Identifying Important Attributes for Prognostic Prediction in Traumatic Brain Injury Patients

 

 Buy Article Permissions and Reprints

Summary

Background: Generally, traumatic brain injury (TBI) patients do not have a stable condition, particularly after the first week of TBI. Hence, indicating the attributes in prognosis through a prediction model is of utmost importance since it helps caregivers with treatment-decision options, or prepares the relatives for the most-likely outcome. Objectives: This study attempted to determine and order the attributes in prognostic prediction in TBI patients, based on early clinical findings. A hybrid method was employed, which combines a decision tree (DT) and an artificial neural network (ANN) in order to improve the modeling process. Methods: The DT approach was applied as the initial analysis of the network architecture to increase accuracy in prediction. Afterwards, the ANN structure was mapped from the initial DT based on a part of the data. Subsequently, the designed network was trained and validated by the remaining data. 5-fold cross-validation method was applied to train the network. The area under the receiver operating characteristic (ROC) curve, sensitivity, specificity, and accuracy rate were utilized as performance measures. The important attributes were then determined from the trained network using two methods: change of mean squared error (MSE), and sensitivity analysis (SA). Results: The hybrid method offered better results compared to the DT method. The accuracy rate of 86.3 % vs. 82.2 %, sensitivity value of 55.1 % vs. 47.6 %, specificity value of 93.6 % vs. 91.1 %, and the area under the ROC curve of 0.705 vs. 0.695 were achieved for the hybrid method and DT, respectively. However, the attributes’ order by DT method was more consistent with the clinical literature. Conclusions: The combination of different modeling methods can enhance their performance. However, it may create some complexities in computations and interpretations. The outcome of the present study could deliver some useful hints in prognostic prediction on the basis of early clinical findings for TBI patients.

