Search

Objectives: Seizures and seizure-like electroencephalography (EEG) patterns, collectively referred to as “ictal interictal injury continuum” (IIIC) patterns, are commonly encountered in critically ill patients. Automated detection is important for patient care and to enable research. However, training accurate detectors requires a large labeled dataset. Active Learning (AL) may help select informative examples to label, but the optimal AL approach remains unclear. Methods: We assembled >200,000 h of EEG from 1,454 hospitalized patients. From these, we collected 9,808 labeled and 120,000 unlabeled 10-second EEG segments. Labels included 6 IIIC patterns. In each AL iteration, a Dense-Net Convolutional Neural Network (CNN) learned vector representations for EEG segments using available labels, which were used to create a 2D embedding map. Nearest-neighbor label spreading within the embedding map was used to create additional pseudo-labeled data. A second Dense-Net was trained using real- and pseudo-labels. We evaluated several strategies for selecting candidate points for experts to label next. Finally, we compared two methods for class balancing within queries: standard balanced-based querying (SBBQ), and high confidence spread-based balanced querying (HCSBBQ). Results: Our results show: 1) Label spreading increased convergence speed for AL. 2) All query criteria produced similar results to random sampling. 3) HCSBBQ query balancing performed best. Using label spreading and HCSBBQ query balancing, we were able to train models approaching expert-level performance across all pattern categories after obtaining ∼7000 expert labels. Conclusion: Our results provide guidance regarding the use of AL to efficiently label large EEG datasets in critically ill patients., SCOPUS: ar.j, info:eu-repo/semantics/published

Objectives Electroencephalography (EEG) is a central part of the medical evaluation for patients with neurological disorders. Training an algorithm to label the EEG normal vs abnormal seems challenging, because of EEG heterogeneity and dependence of contextual factors, including age and sleep stage. Our objectives were to validate prior work on an independent data set suggesting that deep learning methods can discriminate between normal vs abnormal EEGs, to understand whether age and sleep stage information can improve discrimination, and to understand what factors lead to errors. Methods We train a deep convolutional neural network on a heterogeneous set of 8522 routine EEGs from the Massachusetts General Hospital. We explore several strategies for optimizing model performance, including accounting for age and sleep stage. Results The area under the receiver operating characteristic curve (AUC) on an independent test set (n = 851) is 0.917 marginally improved by including age (AUC = 0.924), and both age and sleep stages (AUC = 0.925), though not statistically significant. Conclusions The model architecture generalizes well to an independent dataset. Adding age and sleep stage to the model does not significantly improve performance. Significance Insights learned from misclassified examples, and minimal improvement by adding sleep stage and age suggest fruitful directions for further research.

BACKGROUND: Burst suppression in mechanically ventilated intensive care unit (ICU) patients is associated with increased mortality. However, the relative contributions of propofol use and critical illness itself to burst suppression; of burst suppression, propofol, and critical illness to mortality; and whether preventing burst suppression might reduce mortality, have not been quantified. METHODS: The dataset contains 471 adults from seven ICUs, after excluding anoxic encephalopathy due to cardiac arrest or intentional burst suppression for therapeutic reasons. We used multiple prediction and causal inference methods to estimate the effects connecting burst suppression, propofol, critical illness, and in-hospital mortality in an observational retrospective study. We also estimated the effects mediated by burst suppression. Sensitivity analysis was used to assess for unmeasured confounding. RESULTS: The expected outcomes in a “counterfactual” Randomized Controlled Trial (cRCT) that assigned patients to mild vs. severe illness is expected to show a difference in burst suppression burden of 39%, 95% CI [8–66]%, and in mortality of 35% [29–41]%. Assigning patients to maximal (100%) burst suppression burden is expected to increase mortality by 12% [7–17]% compared to 0% burden. Burst suppression mediates 10% [2–21]% of the effect of critical illness on mortality. A high cumulative propofol dose (1316 mg/kg) is expected to increase burst suppression burden by 6% [0.8–12]% compared to a low dose (284 mg/kg). Propofol exposure has no significant direct effect on mortality; its effect is entirely mediated through burst suppression. CONCLUSIONS: Our analysis clarifies how important factors contribute to mortality in ICU patients. Burst suppression appears to contribute to mortality but is primarily an effect of critical illness rather than iatrogenic use of propofol.

