Abstracts

Cerebral Recovery Index for prediction of neurological outcome after cardiac arrest

Abstract number : 3.102
Submission category : 3. Neurophysiology / 3B. ICU EEG
Year : 2016
Submission ID : 198087
Source : www.aesnet.org
Presentation date : 12/5/2016 12:00:00 AM
Published date : Nov 21, 2016, 18:00 PM

Authors :
Marleen C. Tjepkema-Cloostermans, Medisch Spectrum Twente, Enschede, The Netherlands., Netherlands; Jeannette Hofmeijer, University of Twente / Rijnstate hospital, Netherlands; Harold Hom, Medisch Spectrum Twente, Enschede, The Netherlands, Netherlands; M

Rationale: Early EEG measures contribute to outcome prediction of comatose patients after cardiac arrest (Hofmeijer et al, 2015). We present predictive values of a cerebral recovery index (CRI), based on a combination of qEEG measures, extracted every hour, and combined by the use of a random forest classifier. In previous work (Tjepkema-Cloostermans et al, 2013), the CRI was introduced. Here, we present a modified version, with improved performance and evaluated on a much larger dataset. Methods: In a cohort study, 283 consecutive comatose patients after cardiac arrest were included. Continuous EEG was recorded during the first three days. Outcome at 6 months was dichotomized as good (CPC 1-2) or poor (CPC 3-5). Nine qEEG measures were extracted. Patients were randomly divided over a training and validation set. Within the training set, a random forest classifier was fitted for each hour after cardiac arrest. Diagnostic accuracy was evaluated in the validation set. The relative contributions of resuscitation parameters and patient characteristics were evaluated. Results: The CRI ranges from 0 (prediction of death) to 1 (prediction of full recovery). Poor outcome could be predicted without false positives at a sensitivity of 56% at 12 hours after cardiac arrest. At 24 hours, a sensitivity of 65% at a specificity of 94% was obtained. Good neurological outcome could be predicted with sensitivities of 63 and 58% at specificities of 93 and 94% at 12 and 24 hours, respectively. Adding patient characteristics was of limited additional predictive value. Conclusions: A modifed CRI based on a combination of intermittently extracted, optimally combined qEEG measures provides unequalled prognostic value for comatose patients after cardiac arrest and enables bedside EEG interpretation of unexperienced readers. References Hofmeijer J, Beernink TM, Bosch FH, Beishuizen A, Tjepkema-Cloostermans MC, van Putten MJ Early EEG contributes to multimodal outcome prediction of postanoxic coma, Neurology. 2015 Jul 14;85(2):137-43 Tjepkema-Cloostermans MC, van Meulen FB, Meinsma G, van Putten MJ. A Cerebral Recovery Index (CRI) for early prognosis in patients after cardiac arrest. Crit Care. 2013 Oct 22;17(5): R252. Funding: none
Neurophysiology