Abstract
Previous studies have identified some clinical parameters for predicting long-term functional recovery and mortality after traumatic brain injury (TBI). Here, data mining methods were combined with serial Glasgow Coma Scale (GCS) scores and clinical and laboratory parameters to predict 6-month functional outcome and mortality in patients with TBI. Data of consecutive adult patients presenting at a trauma center with moderate-to-severe head injury were retrospectively analyzed. Clinical parameters including serial GCS measurements at emergency department, 7th day, and 14th day and laboratory data were included for analysis (n = 115). We employed artificial neural network (ANN), naïve Bayes (NB), decision tree, and logistic regression to predict mortality and functional outcomes at 6 months after TBI. Favorable functional outcome was achieved by 34.8 % of the patients, and overall 6-month mortality was 25.2 %. For 6-month functional outcome prediction, ANN was the best model, with an area under the receiver operating characteristic curve (AUC) of 96.13 %, sensitivity of 83.50 %, and specificity of 89.73 %. The best predictive model for mortality was NB with AUC of 91.14 %, sensitivity of 81.17 %, and specificity of 90.65 %. Sensitivity analysis demonstrated GCS measurements on the 7th and 14th day and difference between emergency room and 14th day GCS score as the most influential attributes both in mortality and functional outcome prediction models. Analysis of serial GCS measurements using data mining methods provided additional predictive information in relation to 6-month mortality and functional outcome in patients with moderate-to-severe TBI.
Similar content being viewed by others
References
Traumatic brain injury: Time to end the silence. Lancet Neurol. 9(4):331, 2010. doi:10.1016/S1474-4422(10)70069-7.
Ghajar, J., Traumatic brain injury. Lancet 356(9233):923–929, 2000. doi:10.1016/S0140-6736(00)02689-1.
Maas, A. I., Stocchetti, N., and Bullock, R., Moderate and severe traumatic brain injury in adults. Lancet Neurol. 7(8):728–741, 2008. doi:10.1016/S1474-4422(08)70164-9.
Roozenbeek, B., Chiu, Y. L., Lingsma, H. F., Gerber, L. M., Steyerberg, E. W., Ghajar, J., and Maas, A. I., Predicting 14-day mortality after severe traumatic brain injury: Application of the IMPACT models in the brain trauma foundation TBI-trac(R) New York State database. J. Neurotrauma 29(7):1306–1312, 2012. doi:10.1089/neu.2011.1988.
Perez, R., Costa, U., Torrent, M., Solana, J., Opisso, E., Caceres, C., Tormos, J. M., Medina, J., and Gomez, E. J., Upper limb portable motion analysis system based on inertial technology for neurorehabilitation purposes. Sensors (Basel) 10(12):10733–10751, 2010. doi:10.3390/s101210733.
Silver, J. M., McAllister, T. W., and Yudofsky, S. C., Textbook of traumatic brain injury, 2nd edition. American Psychiatric Pub, Washington, DC, 2011.
Brown, A. W., Malec, J. F., McClelland, R. L., Diehl, N. N., Englander, J., and Cifu, D. X., Clinical elements that predict outcome after traumatic brain injury: A prospective multicenter recursive partitioning (decision-tree) analysis. J. Neurotrauma 22(10):1040–1051, 2005. doi:10.1089/neu.2005.22.1040.
Lingsma, H. F., Roozenbeek, B., Steyerberg, E. W., Murray, G. D., and Maas, A. I., Early prognosis in traumatic brain injury: From prophecies to predictions. Lancet Neurol. 9(5):543–554, 2010. doi:10.1016/S1474-4422(10)70065-X.
Eftekhar, B., Mohammad, K., Ardebili, H. E., Ghodsi, M., and Ketabchi, E., Comparison of artificial neural network and logistic regression models for prediction of mortality in head trauma based on initial clinical data. BMC Med. Inf. Decis. Making 5:3, 2005. doi:10.1186/1472-6947-5-3.
Wyatt, J. C., and Altman, D. G., Prognostic models: Clinically useful or quickly forgotten? Brit. M. J. 311:1539–1541, 1995.
