Skip to main page content
Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
, 23 (1), 401

Predicting Outcome in Patients With Moderate to Severe Traumatic Brain Injury Using Electroencephalography

Affiliations

Predicting Outcome in Patients With Moderate to Severe Traumatic Brain Injury Using Electroencephalography

Marjolein E Haveman et al. Crit Care.

Abstract

Background: Better outcome prediction could assist in reliable quantification and classification of traumatic brain injury (TBI) severity to support clinical decision-making. We developed a multifactorial model combining quantitative electroencephalography (qEEG) measurements and clinically relevant parameters as proof of concept for outcome prediction of patients with moderate to severe TBI.

Methods: Continuous EEG measurements were performed during the first 7 days of ICU admission. Patient outcome at 12 months was dichotomized based on the Extended Glasgow Outcome Score (GOSE) as poor (GOSE 1-2) or good (GOSE 3-8). Twenty-three qEEG features were extracted. Prediction models were created using a Random Forest classifier based on qEEG features, age, and mean arterial blood pressure (MAP) at 24, 48, 72, and 96 h after TBI and combinations of two time intervals. After optimization of the models, we added parameters from the International Mission for Prognosis And Clinical Trial Design (IMPACT) predictor, existing of clinical, CT, and laboratory parameters at admission. Furthermore, we compared our best models to the online IMPACT predictor.

Results: Fifty-seven patients with moderate to severe TBI were included and divided into a training set (n = 38) and a validation set (n = 19). Our best model included eight qEEG parameters and MAP at 72 and 96 h after TBI, age, and nine other IMPACT parameters. This model had high predictive ability for poor outcome on both the training set using leave-one-out (area under the receiver operating characteristic curve (AUC) = 0.94, specificity 100%, sensitivity 75%) and validation set (AUC = 0.81, specificity 75%, sensitivity 100%). The IMPACT predictor independently predicted both groups with an AUC of 0.74 (specificity 81%, sensitivity 65%) and 0.84 (sensitivity 88%, specificity 73%), respectively.

Conclusions: Our study shows the potential of multifactorial Random Forest models using qEEG parameters to predict outcome in patients with moderate to severe TBI.

Keywords: EEG; ICU; Prognosis; Random forest; Traumatic brain injury.

Conflict of interest statement

MP is the co-founder of Clinical Science Systems, a supplier of EEG systems for Medisch Spectrum Twente. Clinical Science Systems offered no funding and was not involved in the design, execution, analysis, interpretation, or publication of the study. The remaining authors declare that they do not have competing interests.

Figures

Fig. 1
Fig. 1
Flow diagram for inclusion and exclusion of eligible patients. Exclusion criteria were trauma following or combined with severe circulatory failure (cardiac arrest/cerebral hemorrhage), earlier TBI or CVA without full recovery, progressive brain illness (tumor, neurodegenerative disease), or limited life expectancy (< 6 months) prior to TBI. Besides, patients were not included because of practical reasons, for example, if the research team was not aware of the admission of a patient
Fig. 2
Fig. 2
Receiver operating characteristic (ROC) curves with 50% confidence interval of our best models with and without IMPACT features and the online International Mission for Prognosis And Clinical Trial Design (IMPACT) predictions of poor outcome (Extended Glasgow Outcome Scale 1–2) in the training set (38 patients) and validation set (19 patients). The red dots indicate the threshold at which the sensitivity and specificity are best. The area under the curve (AUC) of the model with IMPACT features was higher than our best model without those and similar to the impact predictor alone. The sensitivity and specificity of our best model with IMPACT parameters are slightly higher than those of the IMPACT predictor alone in both the training and the validation sets
Fig. 3
Fig. 3
Feature contribution of the best models at 72 + 96 h after traumatic brain injury. Mean amplitude of the electroencephalography (std), age, and mean arterial blood pressure (MAP) were important features. Glucose level at admission strongly contributed to the predictive ability of the models. Pupillary reactivity (pupils), hypotension, hypoxia, and the presence of epidural hematoma or traumatic subdural hemorrhage at the CT scan (CT-EDH and CT-tSAH respectively) were the least relevant features. The bars indicate the contribution of the features in the prediction of good or poor outcome

Similar articles

See all similar articles

References

    1. Maas AIR, Menon DK, Adelson PD, Andelic N, Bell MJ, Belli A, et al. Traumatic brain injury: integrated approaches to improve prevention, clinical care, and research. Lancet Neurol. 2017;16:987–1048. doi: 10.1016/S1474-4422(17)30371-X. - DOI - PubMed
    1. Murray GD, Butcher I, McHugh GS, Lu J, Mushkudiani NA, Maas AIR, et al. Multivariable prognostic analysis in traumatic brain injury: results from the IMPACT study. J Neurotrauma. 2007;24:329–337. doi: 10.1089/neu.2006.0035. - DOI - PubMed
    1. Steyerberg EW, Mushkudiani N, Perel P, Butcher I, Lu J, McHugh GS, et al. Predicting outcome after traumatic brain injury: development and international validation of prognostic scores based on admission characteristics. PLoS Med. 2008;5:e165. doi: 10.1371/journal.pmed.0050165. - DOI - PMC - PubMed
    1. Ghajar J. Traumatic brain injury. Lancet. 2000;356:923–929. doi: 10.1016/S0140-6736(00)02689-1. - DOI - PubMed
    1. Young GB. The EEG in coma. J Clin Neurophysiol. 2000;17:473–485. doi: 10.1097/00004691-200009000-00006. - DOI - PubMed

LinkOut - more resources

Feedback