Monitoring the Burden of Seizures and Highly Epileptiform Patterns in Critical Care with a Novel Machine Learning Method.

INTRODUCTION: Current electroencephalography (EEG) practice relies on interpretation by expert neurologists, which introduces diagnostic and therapeutic delays that can impact patients' clinical outcomes. As EEG practice expands, these experts are becoming increasingly limited resources. A highly sensitive and specific automated seizure detection system would streamline practice and expedite appropriate management for patients with possible nonconvulsive seizures. We aimed to test the performance of a recently FDA-cleared machine learning method (Claritγ, Ceribell Inc.) that measures the burden of seizure activity in real time and generates bedside alerts for possible status epilepticus (SE). METHODS: We retrospectively identified adult patients (n = 353) who underwent evaluation of possible seizures with Rapid Response EEG system (Rapid-EEG, Ceribell Inc.). Automated detection of seizure activity and seizure burden throughout a recording (calculated as the percentage of ten-second epochs with seizure activity in any 5-min EEG segment) was performed with Claritγ, and various thresholds of seizure burden were tested (≥ 10% indicating ≥ 30 s of seizure activity in the last 5 min, ≥ 50% indicating ≥ 2.5 min of seizure activity, and ≥ 90% indicating ≥ 4.5 min of seizure activity and triggering a SE alert). The sensitivity and specificity of Claritγ's real-time seizure burden measurements and SE alerts were compared to the majority consensus of at least two expert neurologists. RESULTS: Majority consensus of neurologists labeled the 353 EEGs as normal or slow activity (n = 249), highly epileptiform patterns (HEP, n = 87), or seizures [n = 17, nine longer than 5 min (e.g., SE), and eight shorter than 5 min]. The algorithm generated a SE alert (≥ 90% seizure burden) with 100% sensitivity and 93% specificity. The sensitivity and specificity of various thresholds for seizure burden during EEG recordings for detecting patients with seizures were 100% and 82% for ≥ 50% seizure burden and 88% and 60% for ≥ 10% seizure burden. Of the 179 EEG recordings in which the algorithm detected no seizures, seizures were identified by the expert reviewers in only two cases, indicating a negative predictive value of 99%. DISCUSSION: Claritγ detected SE events with high sensitivity and specificity, and it demonstrated a high negative predictive value for distinguishing nonepileptiform activity from seizure and highly epileptiform activity. CONCLUSIONS: Ruling out seizures accurately in a large proportion of cases can help prevent unnecessary or aggressive over-treatment in critical care settings, where empiric treatment with antiseizure medications is currently prevalent. Claritγ's high sensitivity for SE and high negative predictive value for cases without epileptiform activity make it a useful tool for triaging treatment and the need for urgent neurological consultation.

Comparing the quality of signals recorded with a rapid response EEG and conventional clinical EEG systems.

OBJECTIVES: To compare the quality of electroencephalography (EEG) signals recorded with a rapid response EEG system and the signals recorded with conventional clinical EEG recordings. METHODS: We studied the differences between EEG recordings taken with a rapid response EEG system (Ceribell) compared to conventional EEG through two separate set of studies. First, we conducted simultaneous recording on a healthy subject in an experimental laboratory setting where the rapid response EEG and two conventional EEG recording systems (Nihon Kohden and Natus) were used at the same time on the same subject using separate but adjacently placed electrodes. The rapid response EEG was applied by a user without prior training in EEG set up while two separate sets of conventional EEG electrodes were placed by a trained EEG technologist. The correlation between each of the recordings was calculated and quantitatively compared. In the second study, we performed a set of consecutive recordings on 22 patients in an ICU environment. The rapid response EEG system was applied by clinical ICU fellows without prior training in EEG set up while waiting for the conventional EEG system to arrive, after which the rapid response EEG was stopped and the conventional EEG was applied by a trained EEG technologist. We measured and compared several metrics of EEG quality using comparative metrics. RESULTS: For the simultaneous recording performed in a laboratory environment, the tested rapid response EEG and conventional EEG recordings showed agreement when aligned and visually compared in the time domain, all EEG waveform features were distinguishable in both recordings. The correlation between each pair of recordings also showed that the correlation between the rapid response EEG recording and each of the two conventional recordings was statistically the same as the correlation between the two conventional recordings. For the consecutive recordings performed in real life clinical ICU environment, Hjorth parameters, spike count, baseline wander, and kurtosis measures were statistically similar (p > 0.05, Wilcoxon signed rank test) for the rapid response EEG and conventional clinical EEG recordings. The rapid response EEG data had significantly lower 60 Hz noise compared to recordings made with the conventional systems both in laboratory and ICU settings. Lastly, the clinical information obtained with the rapid response EEG system was concordant with the diagnostic information obtained with the conventional EEG recordings in the ICU setting. CONCLUSIONS: Our findings show that the tested rapid response EEG system provides EEG recording quality that is equivalent to conventional EEG systems and even better when it comes to 60 Hz noise level. The concordance between the rapid response EEG and conventional EEG systems was demonstrated both in a controlled laboratory environment as well as in the noisy environment of a hospital ICU on patients with altered mental status. SIGNIFICANCE: Our findings clearly confirm that the tested rapid response EEG system provides EEG data that is equivalent in quality to the recordings made using conventional EEG systems despite the fact that the rapid response system can be applied within few minutes and with no reliance on specialized technologists. This can be important for urgent situations where the use of conventional EEG systems is hindered by the lengthy setup time and limited availability of EEG technologists.

Classification of motor imagery by means of cortical current density estimation and Von Neumann entropy.

The goal of the present study is to employ the source imaging methods such as cortical current density estimation for the classification of left- and right-hand motor imagery tasks, which may be used for brain-computer interface (BCI) applications. The scalp recorded EEG was first preprocessed by surface Laplacian filtering, time-frequency filtering, noise normalization and independent component analysis. Then the cortical imaging technique was used to solve the EEG inverse problem. Cortical current density distributions of left and right trials were classified from each other by exploiting the concept of Von Neumann entropy. The proposed method was tested on three human subjects (180 trials each) and a maximum accuracy of 91.5% and an average accuracy of 88% were obtained. The present results confirm the hypothesis that source analysis methods may improve accuracy for classification of motor imagery tasks. The present promising results using source analysis for classification of motor imagery enhances our ability of performing source analysis from single trial EEG data recorded on the scalp, and may have applications to improved BCI systems.

Classification of motor imagery tasks for brain-computer interface applications by means of two equivalent dipoles analysis.

We have developed a novel approach using source analysis for classifying motor imagery tasks. Two-equivalent-dipoles analysis was proposed to aid classification of motor imagery tasks for brain-computer interface (BCI) applications. By solving the electroencephalography (EEG) inverse problem of single trial data, it is found that the source analysis approach can aid classification of motor imagination of left- or right-hand movement without training. In four human subjects, an averaged accuracy of classification of 80% was achieved. The present study suggests the merits and feasibility of applying EEG inverse solutions to BCI applications from noninvasive EEG recordings.