Dataset Information

A Full-Stack Application for Detecting Seizures and Reducing Data During Continuous Electroencephalogram Monitoring.

ABSTRACT: 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.

Methods

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.

Results

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.

SUBMITTER: Bernabei JM

PROVIDER: S-EPMC8280012 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:ObjectiveWe evaluated the impact of monitoring indication, early electroencephalography (EEG), and clinical features on seizure risk in all neonates undergoing continuous EEG (cEEG) monitoring following a standardized monitoring protocol.MethodsAll cEEGs from unique neonates 34-48 weeks postmenstrual age monitored from 1/2011-10/2017 (n = 291) were included. We evaluated the impact of cEEG monitoring indication (acute neonatal encephalopathy [ANE], suspicious clinical events [SCEs], or other high-risk conditions [OHRs]), age, medication status, and early EEG abnormalities (including the presence of epileptiform discharges and abnormal background continuity, amplitude, asymmetry, asynchrony, excessive sharp transients, and burst suppression) on time to first seizure and overall seizure risk using Kaplan-Meier survival curves and multivariable Cox proportional hazards models.ResultsSeizures occurred in 28% of high-risk neonates. Discontinuation of monitoring after 24 hours of seizure-freedom would have missed 8.5% of neonates with seizures. Overall seizure risk was lower in neonates monitored for ANE compared to OHR (P = .004) and trended lower compared to SCE (P = .097). The time course of seizure presentation varied by group, where the probability of future seizure was less than 1% after 17 hours of seizure-free monitoring in the SCE group, but required 42 hours in the OHR group, and 73 hours in the ANE group. The presence of early epileptiform discharges increased seizure risk in each group (ANE: adjusted hazard ratio [aHR] 4.32, 95% confidence interval [CI] 1.23-15.13, P = .022; SCE: aHR 10.95, 95% CI 4.77-25.14, P < 1e-07; OHR: aHR 56.90, 95% CI 10.32-313.72, P < 1e-05).SignificanceNeonates who undergo cEEG are at high risk for seizures, and risk varies by monitoring indication and early EEG findings. Seizures are captured in nearly all neonates undergoing monitoring for SCE within 24 hours of cEEG monitoring. Neonates monitored for OHR and ANE can present with delayed seizures and require longer durations of monitoring. Early epileptiform discharges are the best early EEG feature to predict seizure risk.

Dataset Information

A Full-Stack Application for Detecting Seizures and Reducing Data During Continuous Electroencephalogram Monitoring.

Methods

Results

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets