臺灣博碩士論文加值系統

抗甲氧西林金黃色葡萄球菌(methicillin resistant Staphylococcus aureus, MRSA)是近年來國際間最被注意的一種多重抗藥致病細菌。不同的金黃色葡萄球菌株可製造不同毒素，引起皮膚、傷口、骨髓炎、肺炎及菌血症等各種感染。其感染主要透過直接傳播，身體接觸、皮膚有傷口、擠迫環境以及個人衛生欠佳，亦有可能造成感染。文獻指出感染MRSA菌血症的病人在感染30天內的死亡率是34%。目前臨床上是以微生物培養與抗生素敏感試驗MRSA的確認診斷試驗。而本研究是以資料採礦技術預測MRSA菌血症的病人，在接受傳統萬古黴素治療後7天與30天後，持續陽性菌血症之病人，以及其死亡的機率，目的是希望比傳統培養方法更能快速提供臨床醫師作為抗生素治療的依據。本研究中，我們使用了29個風險因子來預測。研究結果顯示，我們能夠準確的預測病人血液培養中MRSA的7天持續存在準確率為82.0%〜86.6%﹔病人在30天內死亡的準確率為53.4%〜69.2%。這樣的預測方法可以適用在任何醫院，利用前瞻性研究收集病人資料以建立自己的預測模型。

Methicillin-resistant Staphylococcus aureus (MRSA) is a multi-drug-resistant pathogenic bacteria that receive the most attention. Different strains of S. aureus can produce toxins and cause skin, wounds, osteomyelitis, pneumonia, bacteremia, and other infections. Infection is mainly spread through direct physical contact, skin wounds, crowded environment, and poor personal hygiene may also cause infection. Patients infected with MRSA bacteremia within 30 days mortality was 34%. Selection of antibiotics mainly depends on microbial culture and antibiotic sensitivity test. The purpose of this study is predict outcome of patients with MRSA bacteremia using data mining techniques to provide better management of patient therapy. We used MRSA persistence in bacteremia after 7 days, 30 days, and death as endpoints in patients receiving a traditional vancomycin therapy. In this study, we used 29 risk factors associated with MRSA bacteremia. Our results showed that we are able to predict the 7-day persistence of MRSA in blood cultures at accuracy ranged 82.0% ~ 86.6%; death of patient within 30 days at accuracy ranged 53.4% ~ 69.2%. Such a prediction method can be applied in hospitals by use of a prospective study to collect patient data in order to establish their predictive models.

Table of Contents
中文摘要 I
Abstract II
Table of Contents III
List of Tables V
List of Figures VI
1. Introduction 1
1.1 Background 1
1.2 Motivation 3
1.3 Objective 3
2. Literature Review 4
2.1 Methicillin-resistant Staphylococcus aureus (MRSA) 4
2.2 MRSA bloodstream infection (BSI) 5
2.3 Antimicrobial Agents for S. aureus 6
2.4 Laboratory Detection Methods 9
2.5 Data Mining 11
2.5.1 Binary Classification 13
3. Materials and Methods 16
3.1 Study Hospital 16
3.2 Data collection 16
3.3 Data mining Methodology 16
3.4 Risk Factor Groupings 17
3.5 Training Model 17
4. Results 18
4.1 Prediction Accuracy among Binary Classifier Models 18
4.1.1 7 days persistence of S. aureus (Y1) 18
4.1.2 30 days persistence of S. aureus (Y2) 19
4.1.3 Death (Y3) 19
4.2 Application of Prediction Models 19
5. Discussion 21
6. Conclusion and Recommendations 24
7. References 25

 
List of Tables
Table 1. Risk factors used in predictive model construction 30
Table 2. Results of predictive models using 29 risk factors 31
Table 3. Results of prediction in 7 days persistence of S. aureus in blood cultures 32
Table 4. Risk factors used in prediction for 7 days persistence of S. aureus in blood cultures 33
Table 5. Results of prediction in 30 days persistence of S. aureus in blood cultures 34
Table 6. Risk factors used in prediction for 30 days persistence of S. aureus in blood cultures 35
Table 7. Results of prediction in death within 30 days 36
Table 8. Risk factors used in prediction of death 37





 
List of Figures
Figure 1. C&R Tree model prediction for 7 days persistence of S. aureus in blood cultures 38
Figure 2. C 5.1 model prediction for 7 days persistence of S. aureus in blood cultures 39
Figure 3. C&R Tree model prediction of death within 30 days 40
Figure 4. C 5.1 model prediction of death within 30 days 41

