A NEW METHOD FOR PREDICTING SURVIVAL AND ESTIMATING UNCERTAINTY IN TRAUMA PATIENTS
https://doi.org/10.23934/2223-9022-2017-6-1-30-33
Abstract
The Trauma and Injury Severity Score (TRISS) is the current “gold” standard of screening patient’s condition for purposes of predicting survival probability. More than 40 years of TRISS practice revealed a number of problems, particularly, 1) unexplained fluctuation of predicted values caused by aggregation of screening tests, and 2) low accuracy of uncertainty intervals estimations. We developed a new method made it available for practitioners as a web calculator to reduce negative effect of factors given above. The method involves Bayesian methodology of statistical inference which, being computationally expensive, in theory provides most accurate predictions. We implemented and tested this approach on a data set including 571,148 patients registered in the US National Trauma Data Bank (NTDB) with 1–20 injuries. These patients were distributed over the following categories: (1) 174,647 with 1 injury, (2) 381,137 with 2–10 injuries, and (3) 15,364 with 11–20 injuries. Survival rates in each category were 0.977, 0.953, and 0.831, respectively. The proposed method has improved prediction accuracy by 0.04%, 0.36%, and 3.64% (p-value <0.05) in the categories 1, 2, and 3, respectively. Hosmer-Lemeshow statistics showed a significant improvement of the new model calibration. The uncertainty 2σ intervals were reduced from 0.628 to 0.569 for patients of the second category and from 1.227 to 0.930 for patients of the third category, both with p-value <0.005. The new method shows the statistically significant improvement (p-value <0.05) in accuracy of predicting survival and estimating the uncertainty intervals. The largest improvement has been achieved for patients with 11–20 injuries. The method is available for practitioners as a web calculator http://www.traumacalc.org.
About the Authors
V. G. Schetinin
Penza State University;
University of Bedfordshire
United Kingdom
United Kingdom
Penza;
PhD, Senior Lecturer in Computing and Information Systems, Luton
L. I. Jakaite
University of Bedfordshire
United Kingdom
Luton
United Kingdom
Luton
V. F. Kuriakin
Penza State University
Russian Federation
Penza
Russian Federation
Penza
V. I. Gorbachenko
Penza State University
Russian Federation
Penza
Russian Federation
Penza
References
1. Boyd C.R., Tolson M.A., Copes W.S. Evaluating trauma care: The TRISS method. Trauma Score and the Injury Severity Score. J Trauma. 1987; 27(4): 370–378. PMID: 310664.
2. Committee on Trauma, American College of Surgeons. NTDB Research Data Set and National Sample Program. 2014. URL: http://www.facs.org/trauma/ntdb/ntdbapp.html. (Accessed Jul 01, 2016.)
3. Kilgo P., Meredith J., Osler T. Injury severity scoring and outcomes research. In: Feliciano D.V., Mattox K.L., Moore E.E., eds. Trauma. 6th ed. New York: McGraw-Hill, 2008: 223–230.
4. Brohi K. TRISS: Trauma — injury severity score. TRISS — Overview and Desktop Calculator. 2012. URL: http://www.trauma.org/index.php/main/article/387. (Accessed Jul 01, 2016.)
5. Osler T., Glance L., Buzas J., et al. A trauma mortality prediction model based on the anatomic injury scale. Ann Surg. 2008; 247(6): 1041–1048. DOI: 10.1097/SLA.0b013e31816ffb3f.
6. Steyerberg E., Vickers A., Cook N., et al. Assessing the performance of prediction models: A framework for traditional and novel measures. Epidemiology. 2010; 21(1): 128–138. DOI: 10.1097/EDE.0b013e3181c30fb2.
7. Rogers F., Osler T., Krasne M., et al. Has TRISS become an anachronism? A comparison of mortality between the National Trauma Data Bank and Major Trauma Outcome Study databases. J Trauma Acute Care Surg. 2012; 73(2): 326–331. DOI: 10.1097/TA.0b013e31825a7758.
8. Bailey T.C., Everson R.M., Fieldsend J.E., et al. Representing classifier confidence in the safety critical domain – an illustration from mortality prediction in trauma cases. Neur Comput Applicat. 2007; 16(1): 1–10. DOI: 10.1007/s00521-006-0053-y.
9. Negrin M.A., Nam J., Briggs A.H. Bayesian solutions for handling uncertainty in survival extrapolation. Med Decis Making. 2016. PII: 0272989X16650669. DOI: 10.1177/0272989X16650669.
10. Schetinin V., Jakaite L., Krzanowski W.J. Bayesian prediction for survival of patients: Study on the US national trauma data bank. Comput Methods Programs Biomed. 2013; 111(3): 602–612. DOI: 10.1016/j.cmpb.2013.05.015.
11. Schetinin V., Jakaite L., Krzanowski W.J. Prediction of survival probabilities with Bayesian decision trees. Exp Syst Applicat. 2013; 40(14): 5466–5476. DOI: 10.1016/j.eswa.2013.04.009.
12. Schetinin V., Jakaite L. TraumaCalc. Bayesian prediction of trauma survival. 2016. URL: http://www.traumacalc.org (Accessed Jul 01, 2016.)
13. Schetinin V., Jakaite L., Jakaitis J., Krzanowski W. Bayesian decision trees for predicting survival of patients: A study on the US national trauma data bank. Computer Methods and Programs in Biomedicine. 2013; 111(3): 602–612. DOI: http://dx.doi.org/10.1016/j.cmpb.2013.05.015.
Review
For citations:
Schetinin V.G., Jakaite L.I., Kuriakin V.F., Gorbachenko V.I. A NEW METHOD FOR PREDICTING SURVIVAL AND ESTIMATING UNCERTAINTY IN TRAUMA PATIENTS. Russian Sklifosovsky Journal "Emergency Medical Care". 2017;6(1):30-33. (In Russ.) https://doi.org/10.23934/2223-9022-2017-6-1-30-33
Views:
3452
Email this article 