Rovlias, A., and Kotsou, S., Classification and regression tree for prediction of outcome after severe head injury using simple clinical and laboratory variables. J. Neurotrauma 21(7):886–893, 2004. doi:10.1089/0897715041526249.
Quigley, M. R., Vidovich, D., Cantella, D., Wilberger, J. E., Maroon, J. C., and Diamond, D., Defining the limits of survivorship after very severe head injury. J. Trauma 42(1):7–10, 1997.
Schreiber, M. A., Aoki, N., Scott, B. G., and Beck, J. R., Determinants of mortality in patients with severe blunt head injury. Arch. Surg. 137(3):285–290, 2002.
Rimel, R. W., Jane, J. A., and Edlich, R. F., An injury severity scale for comprehensive management of central nervous system trauma. JACEP 8(2):64–67, 1979.
Knaus, W. A., Draper, E. A., Wagner, D. P., and Zimmerman, J. E., APACHE II: A severity of disease classification system. Crit. Care Med. 13(10):818–829, 1985.
Teasdale, G., and Jennett, B., Assessment of coma and impaired consciousness. A practical scale. Lancet 2(7872):81–84, 1974.
Collaborators, M. C. T., Perel, P., Arango, M., Clayton, T., Edwards, P., Komolafe, E., Poccock, S., Roberts, I., Shakur, H., Steyerberg, E., and Yutthakasemsunt, S., Predicting outcome after traumatic brain injury: Practical prognostic models based on large cohort of international patients. BMJ 336(7641):425–429, 2008. doi:10.1136/bmj.39461.643438.25.
Roozenbeek, B., Lingsma, H. F., Lecky, F. E., Lu, J., Weir, J., Butcher, I., McHugh, G. S., Murray, G. D., Perel, P., Maas, A. I., Steyerberg, E. W., and International Mission on Prognosis Analysis of Clinical Trials in Traumatic Brain Injury Study G, Corticosteroid Randomisation After Significant Head Injury Trial C, Trauma A, Research N, Prediction of outcome after moderate and severe traumatic brain injury: External validation of the International Mission on Prognosis and Analysis of Clinical Trials (IMPACT) and Corticoid Randomisation after Significant Head injury (CRASH) prognostic models. Crit. Care Med. 40(5):1609–1617, 2012. doi:10.1097/CCM.0b013e31824519ce.
Duncan, R., and Thakore, S., Decreased Glasgow Coma Scale score does not mandate endotracheal intubation in the emergency department. J. Emerg. Med. 37(4):451–455, 2009. doi:10.1016/j.jemermed.2008.11.026.
Jain, S., Dharap, S. B., and Gore, M. A., Early prediction of outcome in very severe closed head injury. Injury 39(5):598–603, 2008. doi:10.1016/j.injury.2007.06.003.
Marmarou, A., Lu, J., Butcher, I., McHugh, G. S., Murray, G. D., Steyerberg, E. W., Mushkudiani, N. A., Choi, S., and Maas, A. I., Prognostic value of the Glasgow Coma Scale and pupil reactivity in traumatic brain injury assessed pre-hospital and on enrollment: An IMPACT analysis. J. Neurotrauma 24(2):270–280, 2007. doi:10.1089/neu.2006.0029.
Steyerberg, E. W., Mushkudiani, N., Perel, P., Butcher, I., Lu, J., McHugh, G. S., Murray, G. D., Marmarou, A., Roberts, I., Habbema, J. D., and Maas, A. I., Predicting outcome after traumatic brain injury: Development and international validation of prognostic scores based on admission characteristics. PLoS Med. 5(8):e165, 2008. doi:10.1371/journal.pmed.0050165. discussion e165.
Stevens, R. D., and Sutter, R., Prognosis in severe brain injury. Crit. Care Med. 41(4):1104–1123, 2013. doi:10.1097/CCM.0b013e318287ee79.
