Abstract
Introduction
Trauma scoring aims for quantification and uniform reporting of trauma-related outcomes. Despite significant advances in trauma scoring, the exact time period at which relevant calculations should be made is not clear. Considering the importance of response to resuscitation, calculation of trauma scores after a period of resuscitation can allow better discrimination of patients who will survive.
Methods
A fuzzy-logic inference system, which is completely based on expert opinion and uses Glasgow Coma Scale (GCS) and systolic blood pressure at arrival to emergency room (ER) and their response to resuscitation as inputs, was developed. Records of the last 150 trauma patients admitted to our surgical intensive care unit (ICU) were used for calculations related to Injury Severity Score (ISS), Revised Trauma Score (RTS), Trauma and Injury Severity Score, and A Severity Characterization of Trauma (ASCOT) systems. Calculation of trauma severity and predicted mortality was performed at different time intervals during resuscitation [at arrival to emergency room (ER), after 1 h of resuscitation, and at ICU admission]. The performance of conventional systems and fuzzy-logic system was compared.
Results
Mean ISS was 32.31 ± 14.01. All systems included showed acceptable discriminative power. Among the conventional systems calculated at emergency room admission, ISS was the best performing [receiver operating characteristics (ROC), 0.9033] and RTS was the worst (ROC, 0.8106). Their performances were improved by up to 13% by use of post-resuscitation physiologic variables. Fuzzy-logic inference system performed slightly better (ROC, 0.9247) then the conventional systems calculated at arrival to ER.
Conclusions
Response to resuscitation has significant impact on trauma mortality and must be considered in trauma scoring and mortality prediction. Fuzzy logic provides important opportunities for design of better predictive systems.
Similar content being viewed by others
References
Fingerhut LA, Warner M. Injury Chartbook. Health, United States, 1996–97. National Center for Health Statistics. Hyattsville MD, 1997.
MacKenzie EJ, Fowler CJ. Epidemiology. In: Feliciano DV, Mattox KL, Moore EE, eds. Trauma. New York: McGraw-Hill; 2008. p. 25–40.
Medical expenditure panel survey. Total expenses for selected conditions by type of service: United States, 2006. http://www.meps.ahrq.gov/mepsweb/data_stats/tables_compendia_hh_interactive.jsp?_SERVICE=MEPSSocket0&_PROGRAM=MEPSPGM.TC.SAS&File=HCFY2006&Table=HCFY2006_CNDXP_C&_Debug=. Accessed 29 May 2009.
WISQARS fatal injuries: mortality reports. http://webappa.cdc.gov/sasweb/ncipc/mortrate.html. Accessed 29 May 29 2009.
Kilgo PD, Meredith JW, Osler TM. Injury severity scoring and outcomes research. In: Feliciano DV, Mattox KL, Moore EE, eds. Trauma. New York: McGraw-Hill; 2008: p. 83–90.
Negnevitsky M. Fuzzy expert systems. In: Negnevitsky M, ed. Artificial intelligence: a guide to intelligent systems. New York: Addison-Wesley; 2005 p. 87–129.
Hudson DL, Cohen ME. Fuzzy systems. In: Hudson DL, Cohen ME, eds. Neural networks and artificial intelligence for biomedical engineering. New York: IEEE Press; 2000 p. 243–260.
Baker SP, O’Neill B, Haddon W, Long WB. The severity score: a method for describing patients with multiple injuries an evaluating emergency care. J Trauma. 1974;14:187–96.
Champion HR, Sacco WJ, Copes WS, Gann DS, Gennarelli TA, Flanagan ME. A revision of the Trauma Score. J Trauma. 1989;29:623–9.
Boyd C, Tolson M, Copes W. Evaluating trauma care: the TRISS method. Trauma Score and the Injury Severity Score. J Trauma. 1987;27:370–8.
Champion HR, Copes WS, Sacco WJ, Lawnick MM, Keast SL, Bain LW, et al. The major trauma outcome study: establishing national norms for trauma care. J Trauma. 1990;30:1356–65.
Millham FH, LaMorte WW. Factors associated with mortality in trauma: re-evaluation of the TRISS method using the National Trauma Data Bank. J Trauma. 2004;56:1090–6.
Association for the Advancement of Automotive Medicine, Committee on Injury Scaling. The Abbreviated Injury Scale 1998. IL: Des Plains; 1998.
Association for the Advancement of Automotive Medicine, Committee on Injury Scaling: the Abbreviated Injury Scale 1998. Des Plains: IL; 1998.
Frankema SPG, Steyerberg EW, Edwards MJR, van Vugt AB. Comparison of current injury scales for survival chance estimation: an evaluation comparing the predictive performance of the ISS, NISS, and AP scores in a Dutch local trauma registration. J Trauma. 2005;58:596–604.
Demetriades D, Chan LS, Velmahos G, Berne TV, Cornwell EE 3rd, Belzberg H, et al. TRISS methodology in trauma: the need for alternatives. Br J Surg. 1998;85:379–84.
Suárez-Alvarez JR, Miquel J, Del Río FJ, Ortega P. Epidemiologic aspects and results of applying the TRISS methodology in a Spanish trauma intensive care unit (TICU). Intensive Care Med. 1995;21:729–36.
Coimbra R, Razuk A, Pinto MC, Aguida HC, Saad R Jr, Rasslan S. Severely injured patients in the intensive care unit: a critical analysis of outcome and unexpected deaths identified by the TRISS methodology. Int Surg. 1996;81:102–6.
Osler TM, Rogers FB, Badger GJ, Healey M, Vane DW, Shackford SR. A simple mathematical modification of TRISS markedly improves calibration. J Trauma. 2002;53:630–4.
Champion HR, Copes WS, Sacco WJ, Lawnick MM, Bain LW, Gann DS, et al. A new characterization of injury severity. J Trauma. 1990;30:539–45.
Meredith W, Rutledge R, Fakhry SM, Emery S, Kromhout-Schiro S. The conundrum of the Glasgow Coma Scale in intubated patients: a linear regression prediction of the Glasgow verbal score from the Glasgow eye and motor scores. J Trauma. 1998;44:839–44.
Rutledge R, Lentz CW, Fakhry S, Hunt J. Appropriate use of the Glasgow Coma Scale in intubated patients: a linear regression prediction of the Glasgow verbal score from the Glasgow eye and motor scores. J Trauma. 1996;41:514–22.
Healey C, Osler TM, Rogers FB, Healey MA, Glance LG, Kilgo PD, et al. Improving the Glasgow Coma Scale score: motor score alone is a better predictor. J Trauma. 2003;54:671–8.
Conflict of Interest
Y.A.K. is a member of the Bilgitay Study Group, an academic research group that mainly works on artificial intelligence applications in intensive care.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Kilic, Y.A., Konan, A., Yorganci, K. et al. A novel fuzzy-logic inference system for predicting trauma-related mortality: emphasis on the impact of response to resuscitation. Eur J Trauma Emerg Surg 36, 543–550 (2010). https://doi.org/10.1007/s00068-010-0010-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00068-010-0010-4