Electromyographic reactivity measured with scalp-EEG contributes to prognostication after cardiac arrest

Caporro, Matteo; Rossetti, Andrea O.; Seiler, Andrea; Kustermann, Thomas; Nguissi, Nathalie Ata Nguepnjo; Pfeiffer, Christian; Zimmermann, Rebekka; Hænggi, Matthias; Oddo, Mauro; Lucia, Marzia De; Zubler, Frédéric

doi:10.1016/j.resuscitation.2019.03.014

Cited by 16 publications

(13 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Thirteen studies [ 52 , 55 , 57 , 59 , 68 , 70 , 72 , 90 , 93 , 98 , 104 , 110 , 111 ] combined EEG features to assess FPR of poor neurological outcome and labelled these as highly malignant patterns. These patterns included isoelectric or low-voltage EEG, suppression, burst suppression (either generic or restricted to the identical bursts subtype), and generalised or continuous periodic discharges in combination with suppression.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of poor neurological outcome in comatose survivors of cardiac arrest: a systematic review

et al. 2020

Self Cite

View full text Add to dashboard Cite

Purpose: To assess the ability of clinical examination, blood biomarkers, electrophysiology, or neuroimaging assessed within 7 days from return of spontaneous circulation (ROSC) to predict poor neurological outcome, defined as death, vegetative state, or severe disability (CPC 3-5) at hospital discharge/1 month or later, in comatose adult survivors from cardiac arrest (CA). Methods: PubMed, EMBASE, Web of Science, and the Cochrane Database of Systematic Reviews (January 2013-April 2020) were searched. Sensitivity and false-positive rate (FPR) for each predictor were calculated. Due to heterogeneities in recording times, predictor thresholds, and definition of some predictors, meta-analysis was not performed. Results: Ninety-four studies (30,200 patients) were included. Bilaterally absent pupillary or corneal reflexes after day 4 from ROSC, high blood values of neuron-specific enolase from 24 h after ROSC, absent N20 waves of short-latency somatosensory-evoked potentials (SSEPs) or unequivocal seizures on electroencephalogram (EEG) from the day of ROSC, EEG background suppression or burst-suppression from 24 h after ROSC, diffuse cerebral oedema on brain CT from 2 h after ROSC, or reduced diffusion on brain MRI at 2-5 days after ROSC had 0% FPR for poor outcome in most studies. Risk of bias assessed using the QUIPS tool was high for all predictors. Conclusion: In comatose resuscitated patients, clinical, biochemical, neurophysiological, and radiological tests have a potential to predict poor neurological outcome with no false-positive predictions within the first week after CA. Guidelines should consider the methodological concerns and limited sensitivity for individual modalities. (PROSPERO CRD42019141169

show abstract

Section: Resultsmentioning

confidence: 99%

“…Assessment of reactivity is prone to variability. In one study we included, the kappa for reactivity among the investigators was 0.74 [55] (ESM Table E9), but it was only 0.26 in another study [153].…”

Section: Eeg Background Reactivitymentioning

confidence: 99%

Prediction of poor neurological outcome in comatose survivors of cardiac arrest: a systematic review

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, EEG plays a decisive role in WLST decision mainly in patients with HIE. The majority of patients with HIE were recruited in Lausanne and Bern, where according to current guidelines, the first EEG (the one used for analysis in the present study) is usually not considered for decision to WLST [6,54]. In patients with other etiologies, EEG is not a primary tool for clinical prognostication; therefore, the risk of self-fulfilling prophecy is probably limited.…”

