Continuous electroencephalogram monitoring is associated with lower mortality in critically ill patients; however, it is underused due to the resource-intensive nature of manually interpreting ...prolonged streams of continuous electroencephalogram data. Here, we present a novel real-time, machine learning-based alerting and monitoring system for epilepsy and seizures that dramatically reduces the amount of manual electroencephalogram review.
We developed a custom data reduction algorithm using a random forest and deployed it within an online cloud-based platform, which streams data and communicates interactively with caregivers via a web interface to display algorithm results. We developed real-time, machine learning-based alerting and monitoring system for epilepsy and seizures on continuous electroencephalogram recordings from 77 patients undergoing routine scalp ICU electroencephalogram monitoring and tested it on an additional 20 patients.
We achieved a mean seizure sensitivity of 84% in cross-validation and 85% in testing, as well as a mean specificity of 83% in cross-validation and 86% in testing, corresponding to a high level of data reduction. This study validates a platform for machine learning-assisted continuous electroencephalogram analysis and represents a meaningful step toward improving utility and decreasing cost of continuous electroencephalogram monitoring. We also make our high-quality annotated dataset of 97 ICU continuous electroencephalogram recordings public for others to validate and improve upon our methods.
Summary Encephalitis is a severe inflammatory disorder of the brain with many possible causes and a complex differential diagnosis. Advances in autoimmune encephalitis research in the past 10 years ...have led to the identification of new syndromes and biomarkers that have transformed the diagnostic approach to these disorders. However, existing criteria for autoimmune encephalitis are too reliant on antibody testing and response to immunotherapy, which might delay the diagnosis. We reviewed the literature and gathered the experience of a team of experts with the aims of developing a practical, syndrome-based diagnostic approach to autoimmune encephalitis and providing guidelines to navigate through the differential diagnosis. Because autoantibody test results and response to therapy are not available at disease onset, we based the initial diagnostic approach on neurological assessment and conventional tests that are accessible to most clinicians. Through logical differential diagnosis, levels of evidence for autoimmune encephalitis (possible, probable, or definite) are achieved, which can lead to prompt immunotherapy.