• References

• 1 Witten IH, Frank E. Data Mining: Practical machine learning tools and techniques. 2nd ed. San Francisco: Morgan Kaufmann Publishers; 2005
  Google Scholar
• 2 Seifert JW. editor. Data mining and homeland security: An overview. 2007 DTIC Document.
  PubMedGoogle Scholar
• 3 Bellazzi R, Zupan B. Predictive data mining in clinical medicine: current issues and guidelines. Int J Med Inform 2008; 77 (Suppl. 02) 81-97.
  CrossrefPubMedGoogle Scholar
• 4 Sakai S, Kobayashi K, Nakamura J, Toyabe S, Akazawa K. Accuracy in the Diagnostic Prediction of Acute Appendicitis Based on the Bayesian Network Model. Methods Inf Med 2007; 46 (Suppl. 06) 723-726.
  Article in Thieme ConnectPubMedGoogle Scholar
• 5 Pourahmad S, Azad M, Paydar S. Diagnosis of Malignancy in Thyroid Tumors by Multi-Layer Perceptron Neural Networks With Different Batch Learning Algorithms. Glob J Health Sci 2015; 7 (Suppl. 06) 46-54.
  PubMedGoogle Scholar
• 6 Eftekhar B, Mohammad K, Ardebili HE, Ghodsi M, 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 Inform Decis Mak 2005; 5 (Suppl. 01) 3.
  CrossrefPubMedGoogle Scholar
• 7 Khosravi B, Pourahmad S, Bahreini A, Nikeghbalian S, Mehrdad G. Five Years Survival of Patients After Liver Transplantation and Its Effective Factors by Neural Network and Cox Poroportional Hazard Regression Models. Hepat Mon 2015; 15 (Suppl. 09) e25164.
  PubMedGoogle Scholar
• 8 Zhu K, Lou Z, Zhou J, Ballester N, Kong N, Parikh P. Predicting 30-day Hospital Readmission with Publicly Available Administrative Database. Methods Inf Med 2015; 54 (Suppl. 06) 560-567.
  Article in Thieme ConnectPubMedGoogle Scholar
• 9 Pourahmad S, Safarpour AR, Bananzadeh A, Rahimikazerooni S, Zabangirfard Z. A Pilot study on Prediction of Pouchitis in Ulcerative Colitis Patients by Decision Tree Method Versus Logistic Regression Analysis. Ann Colorectal Res 2013 1. 02
  PubMedGoogle Scholar
• 10 Peña Y, Fernández-Britto JE, Bacallao J, Batista JF, León MLd. Lipid levels as predictors of silent myocardial ischemia in a type 2 diabetic population in Havana. MEDICC review 2012; 14 (Suppl. 01) 18-24.
  PubMedGoogle Scholar
• 11 Liu C, Pan C, Shen J, Wang H, Yong L. MALDITOF MS combined with magnetic beads for detecting serum protein biomarkers and establishment of boosting decision tree model for diagnosis of colorectal cancer. Int J Med Sci 2011; 8 (Suppl. 01) 39-47.
  CrossrefPubMedGoogle Scholar
• 12 Jerez-Aragonés JM, Gómez-Ruiz JA, Ramos-Jiménez G, Muñoz-Pérez J, Alba-Conejo E. A combined neural network and decision trees model for prognosis of breast cancer relapse. Artif Intell Med 2003; 27 (Suppl. 01) 45-63.
  CrossrefPubMedGoogle Scholar
• 13 Bozsik J. Decision tree combined with neural networks for financial forecast. Electrical Engineering 2013; 55 3–4 95-101.
  PubMedGoogle Scholar
• 14 Rahimi I, Behmanesh R. Improve poultry farm efficiency in Iran: using combination neural networks, decision trees, and data envelopment analysis (DEA). International Journal of Applied Operational Research 2012; 2 (Suppl. 03) 69-84.
  PubMedGoogle Scholar
• 15 Sethi IK. Entropy nets: From decision trees to neural networks. Proceedings of the IEEE 1990; 78 (Suppl. 10) 1605-13.
  CrossrefPubMedGoogle Scholar
• 16 Oh H, Seo W. Functional and Cognitive Recovery of Patients With Traumatic Brain Injury Prediction Tree Model Versus General Model. Crit Care Nurse 2009; 29 (Suppl. 04) 12-22.
  PubMedGoogle Scholar
• 17 Bell KR, Brockway JA, Hart T, Whyte J, Sherer M, Fraser RT. et al. Scheduled telephone intervention for traumatic brain injury: a multicenter randomized controlled trial. Arch Phys Med Rehabil 2011; 92 (Suppl. 10) 1552-60.
  CrossrefPubMedGoogle Scholar
• 18 Lingsma HF, Roozenbeek B, Steyerberg EW, Murray GD, Maas AIR. Early prognosis in traumatic brain injury: from prophecies to predictions. Lancet Neurol 2010; 9: 543-54.
  CrossrefPubMedGoogle Scholar
• 19 Lesko MM, Jenks T, O’Brien SJ, Childs C, Bouamra O, Woodford M. et al. Comparing model performance for survival prediction using total Glasgow Coma Scale and its components in traumatic brain injury. J Neurotrauma 2013; 30 (Suppl. 01) 17-22.
  CrossrefPubMedGoogle Scholar
• 20 Harrison D, Prabhu G, Grieve R, Harvey S, Sadique M, Gomes M. et al. Risk Adjustment In Neurocritical care (RAIN)-prospective validation of risk prediction models for adult patients with acute traumatic brain injury to use to evaluate the optimum location and comparative costs of neurocritical care: a cohort study. Health Technol Assess 2013; 17 (Suppl. 23) 1-350.
  PubMedGoogle Scholar
• 21 Pang BC, Kuralmani V, Joshi R, Hongli Y, Lee KK, Ang BT. et al. Hybrid outcome prediction model for severe traumatic brain injury. J Neurotrauma 2007; 24 (Suppl. 01) 136-46.
  CrossrefPubMedGoogle Scholar
• 22 Shibuya TY, Karam AM, Doerr T, Stachler RJ, Zor-meier M, Mathog RH. et al. Facial fracture repair in the traumatic brain injury patient. J Oral Maxillofac Surg 2007; 65 (Suppl. 09) 1693-9.
  CrossrefPubMedGoogle Scholar
• 23 Sobuwa S, Halzenberg H, Geduld H, Uys C. Predicting outcome in severe traumatic brain injury using a simple prognostic model. SAMJ: South African Medical Journal 2014; 104 (Suppl. 07) 492-4.
  PubMedGoogle Scholar
• 24 Subaiya S, Roberts I, Komolafe E, Perel P. Predicting intracranial hemorrhage after traumatic brain injury in low and middle-income countries: A prognostic model based on a large, multi-center, international cohort. BMC Emergency Medicine 2012; 12 (Suppl. 01) 17.
  CrossrefPubMedGoogle Scholar
• 25 Wong GKC, Teoh J, Yeung J, Chan E, Siu E, Woo P. et al. Outcomes of traumatic brain injury in Hong Kong: Validation with the TRISS, CRASH, and IMPACT models. J Clin Neurosci 2013; 20 (Suppl. 12) 1693-6.
  CrossrefPubMedGoogle Scholar
• 26 van der Ploeg T, Smits M, Dippel DW, Hunink M, Steyerberg EW. Prediction of intracranial findings on CT-scans by alternative modelling techniques. BMC Med Res Methodol 2011; 11 (Suppl. 01) 143.
  CrossrefPubMedGoogle Scholar
• 27 Marmarou A, Lu J, Butcher I, McHugh GS, Murray GD, Steyerberg EW. et al. 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 2007; 24 (Suppl. 02) 270-80.
  CrossrefPubMedGoogle Scholar
• 28 Jelodar S, Jafari P, Yadollahi M, SabetianJahromi G, Khalili H, Abbasi H, Bolandparvaz Sh, Paydar Sh. Potential Risk Factors of Death in Multiple Trauma Patients. Emerg (Tehran) 2014; 2 (Suppl. 04) 170-173.
  PubMedGoogle Scholar
• 29 Dolce G, Quintieri M, Serra S, Lagani V, Pignolo L. Clinical signs and early prognosis in vegetative state: a decisional tree, data-mining study. Brain Inj 2008; 22 7–8 617-23.
  CrossrefPubMedGoogle Scholar
• 30 Andrews PJ, Sleeman DH, Statham PF, McQuatt A, Corruble V, Jones PA. et al. Predicting recovery in patients suffering from traumatic brain injury by using admission variables and physiological data: a comparison between decision tree analysis and logistic regression. J Neurosurg 2002; 97 (Suppl. 02) 326-36.
  CrossrefPubMedGoogle Scholar
• 31 Sung A. Ranking importance of input parameters of neural networks. Expert Systems with Applications 1998; 15 (Suppl. 03) 405-11.
  CrossrefPubMedGoogle Scholar
• 32 Allison P. Alternatives to the Hosmer-Lemeshow Test. Statistical Horizons. 2014 April 9.
  PubMedGoogle Scholar
• 33 Kokol P, Pohorec S, Štiglic G, Podgorelec V. Evolutionary design of decision trees for medical application. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery 2012; 2 (Suppl. 03) 237-54.
  CrossrefPubMedGoogle Scholar
• 34 Kotsiantis SB. Decision trees: a recent overview. Artif Intell Rev 2013; 39: 261-283.
  CrossrefPubMedGoogle Scholar