Galanaud, D., Perlbarg, V., Gupta, R., Stevens, R. D., Sanchez, P., Tollard, E., de Champfleur, N. M., Dinkel, J., Faivre, S., Soto-Ares, G., Veber, B., Cottenceau, V., Masson, F., Tourdias, T., Andre, E., Audibert, G., Schmitt, E., Ibarrola, D., Dailler, F., Vanhaudenhuyse, A., Tshibanda, L., Payen, J. F., Le Bas, J. F., Krainik, A., Bruder, N., Girard, N., Laureys, S., Benali, H., Puybasset, L., and Neuro Imaging for Coma E, Recovery C, Assessment of white matter injury and outcome in severe brain trauma: A prospective multicenter cohort. Anesthesiology 117(6):1300–1310, 2012. doi:10.1097/ALN.0b013e3182755558.
Han, J., and Kamber, M., Data mining: concepts and techniques. Diane Cerra, San Francisco, CA, 2006.
Bellazzi, R., and Zupan, B., Predictive data mining in clinical medicine: Current issues and guidelines. Int. J. Med. Inform. 77(2):81–97, 2008. doi:10.1016/j.ijmedinf.2006.11.006.
Meisel, S., and Mattfeld, D., Synergies of operations research and data mining. Eur. J. Oper. Res. 206(1):1–10, 2010. doi:10.1016/j.ejor.2009.10.017.
Ramesh, A. N., Kambhampati, C., Monson, J. R., and Drew, P. J., Artificial intelligence in medicine. Ann. R. Coll. Surg. Engl. 86(5):334–338, 2004. doi:10.1308/147870804290.
Ting, H., Mai, Y. T., Hsu, H. C., Wu, H. C., and Tseng, M. H., Decision tree based diagnostic system for moderate to severe obstructive sleep apnea. J. Med. Syst. 38(9):94, 2014. doi:10.1007/s10916-014-0094-1.
Keltch, B., Lin, Y., and Bayrak, C., Comparison of AI techniques for prediction of liver fibrosis in hepatitis patients. J. Med. Syst. 38(8):60, 2014. doi:10.1007/s10916-014-0060-y.
Sen, B., Peker, M., Cavusoglu, A., and Celebi, F. V., A comparative study on classification of sleep stage based on EEG signals using feature selection and classification algorithms. J. Med. Syst. 38(3):18, 2014. doi:10.1007/s10916-014-0018-0.
Maas, A. I., Hukkelhoven, C. W., Marshall, L. F., and Steyerberg, E. W., Prediction of outcome in traumatic brain injury with computed tomographic characteristics: A comparison between the computed tomographic classification and combinations of computed tomographic predictors. Neurosurgery 57(6):1173–1182, 2005. discussion 1173–1182.
Segal, M. E., Goodman, P. H., Goldstein, R., Hauck, W., Whyte, J., Graham, J. W., Polansky, M., and Hammond, F. M., The accuracy of artificial neural networks in predicting long-term outcome after traumatic brain injury. J. Head Trauma Rehabil. 21(4):298–314, 2006.
Lee, S. Y., Kim, S. S., Kim, C. H., Park, S. W., Park, J. H., and Yeo, M., Prediction of outcome after traumatic brain injury using clinical and neuroimaging variables. J. Clin. Neurol. 8(3):224–229, 2012. doi:10.3988/jcn.2012.8.3.224.
Jennett, B., Teasdale, G., Galbraith, S., Pickard, J., Grant, H., Braakman, R., Avezaat, C., Maas, A., Minderhoud, J., Vecht, C. J., Heiden, J., Small, R., Caton, W., and Kurze, T., Severe head injuries in three countries. J. Neurol. Neurosurg. Psychiatry 40(3):291–298, 1977.
Jennett, B., Snoek, J., Bond, M. R., and Brooks, N., Disability after severe head injury: Observations on the use of the Glasgow Outcome Scale. J. Neurol. Neurosurg. Psychiatry 44(4):285–293, 1981.
