Seizure Assessment and Forecasting With Efficient Rapid-EEG: A Retrospective Multicenter Comparative Effectiveness Study

Abstract

Background and objectives: Approximately 30% of critically ill patients have seizures, and more than half of these seizures do not have an overt clinical correlate. EEG is needed to avoid missing seizures and prevent overtreatment with antiseizure medications. Conventional-EEG (cEEG) resources are logistically constrained and unable to meet their growing demand for seizure detection even in highly developed centers. Brief EEG screening with the validated 2HELPS2B algorithm was proposed as a method to triage cEEG resources, but it is hampered by cEEG requirements, primarily EEG technologists. Seizure risk-stratification using reduced time-to-application rapid response-EEG (rrEEG) systems (∼5 minutes) could be a solution. We assessed the noninferiority of the 2HELPS2B score on a 1-hour rrEEG compared to cEEG.

Methods: A multicenter retrospective EEG diagnostic accuracy study was conducted from October 1, 2021, to July 31, 2022. Chart and EEG review performed with consecutive sampling at 4 tertiary care centers, included records of patients ≥18 years old, from January 1, 2018, to June 20, 2022. Monte Carlo simulation power analysis yielded n = 500 rrEEG; for secondary outcomes n = 500 cEEG and propensity-score covariate matching was planned. Primary outcome, noninferiority of rrEEG for seizure risk prediction, was assessed per area under the receiver operator characteristic curve (AUC). Noninferiority margin (0.05) was based on the 2HELPS2B validation study.

Results: A total of 240 rrEEG with follow-on cEEG were obtained. Median age was 64 (interquartile range 22); 42% were female. 2HELPS2B on a 1-hour rrEEG met noninferiority to cEEG (AUC 0.85, 95% CI 0.78-0.90, p = 0.001). Secondary endpoints of comparison with a matched contemporaneous cEEG showed no significant difference in AUC (0.89, 95% CI 0.83-0.94, p = 0.31); in false negative rate for the 2HELPS2B = 0 group (p = 1.0) rrEEG (0.021, 95% CI 0-0.062), cEEG (0.016, 95% CI 0-0.048); nor in survival analyses.

Discussion: 2HELPS2B on 1-hour rrEEG is noninferior to cEEG for seizure prediction. Patients with low-risk (2HELPS2B = 0) may be able to forgo prolonged cEEG, allowing for increased monitoring of at-risk patients.

Classification of evidence: This study provides Class II evidence that rrEEG is noninferior to cEEG in calculating the 2HELPS2B score to predict seizure risk.

Figure 1. SAFER Flow Diagram

(A) EEG duration is shown as the median in hours with the IQR. (B) Percentages of the cohorts are expressed in parentheses. cEEG = conventional-EEG >4 hours; IQR = interquartile range; MGH = Massachusetts General Hospital; rrEEG = rapid-EEG; SAFER = Seizure Assessment and Forecasting With Efficient Rapid-EEG; UNM = University of New Mexico; UW = University of Wisconsin-Madison; Yale = Yale University.

Figure 2. Primary Outcome Assessments of AUC

For the primary outcome, the rrEEG AUC met the noninferiority margin (0.75), which is 0.05 below the AUC from the 2HELPS2B validation study (0.80). The 0.050 was derived from the CI spread of the AUC in the validation study (0.78–0.83). For the secondary outcome, the SAFER cohorts had overlapping CIs. AUC = area under the receiver operator curve; rrEEG = rapid response-EEG; SAFER = Seizure Assessment and Forecasting With Efficient Rapid-EEG.

Figure 3. Primary and Secondary Outcome Assessments of AUC

For the secondary outcome rapid response-EEG AUC was not significantly different from the conventional-EEG AUC. AUC = area under the receiver operator curve; ROC = receiver operator curve.

Figure 4. Secondary Outcome: 2HELPS2B Risk-Calibration

For the secondary outcome, the 2HELPS2B Risk-Calibration shows no significant differences between cohorts. AUC = area under the receiver operator curve.