Alipour, F., Ahmadi, M., & Javadi, S. (2014). Evaluation of different methods to detect methicillin resistance in Staphylococcus aureus (MRSA). J Infect Public Health, 7 (3), 186-191. doi: 10.1016/j.jiph.2014.01.007
Chastre, J., Blasi, F., Masterton, R., Rello, J., Torres, A., & Welte, T. (2014). European perspective and update on the management of nosocomial pneumonia due to methicillin‐resistant Staphylococcus aureus after more than 10 years of experience with linezolid. Clinical Microbiology and Infection, 20 (s4), 19-36.
Chen, X., Wang, W. K., Han, L. Z., Liu, Y., Zhang, H., Tang, J., . . . Ni, Y. X. (2013). Epidemiological and genetic diversity of Staphylococcus aureus causing bloodstream infection in Shanghai, 2009-2011. PLoS One, 8 (9), e72811. doi: 10.1371/journal.pone.0072811
Datta, R., & Huang, S. S. (2008). Risk of infection and death due to methicillin-resistant Staphylococcus aureus in long-term carriers. Clin Infect Dis, 47 (2), 176-181. doi: 10.1086/589241
Davis, K. A., Stewart, J. J., Crouch, H. K., Florez, C. E., & Hospenthal, D. R. (2004). Methicillin-resistant Staphylococcus aureus (MRSA) nares colonization at hospital admission and its effect on subsequent MRSA infection. Clinical Infectious Diseases, 39 (6), 776-782.
Graffunder, E. M., & Venezia, R. A. (2002). Risk factors associated with nosocomial methicillin-resistant Staphylococcus aureus (MRSA) infection including previous use of antimicrobials. Journal of Antimicrobial Chemotherapy, 49(6), 999-1005.
Guilarde, A. O., Turchi, M. D., Martelli, C. M., & Primo, M. G. (2006). Staphylococcus aureus bacteraemia: incidence, risk factors and predictors for death in a Brazilian teaching hospital. J Hosp Infect, 63 (3), 330-336. doi: 10.1016/j.jhin.2006.02.011
Haddadin, A., Fappiano, S., & Lipsett, P. (2002). Methicillin resistant Staphylococcus aureus (MRSA) in the intensive care unit. Postgrad Med J, 78 (921), 385-392.
Hounsom, L., Grayson, K., & Melzer, M. (2011). Mortality and associated risk factors in consecutive patients admitted to a UK NHS trust with community acquired bacteraemia. Postgrad Med J, 87 (1033), 757-762. doi: 10.1136/pgmj.2010.116616
Hsu, C. C., Lin, Y. E., Chen, Y. S., Liu, Y. C., & Muder, R. R. (2008). Validation study of artificial neural network models for prediction of methicillin-resistant Staphylococcus aureus carriage. Infect Control Hosp Epidemiol, 29 (7), 607-614. doi: 10.1086/588588
Ibrahim MD, Sherman G, Ward S, Fraser VJ, Kollef MH. The influence of inadequate antimicrobial treatment of bloodstream infections on patient outcomes in the ICU setting. Chest 2000; 118:146-55.
Joo, J., Yamaki, J., Lou, M., Hshieh, S., Chu, T., Shriner, K. A., & Wong-Beringer, A. (2013). Early response assessment to guide management of methicillin-resistant Staphylococcus aureus bloodstream infections with vancomycin therapy. Clin Ther, 35 (7), 995-1004. doi: 10.1016/j.clinthera.2013.05.018
Kaasch, A. J., Barlow, G., Edgeworth, J. D., Fowler, V. G., Jr., Hellmich, M., Hopkins, S., . . . Thwaites, G. E. (2014). Staphylococcus aureus bloodstream infection: a pooled analysis of five prospective, observational studies. J Infect, 68 (3), 242-251. doi: 10.1016/j.jinf.2013.10.015
Lavrač, N. (1999). Selected techniques for data mining in medicine. Artificial intelligence in medicine, 16 (1), 3-23.
Laupland, K. B., Ross, T., & Gregson, D. B. (2008). Staphylococcus aureus bloodstream infections: risk factors, outcomes, and the influence of methicillin resistance in Calgary, Canada, 2000–2006. Journal of Infectious Diseases,198(3), 336-343.