Overgaard, J., Hvid-Hansen, O., Land, A. M., Pedersen, K. K., Christensen, S., Haase, J., Hein, O., and Tweed, W. A., Prognosis after head injury based on early clinical examination. Lancet 2(7830):631–635, 1973.
Becker, D. P., Miller, J. D., Ward, J. D., Greenberg, R. P., Young, H. F., and Sakalas, R., The outcome from severe head injury with early diagnosis and intensive management. J. Neurosurg. 47(4):491–502, 1977. doi:10.3171/jns.1977.47.4.0491.
Carlsson, C. A., von Essen, C., and Lofgren, J., Factors affecting the clinical corse of patients with severe head injuries. 1. Influence of biological factors. 2. Significance of posttraumatic coma. J. Neurosurg. 29(3):242–251, 1968. doi:10.3171/jns.1968.29.3.0242.
Bowers, S. A., and Marshall, L. F., Outcome in 200 consecutive cases of severe head injury treated in San Diego County: A prospective analysis. Neurosurgery 6(3):237–242, 1980.
Levati, A., Farina, M. L., Vecchi, G., Rossanda, M., and Marrubini, M. B., Prognosis of severe head injuries. J. Neurosurg. 57(6):779–783, 1982. doi:10.3171/jns.1982.57.6.0779.
Mazumdar, M., and Glassman, J. R., Categorizing a prognostic variable: Review of methods, code for easy implementation and applications to decision-making about cancer treatments. Stat. Med. 19(1):113–132, 2000.
Shrout, P. E., and Fleiss, J. L., Intraclass correlations: Uses in assessing rater reliability. Psychol. Bull. 86(2):420–428, 1979.
Lin, C. C., Ou, Y. K., Chen, S. H., Liu, Y. C., and Lin, J., Comparison of artificial neural network and logistic regression models for predicting mortality in elderly patients with hip fracture. Injury 41(8):869–873, 2010. doi:10.1016/j.injury.2010.04.023.
Patterson, D. W., Artificial neural networks: theory and applications. Prentice Hall, Singapore, New York, 1996.
Quinlan, J. R., C4.5: programs for machine learning. Morgan Kaufmann, San Francisco, 1993.
Breiman, L., Classification and regression trees. Wadsworth statistics/probability series. Wadsworth International Group, Belmont, Calif., 1984.
Podgorelec, V., Kokol, P., Stiglic, B., and Rozman, I., Decision trees: An overview and their use in medicine. J. Med. Syst., Kluwer Academic/Plenum Press 26(5):445–463, 2002.
Quinlan, J. R., Induction of decision trees. Mach. Learn. 1:81–106, 1986.
Polat, K., Sahan, S., and Gunes, S., A new method to medical diagnosis: Artificial immune recognition system (AIRS) with fuzzy weighted pre-processing and application to ECG arrhythmia. Expert Syst. Appl. 31(2):264–269, 2006. doi:10.1016/j.eswa.2005.09.019.
Bengio, Y., and Grandvalet, Y., No unbiased estimator of the variance of K-fold cross-validation. J. Mach. Learn. Res. 5:1089–1105, 2004.
Stone, M., Cross-validatory choice and assessment of statistical predictions. J. R. Stat. Soc. 36(1):111–147, 1974.
Efron, B., and Tibshirani, R., Improvements on cross-validation: The. 632+ bootstrap method. J. Am. Stat. Assoc. 92(438):548–560, 1997.
Frawley, W. J., Paitetsky-Shapiro, G., and Matheus, C. J. Advances in knowledge discovery and data mining. In: Fayyad, U. M. (Ed.), From Data Mining to Knowledge Discovery: An Overview. AAAI Press/The MIT Press, p 661–620, 1996.
Breiman, L., Friedman, J., Olshen, R., and Stone, C., Classification and regression trees. Wadsworth, Belmont, CA, 1984.
Dreiseitl, S., and Ohno-Machado, L., Logistic regression and artificial neural network classification models: A methodology review. J. Biomed. Inform. 35(5–6):352–359, 2002.
Altman, D. G., and Bland, J. M., Diagnostic tests 3: Receiver operating characteristic plots. BMJ 309(6948):188, 1994.
