Seungha Lee1, Xuelong Zhao1, Kathryn A Davis1, Alexis A Topjian1, Brian Litt1, Nicholas S Abend2. 1. From the Department of Bioengineering (S.L., X.Z., B.L.), The University of Pennsylvania; Department of Neurology (K.A.D., B.L., N.S.A.), Perelman School of Medicine at the University of Pennsylvania; and the Departments of Pediatrics (N.S.A.) and Anesthesia and Critical Care Medicine (A.A.T., N.S.A.), Children's Hospital of Philadelphia and Perelman School of Medicine at the University of Pennsylvania, Philadelphia. 2. From the Department of Bioengineering (S.L., X.Z., B.L.), The University of Pennsylvania; Department of Neurology (K.A.D., B.L., N.S.A.), Perelman School of Medicine at the University of Pennsylvania; and the Departments of Pediatrics (N.S.A.) and Anesthesia and Critical Care Medicine (A.A.T., N.S.A.), Children's Hospital of Philadelphia and Perelman School of Medicine at the University of Pennsylvania, Philadelphia. abend@email.chop.edu.
Abstract
OBJECTIVE: To determine whether quantitative EEG (QEEG) features predict neurologic outcomes in children after cardiac arrest. METHODS: We performed a single-center prospective observational study of 87 consecutive children resuscitated and admitted to the pediatric intensive care unit after cardiac arrest. Full-array conventional EEG data were obtained as part of clinical management. We computed 8 QEEG features from 5-minute epochs every hour after return of circulation. We developed predictive models utilizing random forest classifiers trained on patient age and 8 QEEG features to predict outcome. The features included SD of each EEG channel, normalized band power in alpha, beta, theta, delta, and gamma wave frequencies, line length, and regularity function scores. We measured outcomes using Pediatric Cerebral Performance Category (PCPC) scores. We evaluated the models using 5-fold cross-validation and 1,000 bootstrap samples. RESULTS: The best performing model had a 5-fold cross-validation accuracy of 0.8 (0.88 area under the receiver operating characteristic curve). It had a positive predictive value of 0.79 and a sensitivity of 0.84 in predicting patients with favorable outcomes (PCPC score of 1-3). It had a negative predictive value of 0.8 and a specificity of 0.75 in predicting patients with unfavorable outcomes (PCPC score of 4-6). The model also identified the relative importance of each feature. Analyses using only frontal electrodes did not differ in prediction performance compared to analyses using all electrodes. CONCLUSIONS: QEEG features can standardize EEG interpretation and predict neurologic outcomes in children after cardiac arrest.
OBJECTIVE: To determine whether quantitative EEG (QEEG) features predict neurologic outcomes in children after cardiac arrest. METHODS: We performed a single-center prospective observational study of 87 consecutive children resuscitated and admitted to the pediatric intensive care unit after cardiac arrest. Full-array conventional EEG data were obtained as part of clinical management. We computed 8 QEEG features from 5-minute epochs every hour after return of circulation. We developed predictive models utilizing random forest classifiers trained on patient age and 8 QEEG features to predict outcome. The features included SD of each EEG channel, normalized band power in alpha, beta, theta, delta, and gamma wave frequencies, line length, and regularity function scores. We measured outcomes using Pediatric Cerebral Performance Category (PCPC) scores. We evaluated the models using 5-fold cross-validation and 1,000 bootstrap samples. RESULTS: The best performing model had a 5-fold cross-validation accuracy of 0.8 (0.88 area under the receiver operating characteristic curve). It had a positive predictive value of 0.79 and a sensitivity of 0.84 in predicting patients with favorable outcomes (PCPC score of 1-3). It had a negative predictive value of 0.8 and a specificity of 0.75 in predicting patients with unfavorable outcomes (PCPC score of 4-6). The model also identified the relative importance of each feature. Analyses using only frontal electrodes did not differ in prediction performance compared to analyses using all electrodes. CONCLUSIONS: QEEG features can standardize EEG interpretation and predict neurologic outcomes in children after cardiac arrest.