Background: Manual annotation of seizures and interictal-ictal-injury continuum (IIIC) patterns in continuous EEG (cEEG) recorded from critically ill patients is a time-intensive process for clinicians and researchers. In this study, we evaluated the accuracy and efficiency of an automated clustering method to accelerate expert annotation of cEEG.New method: We learned a local dictionary from 97 ICU patients by applying k-medoids clustering to 592 features in the time and frequency domains. We utilized changepoint detection (CPD) to segment the cEEG recordings. We then computed a bag-of-words (BoW) representation for each segment. We further clustered the segments by affinity propagation. EEG experts scored the resulting clusters for each patient by labeling only the cluster medoids. We trained a random forest classifier to assess validity of the clusters.Results: Mean pairwise agreement of 62.6% using this automated method was not significantly different from interrater agreements using manual labeling (63.8%), demonstrating the validity of the method. We also found that it takes experts using our method 5.31 +/- 4.44 min to label the 30.19 +/- 3.84 h of cEEG data, more than 45 times faster than unaided manual review, demonstrating efficiency.Comparison with existing methods: Previous studies of EEG data labeling have generally yielded similar human expert interrater agreements, and lower agreements with automated methods.Conclusions: Our results suggest that long EEG recordings can be rapidly annotated by experts many times faster than unaided manual review through the use of an advanced clustering method.

Importance Seizure risk stratification is needed to boost inpatient seizure detection and to improve continuous electroencephalogram (cEEG) cost-effectiveness. 2HELPS2B can address this need but requires validation. Objective To use an independent cohort to validate the 2HELPS2B score and develop a practical guide for its use. Design, Setting, and Participants This multicenter retrospective medical record review analyzed clinical and EEG data from patients 18 years or older with a clinical indication for cEEG and an EEG duration of 12 hours or longer who were receiving consecutive cEEG at 6 centers from January 2012 to January 2019. 2HELPS2B was evaluated with the validation cohort using the mean calibration error (CAL), a measure of the difference between prediction and actual results. A Kaplan-Meier survival analysis was used to determine the duration of EEG monitoring to achieve a seizure risk of less than 5% based on the 2HELPS2B score calculated on first- hour (screening) EEG. Participants undergoing elective epilepsy monitoring and those who had experienced cardiac arrest were excluded. No participants who met the inclusion criteria were excluded. Main Outcomes and Measures The main outcome was a CAL error of less than 5% in the validation cohort. Results The study included 2111 participants (median age, 51 years; 1113 men [52.7%]; median EEG duration, 48 hours) and the primary outcome was met with a validation cohort CAL error of 4.0% compared with a CAL of 2.7% in the foundational cohort (P = .13). For the 2HELPS2B score calculated on only the first hour of EEG in those without seizures during that hour, the CAL error remained at less than 5.0% at 4.2% and allowed for stratifying patients into low- (2HELPS2B = 0; 25%) groups. Each of the categories had an associated minimum recommended duration of EEG monitoring to achieve at least a less than 5% risk of seizures, a 2HELPS2B score of 0 at 1-hour screening EEG, a 2HELPS2B score of 1 at 12 hours, and a 2HELPS2B score of 2 or greater at 24 hours. Conclusions and Relevance In this study, 2HELPS2B was validated as a clinical tool to aid in seizure detection, clinical communication, and cEEG use in hospitalized patients. In patients without prior clinical seizures, a screening 1-hour EEG that showed no epileptiform findings was an adequate screen. In patients with any highly epileptiform EEG patterns during the first hour of EEG (ie, a 2HELPS2B score of ≥2), at least 24 hours of recording is recommended.

Aims Although approving new anticonvulsants was a major breakthrough in the field of epilepsy control, so far we have met limited success in almost one third of patients suffering from epilepsy and a definite and reliable method is yet to be found. Levosimendan demonstrated neuroprotective effects and reduced mortality in conditions in which seizure can be an etiology of death; however, the underlying neuroprotective mechanisms of levosimendan still eludes us. In the light of evidence suggesting levosimendan can be a K ATP channel opener and nitrergic pathway activator, levosimendan may exert antiseizure effects through K ATP channels and nitrergic pathway. Main methods In this study, the effects of levosimendan on seizure susceptibility was studied by PTZ-induced seizures model in mice. Key findings Administration of a single effective dose of levosimendan significantly increased seizures threshold and the nitrite level in the hippocampus and temporal cortex. Pretreatment with noneffective doses of glibenclamide (a K ATP channel blocker) and L-NAME (a non-selective NOS inhibitor) neutralize the anticonvulsant and nitrite elevating effects of levosimendan. While 7-NI (a neural NOS inhibitor) blocked the anticonvulsant effect of levosimendan, Aminoguanidine (an inducible NOS inhibitor) failed to affect the anticonvulsant effects of levosimendan. Cromakalim (a K ATP channel opener) or l -arginine (an NO precursor) augmented the anticonvulsant effects of a subeffective dose of levosimendan. Moreover, co-administration of noneffective doses of Glibenclamide and L-NAME demonstrated a synergistic effect in blocking the anticonvulsant effects of levosimendan. Significance Levosimendan has anticonvulsant effects possibly via K ATP /nNOS/NO pathway activation in the hippocampus and temporal cortex.

