OBJECTIVE: This study was undertaken to determine the dose-response relation between epileptiform activity burden and outcomes in acutely ill patients. METHODS: A single center retrospective analysis was made of 1,967 neurologic, medical, and surgical patients who underwent >16 hours of continuous electroencephalography (EEG) between 2011 and 2017. We developed an artificial intelligence algorithm to annotate 11.02 terabytes of EEG and quantify epileptiform activity burden within 72 hours of recording. We evaluated burden (1) in the first 24 hours of recording, (2) in the 12-hours epoch with highest burden (peak burden), and (3) cumulatively through the first 72 hours of monitoring. Machine learning was applied to estimate the effect of epileptiform burden on outcome. Outcome measure was discharge modified Rankin Scale, dichotomized as good (0-4) versus poor (5-6). RESULTS: Peak epileptiform burden was independently associated with poor outcomes (p < 0.0001). Other independent associations included age, Acute Physiology and Chronic Health Evaluation II score, seizure on presentation, and diagnosis of hypoxic-ischemic encephalopathy. Model calibration error was calculated across 3 strata based on the time interval between last EEG measurement (up to 72 hours of monitoring) and discharge: (1) <5 days between last measurement and discharge, 0.0941 (95% confidence interval [CI] = 0.0706-0.1191); 5 to 10 days between last measurement and discharge, 0.0946 (95% CI = 0.0631-0.1290); >10 days between last measurement and discharge, 0.0998 (95% CI = 0.0698-0.1335). After adjusting for covariates, increase in peak epileptiform activity burden from 0 to 100% increased the probability of poor outcome by 35%. INTERPRETATION: Automated measurement of peak epileptiform activity burden affords a convenient, consistent, and quantifiable target for future multicenter randomized trials investigating whether suppressing epileptiform activity improves outcomes. ANN NEUROL 2021;90:300-311.
OBJECTIVE: This study was undertaken to determine the dose-response relation between epileptiform activity burden and outcomes in acutely ill patients. METHODS: A single center retrospective analysis was made of 1,967 neurologic, medical, and surgical patients who underwent >16 hours of continuous electroencephalography (EEG) between 2011 and 2017. We developed an artificial intelligence algorithm to annotate 11.02 terabytes of EEG and quantify epileptiform activity burden within 72 hours of recording. We evaluated burden (1) in the first 24 hours of recording, (2) in the 12-hours epoch with highest burden (peak burden), and (3) cumulatively through the first 72 hours of monitoring. Machine learning was applied to estimate the effect of epileptiform burden on outcome. Outcome measure was discharge modified Rankin Scale, dichotomized as good (0-4) versus poor (5-6). RESULTS: Peak epileptiform burden was independently associated with poor outcomes (p < 0.0001). Other independent associations included age, Acute Physiology and Chronic Health Evaluation II score, seizure on presentation, and diagnosis of hypoxic-ischemic encephalopathy. Model calibration error was calculated across 3 strata based on the time interval between last EEG measurement (up to 72 hours of monitoring) and discharge: (1) <5 days between last measurement and discharge, 0.0941 (95% confidence interval [CI] = 0.0706-0.1191); 5 to 10 days between last measurement and discharge, 0.0946 (95% CI = 0.0631-0.1290); >10 days between last measurement and discharge, 0.0998 (95% CI = 0.0698-0.1335). After adjusting for covariates, increase in peak epileptiform activity burden from 0 to 100% increased the probability of poor outcome by 35%. INTERPRETATION: Automated measurement of peak epileptiform activity burden affords a convenient, consistent, and quantifiable target for future multicenter randomized trials investigating whether suppressing epileptiform activity improves outcomes. ANN NEUROL 2021;90:300-311.
Authors: Jan Claassen; Lawrence J Hirsch; Jennifer A Frontera; Andres Fernandez; Michael Schmidt; Gregory Kapinos; John Wittman; E Sander Connolly; Ronald G Emerson; Stephan A Mayer Journal: Neurocrit Care Date: 2006 Impact factor: 3.210
Authors: L J Hirsch; S M LaRoche; N Gaspard; E Gerard; A Svoronos; S T Herman; R Mani; H Arif; N Jette; Y Minazad; J F Kerrigan; P Vespa; S Hantus; J Claassen; G B Young; E So; P W Kaplan; M R Nuwer; N B Fountain; F W Drislane Journal: J Clin Neurophysiol Date: 2013-02 Impact factor: 2.177
Authors: J A Kim; E S Rosenthal; S Biswal; S Zafar; A V Shenoy; K L O'Connor; S C Bechek; J Valdery Moura; M M Shafi; A B Patel; S S Cash; M B Westover Journal: Clin Neurophysiol Date: 2017-01-29 Impact factor: 3.708
Authors: J Claassen; N Jetté; F Chum; R Green; M Schmidt; H Choi; J Jirsch; J A Frontera; E Sander Connolly; R G Emerson; S A Mayer; L J Hirsch Journal: Neurology Date: 2007-09-25 Impact factor: 9.910
Authors: M Brandon Westover; Mouhsin M Shafi; Matt T Bianchi; Lidia M V R Moura; Deirdre O'Rourke; Eric S Rosenthal; Catherine J Chu; Samantha Donovan; Daniel B Hoch; Ronan D Kilbride; Andrew J Cole; Sydney S Cash Journal: Clin Neurophysiol Date: 2014-07-11 Impact factor: 3.708
Authors: Wendong Ge; Jin Jing; Sungtae An; Aline Herlopian; Marcus Ng; Aaron F Struck; Brian Appavu; Emily L Johnson; Gamaleldin Osman; Hiba A Haider; Ioannis Karakis; Jennifer A Kim; Jonathan J Halford; Monica B Dhakar; Rani A Sarkis; Christa B Swisher; Sarah Schmitt; Jong Woo Lee; Mohammad Tabaeizadeh; Andres Rodriguez; Nicolas Gaspard; Emily Gilmore; Susan T Herman; Peter W Kaplan; Jay Pathmanathan; Shenda Hong; Eric S Rosenthal; Sahar Zafar; Jimeng Sun; M Brandon Westover Journal: J Neurosci Methods Date: 2020-10-22 Impact factor: 2.390
Authors: Paula R Sanches; Mohammad Tabaeizadeh; Lidia M V R Moura; Eric S Rosenthal; Luis Otavio Caboclo; John Hsu; Elisabetta Patorno; M Brandon Westover; Sahar F Zafar Journal: Neurol Sci Date: 2022-06-17 Impact factor: 3.830