Authors: Nicholas S Abend; Alexis A Topjian; Sudha Kilaru Kessler; Ana M Gutierrez-Colina; Robert A Berg; Vinay Nadkarni; Dennis J Dlugos; Robert R Clancy; Rebecca N Ichord Journal: Pediatr Crit Care Med Date: 2012-01 Impact factor: 3.624
Authors: Akira Nishisaki; Joseph Sullivan; Bernhard Steger; Carey R Bayer; Dennis Dlugos; Richard Lin; Rebecca Ichord; Mark A Helfaer; Vinay Nadkarni Journal: Pediatr Crit Care Med Date: 2007-01 Impact factor: 3.624
Authors: Alexis A Topjian; Benjamin French; Robert M Sutton; Thomas Conlon; Vinay M Nadkarni; Frank W Moler; J Michael Dean; Robert A Berg Journal: Crit Care Med Date: 2014-06 Impact factor: 7.598
Authors: Kyoung Min You; Gil Joon Suh; Woon Yong Kwon; Kyung Su Kim; Sang-Bae Ko; Min Ji Park; Taegyun Kim; Jung-In Ko Journal: Resuscitation Date: 2017-05-13 Impact factor: 5.262
Authors: Laurence Ducharme-Crevier; Craig A Press; Jonathan E Kurz; Michele G Mills; Joshua L Goldstein; Mark S Wainwright Journal: Pediatr Crit Care Med Date: 2017-05 Impact factor: 3.624
Authors: Gretchen M Brophy; Rodney Bell; Jan Claassen; Brian Alldredge; Thomas P Bleck; Tracy Glauser; Suzette M Laroche; James J Riviello; Lori Shutter; Michael R Sperling; David M Treiman; Paul M Vespa Journal: Neurocrit Care Date: 2012-08 Impact factor: 3.210
Authors: Archana A Patel; Ali Jannati; Sameer C Dhamne; Monica Sapuwa; Elizabeth Kalanga; Maitreyi Mazumdar; Gretchen L Birbeck; Alexander Rotenberg Journal: Epilepsy Behav Date: 2020-11-21 Impact factor: 2.937
Authors: Jennifer C Laws; Lori C Jordan; Lindsay M Pagano; John C Wellons; Michael S Wolf Journal: Pediatr Neurol Date: 2022-02-02 Impact factor: 3.372
Authors: Alexander Andrews; Tesfaye Zelleke; Rima Izem; Jiaxiang Gai; Dana Harrar; Jessica Mvula; Douglas G Postels Journal: Pediatr Neurol Date: 2021-10-19 Impact factor: 3.372
Authors: Wei-Long Zheng; Edilberto Amorim; Jin Jing; Ona Wu; Mohammad Ghassemi; Jong Woo Lee; Adithya Sivaraju; Trudy Pang; Susan T Herman; Nicolas Gaspard; Barry J Ruijter; Marleen C Tjepkema-Cloostermans; Jeannette Hofmeijer; Michel J A M van Putten; M Brandon Westover Journal: IEEE Trans Biomed Eng Date: 2022-04-21 Impact factor: 4.756
Authors: Steven N Baldassano; Shawniqua Williams Roberson; Ramani Balu; Brittany Scheid; John M Bernabei; Jay Pathmanathan; Brian Oommen; Damien Leri; Javier Echauz; Michael Gelfand; Paulomi Kadakia Bhalla; Chloe E Hill; Amanda Christini; Joost B Wagenaar; Brian Litt Journal: IEEE J Biomed Health Inform Date: 2020-01-13 Impact factor: 5.772
Authors: Wei-Long Zheng; Edilberto Amorim; Jin Jing; Wendong Ge; Shenda Hong; Ona Wu; Mohammad Ghassemi; Jong Woo Lee; Adithya Sivaraju; Trudy Pang; Susan T Herman; Nicolas Gaspard; Barry J Ruijter; Jimeng Sun; Marleen C Tjepkema-Cloostermans; Jeannette Hofmeijer; Michel J A M van Putten; M Brandon Westover Journal: Resuscitation Date: 2021-10-24 Impact factor: 5.262
Authors: Archana A Patel; Gretchen L Birbeck; Maitreyi Mazumdar; Suzanna Mwanza; Rosemary Nyirongo; Dixon Berejena; Joseph Kasolo; Tina Mwale; Violet Nambeye; Kafula Lisa Nkole; Nfwama Kawatu; Bo Zhang; Alexander Rotenberg Journal: BMJ Open Date: 2022-07-18 Impact factor: 3.006