Seizures, status epilepticus, and seizure-like rhythmic or periodic activities are common, pathological, harmful states of brain electrical activity seen in the electroencephalogram (EEG) of patients during critical medical illnesses or acute brain injury. Accumulating evidence shows that these states, when prolonged, cause neurological injury. In this study we developed a valid method to automatically discover a small number of homogeneous pattern clusters, to facilitate efficient interactive labelling by EEG experts. 592 time domain and spectral features were extracted from continuous EEG (cEEG) data of 369 ICU (intensive care unit) patients. For each patient, feature dimensionality was reduced using principal component analysis (PCA), retaining 95% of the variance. K-medoids clustering was applied to learn a local dictionary from each patient, consisting of k=100 exemplars/words. Changepoint detection (CPD) was utilized to break each EEG into segments. A bag-of-words (BoW) representation was computed for each segment, specifically, a normalized histogram of the words found within each segment. Segments were further clustered using the BoW histograms by Affinity Propagation (AP) using a χ(2) distance to measure similarities between histograms. The resulting 30 50 clusters for each patient were scored by EEG experts through labeling only the cluster medoids. Embedding methods t-SNE (t-distributed stochastic neighbor embedding) and PCA were used to provide a 2D representation for visualization and exploration of the data. Our results illustrate that it takes approximately 3 minutes to annotate 24 hours of cEEG by experts, which is at least 60 times faster than unaided manual review.

Clinical seizures following acute ischemic stroke (AIS) appear to contribute to worse neurologic outcomes. However, the effect of electrographic epileptiform abnormalities (EAs) more broadly is less clear. Here, we evaluate the impact of EAs, including electrographic seizures and periodic and rhythmic patterns, on outcomes in patients with AIS.This is a retrospective study of all patients with AIS aged ≥ 18 years who underwent at least 18 h of continuous electroencephalogram (EEG) monitoring at a single center between 2012 and 2017. EAs were classified according to American Clinical Neurophysiology Society (ACNS) nomenclature and included seizures and periodic and rhythmic patterns. EA burden for each 24-h epoch was defined using the following cutoffs: EA presence, maximum daily burden 10% versus 10%, maximum daily burden 50% versus 50%, and maximum daily burden using categories from ACNS nomenclature ("rare" 1%; "occasional" 1-9%; "frequent" 10-49%; "abundant" 50-89%; "continuous" 90%). Maximum EA frequency for each epoch was dichotomized into ≥ 1.5 Hz versus 1.5 Hz. Poor neurologic outcome was defined as a modified Rankin Scale score of 4-6 (vs. 0-3 as good outcome) at hospital discharge.One hundred and forty-three patients met study inclusion criteria. Sixty-seven patients (46.9%) had EAs. One hundred and twenty-four patients (86.7%) had poor outcome. On univariate analysis, the presence of EAs (OR 3.87 [1.27-11.71], p = 0.024) and maximum daily burden 10% (OR 12.34 [2.34-210], p = 0.001) and 50% (OR 8.26 [1.34-122], p = 0.035) were associated with worse outcomes. On multivariate analysis, after adjusting for clinical covariates (age, gender, NIHSS, APACHE II, stroke location, stroke treatment, hemorrhagic transformation, Charlson comorbidity index, history of epilepsy), EA presence (OR 5.78 [1.36-24.56], p = 0.017), maximum daily burden 10% (OR 23.69 [2.43-230.7], p = 0.006), and maximum daily burden 50% (OR 9.34 [1.01-86.72], p = 0.049) were associated with worse outcomes. After adjusting for covariates, we also found a dose-dependent association between increasing EA burden and increasing probability of poor outcomes (OR 1.89 [1.18-3.03] p = 0.009). We did not find an independent association between EA frequency and outcomes (OR: 4.43 [.98-20.03] p = 0.053). However, the combined effect of increasing EA burden and frequency ≥ 1.5 Hz (EA burden * frequency) was significantly associated with worse outcomes (OR 1.64 [1.03-2.63] p = 0.039).Electrographic seizures and periodic and rhythmic patterns in patients with AIS are associated with worse outcomes in a dose-dependent manner. Future studies are needed to assess whether treatment of this EEG activity can improve outcomes.