Akobeng, A. K., Understanding diagnostic tests 1: Sensitivity, specificity and predictive values. Acta Paediatr. 96(3):338–341, 2007. doi:10.1111/j.1651-2227.2006.00180.x.
Code, C., Rowley, D., and Kertesz, A., Predicting recovery from aphasia with connectionist networks: Preliminary comparisons with multiple regression. Cortex 30(3):527–532, 1994.
Narayan, R. K., Greenberg, R. P., Miller, J. D., Enas, G. G., Choi, S. C., Kishore, P. R., Selhorst, J. B., Lutz, H. A., 3rd, and Becker, D. P., Improved confidence of outcome prediction in severe head injury. A comparative analysis of the clinical examination, multimodality evoked potentials, CT scanning, and intracranial pressure. J. Neurosurg. 54(6):751–762, 1981. doi:10.3171/jns.1981.54.6.0751.
Hoffmann, M., Lefering, R., Rueger, J. M., Kolb, J. P., Izbicki, J. R., Ruecker, A. H., Rupprecht, M., Lehmann, W., and Trauma Registry of the German Society for Trauma S, Pupil evaluation in addition to Glasgow Coma Scale components in prediction of traumatic brain injury and mortality. Br. J. Surg. 99(Suppl 1):122–130, 2012. doi:10.1002/bjs.7707.
Signorini, D. F., Andrews, P. J., Jones, P. A., Wardlaw, J. M., and Miller, J. D., Predicting survival using simple clinical variables: A case study in traumatic brain injury. J. Neurol. Neurosurg. Psychiatry 66(1):20–25, 1999.
Lesko, M. M., Jenks, T., O’Brien, S. J., Childs, C., Bouamra, O., Woodford, M., and Lecky, F., Comparing model performance for survival prediction using total Glasgow Coma Scale and its components in traumatic brain injury. J. Neurotrauma 30(1):17–22, 2013. doi:10.1089/neu.2012.2438.
Nelson, D. W., Rudehill, A., MacCallum, R. M., Holst, A., Wanecek, M., Weitzberg, E., and Bellander, B. M., Multivariate outcome prediction in traumatic brain injury with focus on laboratory values. J. Neurotrauma 29(17):2613–2624, 2012. doi:10.1089/neu.2012.2468.
Leitgeb, J., Mauritz, W., Brazinova, A., Majdan, M., Janciak, I., Wilbacher, I., and Rusnak, M., Glasgow Coma Scale score at intensive care unit discharge predicts the 1-year outcome of patients with severe traumatic brain injury. Eur. J. Trauma Emerg. Surg. 39(3):285–292, 2013. doi:10.1007/s00068-013-0269-3.
Deeks, J. J., and Altman, D. G., Diagnostic tests 4: Likelihood ratios. BMJ 329:168–169, 2004.
Dujardin, B., Ende, J. V., Gompel, A. V., Unger, J.-P., and Stuyft, P. V. D., Likelihood ratios: A real improvement for clinical decision making? Eur. J. Epidemiol. 10:29–36, 1994.
Gill, C. J., Sabin, L., and Schmid, C. H., Why clinicians are natural Bayesians. BMJ 330(7499):1080–1083, 2005.
Akobeng, A. K., Understanding diagnostic tests 2: Likelihood ratios, pre- and post-test probabilities and their use in clinical practice. Acta Paediatr. 96(4):487–491, 2007. doi:10.1111/j.1651-2227.2006.00179.x.
Author information
Authors and Affiliations
Corresponding author
Additional information
This article is part of the Topical Collection on Systems-Level Quality Improvement
Rights and permissions
About this article
Cite this article
Lu, HY., Li, TC., Tu, YK. et al. Predicting Long-Term Outcome After Traumatic Brain Injury Using Repeated Measurements of Glasgow Coma Scale and Data Mining Methods. J Med Syst 39, 14 (2015). https://doi.org/10.1007/s10916-014-0187-x
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10916-014-0187-x