Risk Factors Affecting Death from Hospital-Acquired Infections in Trauma Patients: Association Rule Mining

Document Type : Original Article

Authors

1 School of Management & Information Sciences, Shiraz University of Medical Sciences, Shiraz, Iran

2 School of Management & Information Sciences, Shiraz University of Medical Sciences, Shiraz, Iran

3 Trauma Research Center, Shahid Rajaee (Emtiaz) Trauma Hospital, Shiraz University of Medical Sciences, Shiraz, Iran

4 Department of Health Information Management, School of Management and Information Sciences, Shiraz University of Medical Sciences, Shiraz, Iran

Abstract

Introduction: Trauma patients are potentially at high risk of acquiring infections in hospitals,
which is the main cause of in-hospital mortality. The aim of this study was to identify the risk
factors contributing to death from hospital-acquired infections in trauma patients by data
mining techniques.
Methods: This is a cohort study. A total of 549 trauma patients with nosocomial infection
who were admitted to Shiraz trauma hospital between 2017 and 2018 were studied. Sex,
age, mechanism of injury, body region injured, injury severity score, length of stay, type
of intervention, infection day after admission, microorganism cause of infections, and
the outcomes were collected. Association rule mining techniques were applied to extract
knowledge from the data set. The IBM SPSS Modeler data mining software version 18.0 was
used as a tool for data mining of the trauma patients with hospital queried infections database.
Results: The age older than 65, surgical site infection skin, bloodstream infection, mechanism
injury of car accident, invasive intervention of tracheal intubation, injury severity score higher
than 16, and multiple injuries with higher than 71 percent confidence level were associated
with in-hospital mortality. The relationship between those predicators and death among
hospital-acquired infection was strong (Lift value >1).
Conclusion: Factors such as increasing age, tracheal intubation, mechanical ventilator,
surgical site infection skin, upper respiratory infection are associated with death from
hospital-acquired infections in trauma patients by data mining.

