Dataset Information

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

ABSTRACT:

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.

SUBMITTER: Muller M

PROVIDER: S-EPMC7720582 | biostudies-literature | 2020 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Müller Michael M Rossetti Andrea O AO Zimmermann Rebekka R Alvarez Vincent V Rüegg Stephan S Haenggi Matthias M Z'Graggen Werner J WJ Schindler Kaspar K Zubler Frédéric F

Critical care (London, England) 20201207 1

<h4>Background</h4>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).<h4>Method</h4>Data from 364 critically ill patients wi ...[more]

PMID: 33287874

Similar Datasets

Project description:BackgroundDisorders of Consciousness (DoC) are clinical conditions following a severe acquired brain injury (ABI) characterized by absent or reduced awareness, known as coma, Vegetative State (VS)/Unresponsive Wakefulness Syndrome (VS/UWS), and Minimally Conscious State (MCS). Misdiagnosis rate between VS/UWS and MCS is attested around 40% due to the clinical and behavioral fluctuations of the patients during bedside consciousness assessments. Given the large body of evidence that some patients with DoC possess "covert" awareness, revealed by neuroimaging and neurophysiological techniques, they are candidates for intervention with brain-computer interfaces (BCIs).ObjectivesThe aims of the present work are (i) to describe the characteristics of BCI systems based on electroencephalography (EEG) performed on DoC patients, in terms of control signals adopted to control the system, characteristics of the paradigm implemented, classification algorithms and applications (ii) to evaluate the performance of DoC patients with BCI.MethodsThe search was conducted on Pubmed, Web of Science, Scopus and Google Scholar. The PRISMA guidelines were followed in order to collect papers published in english, testing a BCI and including at least one DoC patient.ResultsAmong the 527 papers identified with the first run of the search, 27 papers were included in the systematic review. Characteristics of the sample of participants, behavioral assessment, control signals employed to control the BCI, the classification algorithms, the characteristics of the paradigm, the applications and performance of BCI were the data extracted from the study. Control signals employed to operate the BCI were: P300 (N = 19), P300 and Steady-State Visual Evoked Potentials (SSVEP; hybrid system, N = 4), sensorimotor rhythms (SMRs; N = 5) and brain rhythms elicited by an emotional task (N = 1), while assessment, communication, prognosis, and rehabilitation were the possible applications of BCI in DoC patients.ConclusionDespite the BCI is a promising tool in the management of DoC patients, supporting diagnosis and prognosis evaluation, results are still preliminary, and no definitive conclusions may be drawn; even though neurophysiological methods, such as BCI, are more sensitive to covert cognition, it is suggested to adopt a multimodal approach and a repeated assessment strategy.

Project description:PurposeWe aimed to determine which early EEG features and feature combinations most accurately predicted short-term neurobehavioral outcomes and survival in children resuscitated after cardiac arrest.MethodsThis was a prospective, single-center observational study of infants and children resuscitated from cardiac arrest who underwent conventional EEG monitoring with standardized EEG scoring. Logistic regression evaluated the marginal effect of each EEG variable or EEG variable combinations on the outcome. The primary outcome was neurobehavioral outcome (Pediatric Cerebral Performance Category score), and the secondary outcome was mortality. The authors identified the models with the highest areas under the receiver operating characteristic curve (AUC), evaluated the optimal models using a 5-fold cross-validation approach, and calculated test characteristics maximizing specificity.ResultsEighty-nine infants and children were evaluated. Unfavorable neurologic outcome (Pediatric Cerebral Performance Category score 4-6) occurred in 44 subjects (49%), including mortality in 30 subjects (34%). A model incorporating a four-level EEG Background Category (normal, slow-disorganized, discontinuous or burst-suppression, or attenuated-flat), stage 2 Sleep Transients (present or absent), and Reactivity-Variability (present or absent) had the highest AUC. Five-fold cross-validation for the optimal model predicting neurologic outcome indicated a mean AUC of 0.75 (range, 0.70-0.81) and for the optimal model predicting mortality indicated a mean AUC of 0.84 (range, 0.76-0.97). The specificity for unfavorable neurologic outcome and mortality were 95% and 97%, respectively. The positive predictive value for unfavorable neurologic outcome and mortality were both 86%.ConclusionsThe specificity of the optimal model using a combination of early EEG features was high for unfavorable neurologic outcome and mortality in critically ill children after cardiac arrest. However, the positive predictive value was only 86% for both outcomes. Therefore, EEG data must be considered in overall clinical context when used for neuroprognostication early after cardiac arrest.

Project description:ObjectiveTo compare the clinical and radiological features of various etiologies of chronic diffuse lacrimal gland enlargement.Materials and methodsWe retrospectively reviewed 91 consecutive patients who underwent surgical biopsy for chronic diffuse lacrimal gland enlargement and were diagnosed with non-specific dacryoadenitis (DA) (n = 42), immunoglobulin G4-related dacryoadenitis (IgG4-RD) (n = 33), and lymphoma (n = 16). Data on patient demographics, clinical presentation, and CT imaging findings (n = 73) and MRI (n = 43) were collected. The following radiologic features of lacrimal gland enlargement were evaluated: size, unilaterality, wedge sign, angle with the orbital wall, heterogeneity, signal intensity, degree of enhancement, patterns of dynamic contrast-enhanced, and apparent diffusion coefficient value. Radiological features outside the lacrimal glands, such as extra-lacrimal orbital involvement and extra-orbital head and neck involvement, were also evaluated. The clinical and radiological findings were compared among the three diseases.ResultsCompared to the DA and IgG4-RD groups, the lymphoma group was significantly older (mean 59.9 vs. 46.0 and 49.4 years, respectively; p = 0.001) and had a higher frequency of unilateral involvement (62.5% vs. 31.0% and 15.2%, respectively; p = 0.004). Compared to the IgG4-RD and lymphoma groups, the DA group had significantly smaller lacrimal glands (2.3 vs. 2.8 and 3.3 cm, respectively; p < 0.001) and a lower proportion of cases with a wedge sign (54.8% vs. 84.8% and 87.5%, respectively; p = 0.005). The IgG4-RD group showed more frequent involvement of the extra-orbital head and neck structures, including the infraorbital nerve (36.4%), paranasal sinus (72.7%), and salivary gland (58.6%) compared to the DA and lymphoma groups (4.8%-28.6%) (all p < 0.005).ConclusionPatient age, unilaterality, lacrimal gland size, wedge sign, and extra-orbital head and neck involvement differed significantly different between lymphoma, DA, and IgG4-RD. Our results will be useful for the differential diagnosis and proper management of chronic lacrimal gland enlargement.

Dataset Information

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

Background

Method

Results

Conclusions

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets