no. 3, pp. 229-242, Mar, 1993.
[12]	T. Haustein, P. Gastmeier, A. Holmes, J. C. Lucet, R. P. Shannon, D. Pittet, and S. Harbarth, “Use of benchmarking and public reporting for infection control in four high-income countries,” The Lancet Infectious Diseases, vol. 11, no. 6, pp. 471-481, Jun, 2011.
[13]	L. R. Peterson, and S. E. Brossette, “Hunting Health Care-Associated Infections from the Clinical Microbiology Laboratory: Passive, Active, and Virtual Surveillance,” Journal of Clinical Microbiology, vol. 40, no. 1, pp. 1-4, 2002.
[14]	M. Apte, M. Neidell, E. Y. Furuya, D. Caplan, S. Glied, and E. Larson, “Using electronically available inpatient hospital data for research,” Clinical and Translational Science, vol. 4, no. 5, pp. 338-345, Oct, 2011.
[15]	L. Garcia Alvarez, P. Aylin, J. Tian, C. King, M. Catchpole, S. Hassall, K. Whittaker-Axon, and A. Holmes, “Data linkage between existing healthcare databases to support hospital epidemiology,” Journal of Hospital Infection, vol. 79, no. 3, pp. 231-235, Nov, 2011.
[16]	A. Tinoco, R. S. Evans, C. J. Staes, J. F. Lloyd, J. M. Rothschild, and P. J. Haug, “Comparison of computerized surveillance and manual chart review for adverse events,” Journal of the American Medical Informatics Association, vol. 18, no. 4, pp. 491-7, Jul-Aug, 2011.
[17]	C. Bellini, C. Petignat, P. Francioli, A. Wenger, J. Bille, A. Klopotov, Y. Vallet, R. Patthey, and G. Zanetti, “Comparison of automated strategies for surveillance of nosocomial bacteremia,” Infect Control Hosp Epidemiol, vol. 28, no. 9, pp. 1030-5, Sep, 2007.


[18]	W. Koller, A. Blacky, C. Bauer, H. Mandl, and K. P. Adlassnig, “Electronic surveillance of healthcare-associated infections with MONI-ICU--a clinical breakthrough compared to conventional surveillance systems,” Stud Health Technol Inform, vol. 160, no. Pt 1, pp. 432-6, 2010.
[19]	M. S. van Mourik, A. Troelstra, W. W. van Solinge, K. G. Moons, and M. J. Bonten, “Automated surveillance for healthcare-associated infections: opportunities for improvement,” Clinical Infectious Diseases, vol. 57, no. 1, pp. 85-93, Jul, 2013.
[20]	T. C. Horan, M. Andrus, and M. A. Dudeck, “CDC/NHSN surveillance definition of health care-associated infection and criteria for specific types of infections in the acute care setting,” American Journal of Infection Control vol. 36, no. 5, pp. 309-332, Jun, 2008.
[21]	R. A. Weinstein, “Nosocomial infection update,” Emerging Infectious Diseases vol. 4, no. 3, pp. 416-20, Jul-Sep, 1998.
[22]	W. R. Jarvis, “Infection control and changing health-care delivery systems,” Emerging Infectious Diseases vol. 7, no. 2, pp. 170-173, 2001.
[23]	D. J. M. A. Beaujean, H. E. M. Blok, C. M. J. E. VandenbrouckeGrauls, A. J. L. Weersink, J. A. Raymakers, and J. Verhoef, “Surveillance of nosocomial infections in geriatric patients,” Journal of Hospital Infection, vol. 36, no. 4, pp. 275-284, Aug, 1997.
[24]	R. Agarwal, D. Gupta, P. Ray, A. N. Aggarwal, and S. K. Jindal, “Epidemiology, risk factors and outcome of nosocomial infections in a Respiratory Intensive Care Unit in north India,” Journal of Infection, vol. 53, no. 2, pp. 98-105, Aug, 2006.
[25]	T. I. I. Van der Kooi, J. Mannien, J. C. Wille, and B. H. B. van Benthem, “Prevalence of nosocomial infections in The Netherlands, 2007-2008: results of the first four national studies,” Journal of Hospital Infection, vol. 75, no. 3, pp. 168-172, Jul, 2010.
[26]	陳郁慧, “影響醫院導入知識管理之關鍵因素:以感染管制為例,” 國立中正大學, vol. 資訊管理所, 2008.
[27]	M. K. Obenshain, “Application of data mining techniques to healthcare data,” Infect Control Hospital Epidemiology, vol. 25, no. 8, pp. 690-695, Aug, 2004.
[28]	H. Halpin, S. M. Shortell, A. Milstein, and M. Vanneman, “Hospital adoption of automated surveillance technology and the implementation of infection prevention and control programs,” American Journal of Infection Control, vol. 39, no. 4, pp. 270-276, May, 2011.