Moise PA, Forrest A, Bhavnani SM, Birmingham MC, Schentag JJ. Area in the inhibitory curve and a pneumonia scoring system for predicting outcomes of vancomycin therapy for respiratory infections by Staphylococcus aureus. Am J Health-Syst Pharm 2000;57:S4-9.
Moise-Broder PA, Forrest A, Birmingham MC, Shentag JJ. Pharmacodynamics of vancomycin and other antimicrobials in patients with Staphylococcus aureus lower respiratory tract infections. Clin Pharmacokinet 2004;43:925-942.
Naves, K. S., Vaz da Trindade, N., & Gontijo Filho, P. P. (2012). Methicillin-resistant Staphylococcus aureus bloodstream infection: risk factors and clinical outcome in non-intensive-care units. Rev Soc Bras Med Trop, 45 (2), 189-193.
Patel, D. A., Shorr, A. F., Chastre, J., Niederman, M., Simor, A., Stephens, J. M., . . . Nathwani, D. (2014). Modeling the economic impact of linezolid versus vancomycin in confirmed nosocomial pneumonia caused by methicillin-resistant Staphylococcus aureus. Crit Care, 18 (4), R157. doi: 10.1186/cc13996
Porto, J. P., Santos, R. O., Gontijo Filho, P. P., & Ribas, R. M. (2013). Active surveillance to determine the impact of methicillin resistance on mortality in patients with bloodstream infection and influences of the use of antibiotics on the development of MRSA infection. Rev Soc Bras Med Trop, 46 (6), 713-718. doi: 10.1590/0037-8682-0199-2013
Riedel, S., Dam, L., Stamper, P. D., Shah, S. A., & Carroll, K. C. (2010). Evaluation of Bio-Rad MRSASelect Agar for Detection of Methicillin-Resistant Staphylococcus aureus Directly from Blood Cultures. Journal of Clinical Microbiology, 48 (6), 2285-2288.
Rodvold, K. A., & McConeghy, K. W. (2014). Methicillin-Resistant Staphylococcus aureus Therapy: Past, Present, and Future. Clinical Infectious Diseases, 58 (suppl 1), S20-S27.
Saichanma, S., Chulsomlee, S., Thangrua, N., Pongsuchart, P., & Sanmun, D. (2014). The observation report of red blood cell morphology in Thailand teenager by using data mining technique. Adv Hematol, 2014, 493706. doi: 10.1155/2014/493706
Shang, J. S., Lin, Y. S., & Goetz, A. M. (2000). Diagnosis of MRSA with neural networks and logistic regression approach. Health Care Manag Sci, 3 (4), 287-297.
Souweine, B., Traore, O., Aublet-Cuvelier, B., Bret, L., Sirot, J., Laveran, H., & Deteix, P. (2000). Role of infection control measures in limiting morbidity associated with multi-resistant organisms in critically ill patients. Journal of Hospital Infection, 45 (2), 107-116.
Tenover, F. C., Biddle, J. W., & Lancaster, M. V. (2001). Increasing resistance to vancomycin and other glycopeptides in Staphylococcus aureus. Emerg Infect Dis, 7(2), 327.
Tissot, F., Calandra, T., Prod'hom, G., Taffe, P., Zanetti, G., Greub, G., & Senn, L. (2014). Mandatory infectious diseases consultation for MRSA bloodstream infection is associated with reduced mortality. J Infect, 69 (3), 226-234. doi: 10.1016/j.jinf.2014.05.004
Tsumoto, S., Tsumoto, Y., Matsuoka, K., & Yokoyama, S. (2007). Risk mining in medicine: Application of data mining to medical risk management Web Intelligence Meets Brain Informatics (pp. 471-493): Springer.
Weinstein, R. A., & Fridkin, S. K. (2001). Vancomycin-intermediate and-resistant Staphylococcus aureus: what the infectious disease specialist needs to know. Clinical Infectious Diseases, 32(1), 108-115.
Wunderink, R. G., Mendelson, M. H., Somero, M. S., Fabian, T. C., May, A. K., Bhattacharyya, H., . . . Solomkin, J. S. (2008). Early microbiological response to linezolid vs vancomycin in ventilator-associated pneumonia due to methicillin-resistant Staphylococcus aureus. Chest, 134 (6), 1200-1207. doi: 10.1378/chest.08-0011