Predictive value of EEG in postanoxic encephalopathy: A quantitative model-based approach

Efthymiou, Evdokia; Renzel, Roland; Baumann, Christian R.; Poryazova, Rositsa; Imbach, Lukas L.

doi:10.1016/j.resuscitation.2017.07.020

Cited by 11 publications

(6 citation statements)

References 30 publications

(39 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Another feature of the EEG that has been studied in the context of outcome prediction in comatose patients is spontaneous EEG variability . In comatose patients with varying etiologies, typically, less spontaneous variability is associated with worse outcomes . Possibly, spontaneous variability of the EEG, complementary to the stimulus‐induced EEG‐R, increases diagnostic accuracy.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Electroencephalographic reactivity as predictor of neurological outcome in postanoxic coma: A multicenter prospective cohort study

Admiraal

Rootselaar

Hofmeijer

et al. 2019

Annals of Neurology

View full text Add to dashboard Cite

Objective Outcome prediction in patients after cardiac arrest (CA) is challenging. Electroencephalographic reactivity (EEG‐R) might be a reliable predictor. We aimed to determine the prognostic value of EEG‐R using a standardized assessment. Methods In a prospective cohort study, a strictly defined EEG‐R assessment protocol was executed twice per day in adult patients after CA. EEG‐R was classified as present or absent by 3 EEG readers, blinded to patient characteristics. Uncertain reactivity was classified as present. Primary outcome was best Cerebral Performance Category score (CPC) in 6 months after CA, dichotomized as good (CPC = 1–2) or poor (CPC = 3–5). EEG‐R was considered reliable for predicting poor outcome if specificity was ≥95%. For good outcome prediction, a specificity of ≥80% was used. Added value of EEG‐R was the increase in specificity when combined with EEG background, neurological examination, and somatosensory evoked potentials (SSEPs). Results Of 160 patients enrolled, 149 were available for analyses. Absence of EEG‐R for poor outcome prediction had a specificity of 82% and a sensitivity of 73%. For good outcome prediction, specificity was 73% and sensitivity 82%. Specificity for poor outcome prediction increased from 98% to 99% when EEG‐R was added to a multimodal model. For good outcome prediction, specificity increased from 70% to 89%. Interpretation EEG‐R testing in itself is not sufficiently reliable for outcome prediction in patients after CA. For poor outcome prediction, it has no substantial added value to EEG background, neurological examination, and SSEPs. For prediction of good outcome, EEG‐R seems to have added value. ANN NEUROL 2019

show abstract

Section: Discussionmentioning

confidence: 99%

“…35 In comatose patients with varying etiologies, typically, less spontaneous variability is associated with worse outcomes. 35 In comatose patients with varying etiologies, typically, less spontaneous variability is associated with worse outcomes.…”

mentioning

confidence: 99%

Electroencephalographic reactivity as predictor of neurological outcome in postanoxic coma: A multicenter prospective cohort study

Admiraal

Rootselaar

Hofmeijer

et al. 2019

Annals of Neurology

View full text Add to dashboard Cite

show abstract

“…If the absence of malignant feature was a criteria for our network, this cannot be attributed to one specific region. EEG background variability is another EEG feature associated with favorable outcome (Efthymiou, Renzel, Baumann, Poryazova, & Imbach, ) which cannot be attributed to a specific location of the EEG. Background variability might have been used as discriminant feature by the network at the level of the all‐to‐all layer, however, this point cannot be investigated with the Grad‐CAM algorithm (perturbation of the input signal (Becker, Ackermann, Lapuschkin, Müller, & Samek, ) could be a complementary approach to test this hypothesis).…”

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

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

“…These patients were successfully categorized into those with excellent neurological prognosis (C1), intermediate neurological prognosis (C2), and very poor prognosis (C3, C4). Some variables of quantitative EEGs other than aEEG, such as burst suppression ratio, spectral variability and response entropy, have been reported to be associated with prognosis in patients post cardiac arrest [ 14 – 16 ]. However, to the best of our knowledge, classification of adult patients post cardiac arrest based on the pattern of their aEEG and the severity of hypoxic encephalopathy has not been suggested before.…”

Section: Discussionmentioning

confidence: 99%

Categorization of post-cardiac arrest patients according to the pattern of amplitude-integrated electroencephalography after return of spontaneous circulation

et al. 2018

View full text Add to dashboard Cite

BackgroundContinuous electroencephalography (cEEG), interpreted by an experienced neurologist, has been reported to be useful in predicting neurological outcome in adult patients post cardiac arrest. Amplitude-integrated electroencephalography (aEEG) is a type of quantitative EEG and is easily interpreted by a non-neurologist. A few studies have shown the effectiveness of aEEG in prognostication among adult patients post cardiac arrest. In this study, we hypothesized that the pattern of aEEG after return of spontaneous circulation (ROSC) could successfully categorize patients post cardiac arrest according to their expected neurological outcome.MethodsWe assessed the comatose survivors of out-of-hospital cardiac arrest who received targeted temperature management with midazolam-based sedation and were monitored with aEEG at our tertiary emergency care center from January 2013 to June 2017. We categorized the patients into categories 1 (C1) to 4 (C4). C1 included patients who regained continuous normal voltage (CNV) within 12 h post ROSC, C2 included those who recovered CNV 12–36 h post ROSC, C3 included those who did not recover CNV before 36 h post ROSC, and C4 included those who had burst suppression at any time post ROSC. We evaluated the outcomes of neurological function for each category at hospital discharge. A good outcome was defined as a cerebral performance category of 1 or 2.ResultsA total of 61 patients were assessed (median age, 60 years), among whom 42 (70%) had an initial shockable rhythm, and 52 (85%) had cardiac etiology. Of all 61 patients, 40 (66%) survived to hospital discharge and 27 (44%) had a good neurological outcome. Of 20 patients in C1, 19 (95%) had a good outcome, while the percentage dropped to 57% among C2 patients. No patients in C3 or C4 had a good outcome. Three patients could not be classified into any category.ConclusionsThe pattern of aEEG during the early post-cardiac-arrest period can successfully categorize patients according to their neurological prognoses and could be used as a potential guide to customize post-cardiac-arrest care for each patient.Electronic supplementary materialThe online version of this article (10.1186/s13054-018-2138-2) contains supplementary material, which is available to authorized users.

show abstract

Predictive value of EEG in postanoxic encephalopathy: A quantitative model-based approach

Abstract: Model-based quantitative EEG analysis (state space analysis) provides a novel, complementary marker for prognosis in postanoxic encephalopathy.

Cited by 11 publications

References 30 publications

Electroencephalographic reactivity as predictor of neurological outcome in postanoxic coma: A multicenter prospective cohort study

Electroencephalographic reactivity as predictor of neurological outcome in postanoxic coma: A multicenter prospective cohort study

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

Categorization of post-cardiac arrest patients according to the pattern of amplitude-integrated electroencephalography after return of spontaneous circulation

Contact Info

Product

Resources

About