Predicting Neurological Outcome from Electroencephalogram Dynamics in Comatose Patients after Cardiac Arrest with Deep Learning

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 Van Putten, Brandon Westover

Research output: Contribution to journalArticleAcademicpeer-review

17 Citations (Scopus)
66 Downloads (Pure)


Objective: Most cardiac arrest patients who are successfully resuscitated are initially comatose due to hypoxic-ischemic brain injury. Quantitative electroencephalography (EEG) provides valuable prognostic information. However, prior approaches largely rely on snapshots of the EEG, without taking advantage of temporal information. Methods: We present a recurrent deep neural network with the goal of capturing temporal dynamics from longitudinal EEG data to predict long-term neurological outcomes. We utilized a large international dataset of continuous EEG recordings from 1,038 cardiac arrest patients from seven hospitals in Europe and the US. Poor outcome was defined as a Cerebral Performance Category (CPC) score of 3-5, and good outcome as CPC score 0-2 at 3 to 6-months after cardiac arrest. Model performance is evaluated using 5-fold cross validation. Results: The proposed approach provides predictions which improve over time, beginning from an area under the receiver operating characteristic curve (AUC-ROC) of 0.78 (95% CI: 0.72-0.81) at 12 hours, and reaching 0.88 (95% CI: 0.85-0.91) by 66 h after cardiac arrest. At 66 h, (sensitivity, specificity) points of interest on the ROC curve for predicting poor outcomes were (32,99)%, (55,95)%, and (62,90)%, (99,23)%, (95,47)%, and (90,62)%; whereas for predicting good outcome, the corresponding operating points were (17,99)%, (47,95)%, (62,90)%, (99,19)%, (95,48)%, (70,90)%. Moreover, the model provides predicted probabilities that closely match the observed frequencies of good and poor outcomes (calibration error 0.04). Conclusions and Significance: These findings suggest that accounting for EEG trend information can substantially improve prediction of neurologic outcomes for patients with coma following cardiac arrest.

Original languageEnglish
Pages (from-to)1813 - 1825
Number of pages13
JournalIEEE transactions on biomedical engineering
Issue number5
Early online date28 Dec 2021
Publication statusPublished - 1 May 2022


  • Brain modeling
  • Cardiac arrest
  • Deep learning
  • Electroencephalography
  • Hospitals
  • Market research
  • Neurology
  • 22/1 OA procedure


Dive into the research topics of 'Predicting Neurological Outcome from Electroencephalogram Dynamics in Comatose Patients after Cardiac Arrest with Deep Learning'. Together they form a unique fingerprint.

Cite this