Section: Strengths and Limitationsmentioning

confidence: 99%

Standardized visual EEG features predict outcome in patients with acute consciousness impairment of various etiologies

et al. 2020

Self Cite

View full text Add to dashboard Cite

Background Early prognostication in patients with acute consciousness impairment is a challenging but essential task. Current prognostic guidelines vary with the underlying etiology. In particular, electroencephalography (EEG) is the most important paraclinical examination tool in patients with hypoxic ischemic encephalopathy (HIE), whereas it is not routinely used for outcome prediction in patients with traumatic brain injury (TBI). Method Data from 364 critically ill patients with acute consciousness impairment (GCS ≤ 11 or FOUR ≤ 12) of various etiologies and without recent signs of seizures from a prospective randomized trial were retrospectively analyzed. Random forest classifiers were trained using 8 visual EEG features—first alone, then in combination with clinical features—to predict survival at 6 months or favorable functional outcome (defined as cerebral performance category 1–2). Results The area under the ROC curve was 0.812 for predicting survival and 0.790 for predicting favorable outcome using EEG features. Adding clinical features did not improve the overall performance of the classifier (for survival: AUC = 0.806, p = 0.926; for favorable outcome: AUC = 0.777, p = 0.844). Survival could be predicted in all etiology groups: the AUC was 0.958 for patients with HIE, 0.955 for patients with TBI and other neurosurgical diagnoses, 0.697 for patients with metabolic, inflammatory or infectious causes for consciousness impairment and 0.695 for patients with stroke. Training the classifier separately on subgroups of patients with a given etiology (and thus using less training data) leads to poorer classification performance. Conclusions While prognostication was best for patients with HIE and TBI, our study demonstrates that similar EEG criteria can be used in patients with various causes of consciousness impairment, and that the size of the training set is more important than homogeneity of ACI etiology.

show abstract

“…The reason for the error becomes clear when we note that the EEG was recorded very early (13 hr after CA). It is well known that in the very acute phase or under sedation, a burst‐suppression pattern is not always associated with an unfavorable outcome (Caporro et al, ; Cloostermans, van Meulen, Eertman, Hom, & van Putten, ). Using an EEG recorded at a later stage might help solve this particular problem.…”

Section: Discussionmentioning

confidence: 99%

EEG‐based outcome prediction after cardiac arrest with convolutional neural networks: Performance and visualization of discriminative features

Jonas

Rossetti

Oddo

et al. 2019

Human Brain Mapping

Self Cite

View full text Add to dashboard Cite

Prognostication for comatose patients after cardiac arrest is a difficult but essential task. Currently, visual interpretation of electroencephalogram (EEG) is one of the main modality used in outcome prediction. There is a growing interest in computer‐assisted EEG interpretation, either to overcome the possible subjectivity of visual interpretation, or to identify complex features of the EEG signal. We used a one‐dimensional convolutional neural network (CNN) to predict functional outcome based on 19‐channel‐EEG recorded from 267 adult comatose patients during targeted temperature management after CA. The area under the receiver operating characteristic curve (AUC) on the test set was 0.885. Interestingly, model architecture and fine‐tuning only played a marginal role in classification performance. We then used gradient‐weighted class activation mapping (Grad‐CAM) as visualization technique to identify which EEG features were used by the network to classify an EEG epoch as favorable or unfavorable outcome, and also to understand failures of the network. Grad‐CAM showed that the network relied on similar features than classical visual analysis for predicting unfavorable outcome (suppressed background, epileptiform transients). This study confirms that CNNs are promising models for EEG‐based prognostication in comatose patients, and that Grad‐CAM can provide explanation for the models' decision‐making, which is of utmost importance for future use of deep learning models in a clinical setting.

show abstract

Electromyographic reactivity measured with scalp-EEG contributes to prognostication after cardiac arrest

Cited by 16 publications

References 29 publications

Prediction of poor neurological outcome in comatose survivors of cardiac arrest: a systematic review

Prediction of poor neurological outcome in comatose survivors of cardiac arrest: a systematic review

Standardized visual EEG features predict outcome in patients with acute consciousness impairment of various etiologies

EEG‐based outcome prediction after cardiac arrest with convolutional neural networks: Performance and visualization of discriminative features

Contact Info

Product

Resources

About