[29]	王復德, 陳瑛瑛, 顏慕庸, 陳宜君, and 施姍汝, “感染管制成效之政策面影響因素,” 感染控制雜誌, vol. 17, no. 6, pp. 229-236, 2007.
[30]	王崇安, “建構植基於平衡計分卡之醫療資料倉儲,” 成功大學工程科學系專班學位論文, 成功大學, 2005.
[31]	D. F. Sittig, “Personal health records on the internet: a snapshot of the pioneers at the end of the 20th Century,” International Journal of Medical Informatics vol. 65, no. 1, pp. 1-6, Apr, 2002.
[32]	何曉芸, “電子病歷院際交換系統建構與使用者態度之研究 -以台中市地區為例,” 中國醫藥大學醫務管理學系碩士班學位論文, 中國醫藥大學, 2008.
[33]	J. Leal, D. B. Gregson, T. Ross, W. W. Flemons, D. L. Church, and K. B. Laupland, “Development of a Novel Electronic Surveillance System for Monitoring of Bloodstream Infections,” Infection Control and Hospital Epidemiology, vol. 31, no. 7, pp. 740-747, Jul, 2010.
[34]	D. W. Bates, and A. A. Gawande, “Improving safety with information technology,” The New England Journal of Medicine, vol. 348, no. 25, pp. 2526-2534, Jun 19, 2003.
[35]	B. Van de Castle, J. Kim, M. L. Pedreira, A. Paiva, W. Goossen, and D. W. Bates, “Information technology and patient safety in nursing practice: an international perspective,” International journal of medical informatics, vol. 73, no. 7-8, pp. 607-614, Aug, 2004.
[36]	C. Huckvale, J. Car, M. Akiyama, S. Jaafar, T. Khoja, A. Bin Khalid, A. Sheikh, and A. Majeed, “Information technology for patient safety,” Quality and Safety in Health Care, vol. 19, no. Suppl 2, pp. i25-33, Aug, 2010.
[37]	D. Pittet, E. Safran, S. Harbarth, F. Borst, P. Copin, P. Rohner, J. R. Scherrer, and R. Auckenthaler, “Automatic alerts for methicillin-resistant Staphylococcus aureus surveillance and control: role of a hospital information system,” Infect Control Hosp Epidemiol, vol. 17, no. 8, pp. 496-502, Aug, 1996.
[38]	J. P. Burke, D. C. Classen, S. L. Pestotnik, R. S. Evans, and L. E. Stevens, “The HELP system and its application to infection control,” Journal of Hospital Infection, vol. 18 Suppl A, pp. 424-431, Jun, 1991.
[39]	P. J. Haug, B. H. S. C. Rocha, and R. S. Evans, “Decision support in medicine: lessons from the help system,” International Journal of Medical Informatics, vol. 69, no. 2–3, pp. 273-284, 2003.
[40]	R. M. Gardner, T. A. Pryor, and H. R. Warner, “The HELP hospital information system: update 1998,” International Journal of Medical Informatics, vol. 54, no. 3, pp. 169-182, 1999.
[41]	J. Leal, D. B. Gregson, T. Ross, W. W. Flemons, D. L. Church, and K. B. Laupland, “Development of a novel electronic surveillance system for monitoring of bloodstream infections,” Infect Control Hosp Epidemiol, vol. 31, no. 7, pp. 740-7, Jul, 2010.
[42]	H. Halpin, S. M. Shortell, A. Milstein, and M. Vanneman, “Hospital adoption of automated surveillance technology and the implementation of infection prevention and control programs,” Am J Infect Control, vol. 39, no. 4, pp. 270-6, May, 2011.
[43]	M. F. Wisniewski, P. Kieszkowski, B. M. Zagorski, W. E. Trick, M. Sommers, and R. A. Weinstein, “Development of a clinical data warehouse for hospital infection control,” Journal of the American Medical Informatics Association, vol. 10, no. 5, pp. 454-62, Sep-Oct, 2003.
[44]	E. T. Smyth, G. McIlvenny, J. G. Barr, L. M. Dickson, and I. M. Thompson, “Automated entry of hospital infection surveillance data,” Infect Control Hosp Epidemiol, vol. 18, no. 7, pp. 486-91, Jul, 1997.
[45]	王復德, 陳瑛瑛, 顏慕庸, 陳宜君, and 施姍汝, “感染管制成效之政策面影響因素,” 感染控制雜誌, vol. 17, no. 4, 2007.
[46]	A. Kho, K. Johnston, J. Wilson, and S. J. Wilson, “Implementing an animated geographic information system to investigate factors associated with nosocomial infections: A novel approach,” American Journal of Infection Control vol. 34, no. 9, pp. 578-582, Nov, 2006.
[47]	Frawley W. J., Piatetsky-Shapiro G., and Matheus C. J. , “Knowledge Discovery in Databases: An Overview,” AI Magazine, Fall, vol. 13, no. 3, pp. 213-228, 1992.
