Performance of Spectrogram-Based Seizure Identification of Adult EEGs by Critical Care Nurses and Neurophysiologists

Abstract

SUMMARY Introduction Continuous EEG screening using spectrograms or compressed spectral arrays (CSAs) by neurophysiologists has shorter review times with minimal loss of sensitivity for seizure detection when compared with visual analysis of raw EEG. Limited data is available on the performance characteristics of CSA-based seizure detection by neurocritical care nurses. Methods This is a prospective, cross-sectional study that was conducted in two academic neurocritical care units and involved thirty-three neurointensive care unit nurses and four neurophysiologists. Results All nurses underwent a brief training session prior to testing. Forty two-hour CSA segments of continuous EEG were reviewed and rated for the presence of seizures. Two experienced clinical neurophysiologists blinded to the CSA data performed conventional visual analysis of the raw EEG and served as the gold standard. The overall accuracy was 55.7% among nurses and 67.5% among neurophysiologists. Nurse seizure detection sensitivity was 73.8%, and the false-positive rate was 1-per-3.2 hours. Sensitivity and false alarm rate for the neurophysiologists was 66.3% and 1-per-6.4 hours, respectively. Inter-rater agreement for seizure screening was fair for nurses (Gwet’s AC1 statistic: 43.4%) and neurophysiologists (AC1: 46.3%). Conclusions Training nurses to perform seizure screening utilizing continuous EEG CSA displays is feasible and associated with moderate sensitivity. Nurses and neurophysiologists had comparable sensitivities, but nurses had a higher false-positive rate. Further work is needed to improve sensitivity and reduce false-alarm rates.

Quantitative Continuous EEG: Bridging the Gap Between the ICU Bedside and the EEG Interpreter

“…Also, the average length of data collection was only 8 h. In every-day practice, the quality of EEG tracings tends to deteriorate over time due to patient movement and diaphoresis, such that the potential for false positives and false negatives due to EEG artifact also increases, especially if EEG technologists are unavailable to assist with electrode re-application. These considerations likely explain the higher specificity observed by Kang and colleagues in comparison with the previous research involving ICU nurses [18,19,22].…”

“…The previous literature has assessed the diagnostic accuracy of quantitative EEG displays in comparison with the gold standard of raw cEEG interpreted by board-certified neurophysiologists (Table 1) [10,11,[13][14][15][16][17][18][19][20][21][22]. Color density spectral array (CDSA) and amplitude integrated EEG (aEEG) are the quantitative modalities that have been best studied, while a proprietary "rhythmicity spectrogram" has become available more recently and has not been studied as extensively (Figs.…”

“…For example, a recent study found as many as 7-8 false positive "seizures" per 24 h when quantitative displays were reviewed by pediatric intensive care unit (ICU) fellows [19]. Another study reported a specificity of only 38% when tracings were interpreted by ICU nurses [22]. Inappropriate treatment of false positives could potentially cause complications and increased ICU length of stay.…”

Validation of an algorithm of time-dependent electro-clinical risk stratification for electrographic seizures (TERSE) in critically ill patients

“…This is an average value and it is possible that this reduction might be lower in real life as the impact of using TERSE is more pronounced in low risk patients, whose EEG are easier to review by definition. The 95% prediction rate also compares favorably with the sensitivity of alternative approaches, such as simplified EEG montages (Kolls and Husain, 2007;Young et al, 2009;Karakis et al, 2010;Rubin et al, 2013;Gururangan et al, 2018), quantitative EEG (QEEG) displays (Stewart et al, 2010;Swisher et al, 2015;Amorim et al, 2016;Haider et al, 2016). Importantly, TERSE does not lead to false seizure detections, which are common in other strategies, and thus does not introduce a risk of over treatment.…”

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

“…EEG review can also be performed at the bedside by both expert or nonexpert users. For instance, similar to common models of electrocardiographic monitoring [ 40 ] or bedside quantitative EEG products [ 41 , 42 ], critical care staff may be trained to recognize the most salient and clinically important EEG signatures associated with status epilepticus. They can rely on their own bedside visual EEG review combined with the Rapid-EEG’s Brain Stethoscope function [ 43 ].…”