Educational initiatives and implementation of electroencephalography into the acute care environment: a protocol of a systematic review

MindReader: Unsupervised Classification of Electroencephalographic Data

Electroencephalogram (EEG) interpretation plays a critical role in the clinical assessment of neurological conditions, most notably epilepsy. However, EEG recordings are typically analyzed manually by highly specialized and heavily trained personnel. Moreover, the low rate of capturing abnormal events during the procedure makes interpretation time-consuming, resource-hungry, and overall an expensive process. Automatic detection offers the potential to improve the quality of patient care by shortening the time to diagnosis, managing big data and optimizing the allocation of human resources towards precision medicine. Here, we present MindReader, a novel unsupervised machine-learning method comprised of the interplay between an autoencoder network, a hidden Markov model (HMM), and a generative component: after dividing the signal into overlapping frames and performing a fast Fourier transform, MindReader trains an autoencoder neural network for dimensionality reduction and compact representation of different frequency patterns for each frame. Next, we processed the temporal patterns using a HMM, while a third and generative component hypothesized and characterized the different phases that were then fed back to the HMM. MindReader then automatically generates labels that the physician can interpret as pathological and non-pathological phases, thus effectively reducing the search space for trained personnel. We evaluated MindReader's predictive performance on 686 recordings, encompassing more than 980 h from the publicly available Physionet database. Compared to manual annotations, MindReader identified 197 of 198 epileptic events (99.45%), and is, as such, a highly sensitive method, which is a prerequisite for clinical use.

Educational initiatives for electroencephalography in the critical care setting: a systematic review and meta-analysis

PURPOSE

We systematically reviewed existing critical care electroencephalography (EEG) educational programs for non-neurologists, with the primary goal of reporting the content covered, methods of instruction, overall duration, and participant experience. Our secondary goals were to assess the impact of EEG programs on participants' core knowledge, and the agreement between non-experts and experts for seizure identification.

SOURCE

Major databases were searched from inception to 30 August 2020. Randomized controlled trials, cohort studies, and descriptive studies were all considered if they reported an EEG curriculum for non-neurologists in a critical care setting. Data were presented thematically for the qualitative primary outcome and a meta-analysis using a random effects model was performed for the quantitative secondary outcomes.

PRINCIPAL FINDINGS

Twenty-nine studies were included after reviewing 7,486 citations. Twenty-two studies were single centre, 17 were from North America, and 16 were published after 2016. Most EEG studies were targeted to critical care nurses (17 studies), focused on processed forms of EEG with amplitude-integrated EEG being the most common (15 studies), and were shorter than one day in duration (24 studies). In pre-post studies, EEG programs significantly improved participants' knowledge of tested material (standardized mean change, 1.79; 95% confidence interval [CI], 0.86 to 2.73). Agreement for seizure identification between non-experts and experts was moderate (Cohen's kappa = 0.44; 95% CI, 0.27 to 0.60).

CONCLUSIONS

It is feasible to teach basic EEG to participants in critical care settings from different clinical backgrounds, including physicians and nurses. Brief training programs can enable bedside providers to recognize high-yield abnormalities such as non-convulsive seizures.