[48]	Fayyad U. M., Piatetsky-Shapiro G., and Smyth P., “From Data Mining to Knowledge Discovery in Databases,” AI MAGAZINE, vol. 17, no. 3, pp. 37-54, 1996.
[49]	P. M. J. A. Berry, and G. S. Linoff, Data Mining Techniques: For Marketing, Sales, and Customer Support: John Wiley & Sons, Inc., 1997.
[50]	W. Bouaoula, F. Belgoum, A. Shaikh, M. Taleb-Berrouane, and C. Bazan, “The impact of business intelligence through knowledge management,” Business Information Review, vol. 36, no. 3, pp. 130-140, 2019.
[51]	A. K. Jain, and R. C. Dubes, Algorithms for Clustering Data p.^pp. 334: Prentice Hall 1988, 1988.
[52]	J. Qi, Y. Yu, L. Wang, J. Liu, and Y. Wang, “An effective and efficient hierarchical K-means clustering algorithm,” International Journal of Distributed Sensor Networks, vol. 13, no. 8, pp. 1550147717728627, 2017.
[53]	T. Kohonen, “The self-organizing map,” Neurocomputing, vol. 21, no. 1-3, pp. 1-6, Oct, 1998.
[54]	張斐章, 張麗秋, and 黃浩倫, 類神經網路理論與實務: 東華書局, 2003.
[55]	Amiri Babak, and F. Mohammad, “Integration of self-organizing feature map and K-means algorithm for market segmentation,” Computers & Operations Research, vol. 29, no. 11, pp. 1475-1493, Sep, 2002.
[56]	葉怡成, 類神經網路模式應用與實作: 儒林圖書有限公司，台北, 2003.
[57]	S. Roweis, “Levenberg-Marquardt Optimization,” University of Toronto, 1996.
[58]	D. P. Bertsekas, Athena Scientific, Belmont, MA, 1999.
[59]	J. R. Shewchuk, An introduction to the conjugate gradient method without the agonizing pain, Carnegie Mellon University, 1994.
[60]	S. E. Fahlman, “Faster-Learning Variations on Back-Propagation: An Empirical Study,” In Proceedings.Connectionist Models Summer School, Morgan-Kaufmann, Los Altos CA, pp. 38-51, 1998.
[61]	Richard J. R, and Michael W. G, Data Mining:A Tutorial-Based Primer: Addison Wesley, Boston, 2003.
[62]	F. V. Jensen, “An Introduction to Bayesian Network,” New York: Springer Verlag, 1996.
[63]	張雲濤, and 龔玲, 資料探勘原理與技術: 五南圖書出版股份有限公司, 2007.
[64]	林惠玲, and 陳正昌, 應用統計學, 雙葉書廊有限公司, 2003.
[65]	陳榮方, “統計應用與分析-第九章變異數分析,” 高應大企管系(所).
[66]	R. K. Hanson, and D. Thornton, “Improving risk assessments for sex offenders: a comparison of three actuarial scales.,” Law and Human Behavior, vol. 24, no. 1, pp. 119-136, 2000.
[67]	吳萬益, 企業研究方法(四版), 台灣: 華泰文化, 2011.
[68]	R. W. Haley, D. H. Culver, J. W. White, W. M. Morgan, T. G. Emori, V. P. Munn, and T. M. Hooton, “The efficacy of infection surveillance and control programs in preventing nosocomial infections in US hospitals.,” American Journal of Epidemiology, vol. 121 no. 2, pp. 182-205, 1985.
[69]	R. R. Roberts, R. D. S. II, R. Cordell, S. L. Solomon, L. Steele, L. M. Kampe, W. E. Trick, and R. A. Weinstein, “Extra charges and  prolongation  of  stay  attributable  to  nosocomial  infections:  a  prospective  interhospital comparison.,” American Journal of Medicine, vol. 70, pp. 51-58, 1981.
[70]	R. W. Haley, J. W. White, D. H. Culver, and J. M. Hughes, “The financial incentive for hospitals to prevent nosocomial infections under the prospective payment system: an empirical determination from a nationally representative sample. ,” Journal of the American Medical Informatics Association, vol. 257, pp. 1611-1614, 1987.
[71]	S. G. Baugh, “Intermediate Statistics: A Modern Approach (3rd ed.).” Organizational Research Methods, vol. 12, no. 1, pp. 205-207, Jan, 2009.
[72]	B. G. Marcot, P. A. Hohenlohe, S. Morey, R. Holmes, R. Molina, M. C. Turley, M. H. Huff, and J. A. Laurence, “Characterizing species at risk II: Using Bayesian belief networks as decision support tools to determine species conservation categories under the Northwest Forest Plan,” Ecology and Society, vol. 11, no. 2, Dec, 2006.