Keywords


1. Mirhashemi AH, Kalantar Motamedi MH, Mirhashemi S, Taghipour H, Danial Z. Prevalent causes of mortality in the Iranian population. Hospital Practices and Research. 2017;2(3):93. doi: 10.15171/hpr.2017.23.
2. Wallace WC, Cinat M, Gornick WB, Lekawa ME, Wilson SE. Nosocomial infections in the surgical intensive care unit: a difference between trauma and surgical patients. Am Surg. 1999;65(10):987- 90.
3. Burke JP. Infection control - a problem for patient safety. N Engl J Med. 2003;348(7):651-6. doi: 10.1056/NEJMhpr020557.
4. Anderson R, Rosenberg H. National Vital Statistics Reports. Deaths: Leading causes for 1999. 2001.
5. Czaja AS, Rivara FP, Wang J, Koepsell T, Nathens AB, Jurkovich GJ, et al. Late outcomes of trauma patients with infections during index hospitalization. J Trauma. 2009;67(4):805-14. doi: 10.1097/TA.0b013e318185e1fb.
6. Glance LG, Stone PW, Mukamel DB, Dick AW. Increases in mortality, length of stay, and cost associated with hospital-acquired infections in trauma patients. Arch Surg. 2011;146(7):794-801. doi: 10.1001/archsurg.2011.41.
7. Sheng WH, Wang JT, Lin MS, Chang SC. Risk factors affecting in-hospital mortality in patients with nosocomial infections. J Formos Med Assoc. 2007;106(2):110-8. doi: 10.1016/S0929- 6646(09)60226-6.
8. Tejada Artigas A, Bello Dronda S, Chacon Valles E, Munoz Marco J, Villuendas Uson MC, Figueras P, et al. Risk factors for nosocomial pneumonia in critically ill trauma patients. Crit Care Med. 2001;29(2):304-9. doi: 10.1097/00003246- 200102000 00015.
9. Lazarus HM, Fox J, Burke JP, Lloyd JF, Snow GL, Mehta RR, et al. Trauma patient hospitalassociated infections: risks and outcomes. J Trauma. 2005;59(1):188-94. doi: 10.1097/01. ta.0000171535.75484.df.
10. Salgado Yepez E, Bovera MM, Rosenthal VD, Gonzalez Flores HA, Pazmino L, Valencia F, et al. Device-associated infection rates, mortality, length of stay and bacterial resistance in intensive care units in Ecuador: International Nosocomial Infection Control Consortium’s findings. World J Biol Chem. 2017;8(1):95-101. doi: 10.4331/wjbc. v8.i1.95.
11. Matsuoka K, Yokoyama S, Watanabe K, Tsumoto S, editors. Mining rules for risk factors on blood stream infection in hospital information system. 2007 IEEE International Conference on Bioinformatics and Biomedicine (BIBM 2007); 2007: IEEE. doi: 10.1109/BIBM.2007.44.
12. Khajehali N, Alizadeh S. Extract critical factors affecting the length of hospital stay of pneumonia patient by data mining (case study: an Iranian hospital). Artif Intell Med. 2017;83:2-13. doi: 10.1016/j.artmed.2017.06.010.
13. Silva E, Cardoso L, Portela F, Abelha A, Santos MF, Machado J. Predicting nosocomial infection by using data mining technologies. New Contributions in Information Systems and Technologies: Springer; 2015. p. 189-98. doi: 10.1007/978-3-319-16528-8_18.
14. Yoo I, Alafaireet P, Marinov M, Pena-Hernandez K, Gopidi R, Chang JF, et al. Data mining in healthcare and biomedicine: a survey of the literature. J Med Syst. 2012;36(4):2431-48. doi: 10.1007/s10916-011-9710-5.
15. Altaf W, Shahbaz M, Guergachi A. Applications of association rule mining in health informatics: a survey. Artificial Intelligence Review. 2017;47(3):313-40. doi: 10.1007/s10462-016-9483-9.
16. Cai R, Liu M, Hu Y, Melton BL, Matheny ME, Xu H, et al. Identification of adverse drugdrug interactions through causal association rule discovery from spontaneous adverse event reports. Artif Intell Med. 2017;76:7-15. doi: 10.1016/j.artmed.2017.01.004.
17. Cheng C-W, Wang MD. Healthcare Data Mining, Association Rule Mining, and Applications. Health Informatics Data Analysis. Philippines: Springer; 2017. p. 201-10. doi: 10.1007/978-3-319- 44981-4_13.
18. Hareendran SA, Chandra SV, editors. Association Rule Mining in Healthcare Analytics. International Conference on Data Mining and Big Data; 2017: Springer.
19. PandyaJalpa P, MorenaRustom D. A Survey on Association Rule Mining Algorithms Used in Different Application Areas. Volume. 2017;8:1430-6.
20. Lee DG, Ryu KS, Bashir M, Bae JW, Ryu KH. Discovering medical knowledge using association rule mining in young adults with acute myocardial infarction. J Med Syst. 2013;37(2):9896. doi: 10.1007/s10916-012-9896-1.
21. Dhinakaran D, PM JP. A Study on Data Mining: Frequent Itemset Mining Methods Apriori, FP growth, Eclat. 2017.
22. Rao PS, Devi TU. Applicability of apriori based association rules on medical data. Int J Appl Eng Res. 2017;12(20):9451-8.
23. Huang G, Huang Q, Zhang G, Jiang H, Lin Z. Point-prevalence surveys of hospital-acquired infections in a Chinese cancer hospital: From 2014 to 2018. J Infect Public Health. 2020;13(12):1981-7. doi: 10.1016/j.jiph.2020.03.003.
24. Shu H, Li L, Wang Y, Guo Y, Wang C, Yang C, et al. Prediction of the Risk of Hospital Deaths in Patients with Hospital-Acquired Pneumonia Caused by Multidrug-Resistant Acinetobacter baumannii Infection: A Multi-Center Study. Infect Drug Resist. 2020;13:4147-54. doi: 10.2147/ IDR.S265195.
25. Despotovic A, Milosevic B, Milosevic I, Mitrovic N, Cirkovic A, Jovanovic S, et al. Hospitalacquired infections in the adult intensive care unit-Epidemiology, antimicrobial resistance patterns, and risk factors for acquisition and mortality. Am J Infect Control. 2020;48(10):1211- 5. doi: 10.1016/j.ajic.2020.01.009.
26. Lalwani S, Punia P, Mathur P, Trikha V, Satyarthee G, Misra MC. Hospital acquired infections: preventable cause of mortality in spinal cord injury patients. J Lab Physicians. 2014;6(1):36-9. doi: 10.4103/0974-2727.129089.
27. Brady M, Oza A, Cunney R, Burns K. Attributable mortality of hospital-acquired bloodstream infections in Ireland. J Hosp Infect. 2017;96(1):35- 41. doi: 10.1016/j.jhin.2017.02.006.
28. Hosseini S, Ranjbar R. A Case Report of Septicemia Due to Pseudomonas Aeruginosa and Acinetobacter in a Multiple Trauma Patient. Journal of Ilam University of Medical Sciences. 2008;16(2):16-20.