Outcome Prediction of Postanoxic Coma: A Comparison of Automated Electroencephalography Analysis Methods

Autor: Stanley D. T. Pham, Hanneke M. Keijzer, Barry J. Ruijter, Antje A. Seeber, Erik Scholten, Gea Drost, Walter M. van den Bergh, Francois H. M. Kornips, Norbert A. Foudraine, Albertus Beishuizen, Michiel J. Blans, Jeannette Hofmeijer, Michel J. A. M. van Putten, Marleen C. Tjepkema-Cloostermans
Přispěvatelé: Movement Disorder (MD), Critical care, Anesthesiology, Peri-operative and Emergency medicine (CAPE), Clinical Neurophysiology, TechMed Centre
Rok vydání: 2021
Předmět:
Zdroj: Neurocritical Care, 37, Suppl 2, pp. 248-258
Neurocritical care, 37, 248-258. Humana Press
Neurocritical Care, 37, 248-258
Neurocritical care, 37(SUPPL 2), 248-258. Humana Press
ISSN: 1556-0961
1541-6933
Popis: BackgroundTo compare three computer-assisted quantitative electroencephalography (EEG) prediction models for the outcome prediction of comatose patients after cardiac arrest regarding predictive performance and robustness to artifacts.MethodsA total of 871 continuous EEGs recorded up to 3 days after cardiac arrest in intensive care units of five teaching hospitals in the Netherlands were retrospectively analyzed. Outcome at 6 months was dichotomized as “good” (Cerebral Performance Category 1–2) or “poor” (Cerebral Performance Category 3–5). Three prediction models were implemented: a logistic regression model using two quantitative features, a random forest model with nine features, and a deep learning model based on a convolutional neural network. Data from two centers were used for training and fivefold cross-validation (n = 663), and data from three other centers were used for external validation (n = 208). Model output was the probability of good outcome. Predictive performances were evaluated by using receiver operating characteristic analysis and the calculation of predictive values. Robustness to artifacts was evaluated by using an artifact rejection algorithm, manually added noise, and randomly flattened channels in the EEG.ResultsThe deep learning network showed the best overall predictive performance. On the external test set, poor outcome could be predicted by the deep learning network at 24 h with a sensitivity of 54% (95% confidence interval [CI] 44–64%) at a false positive rate (FPR) of 0% (95% CI 0–2%), significantly higher than the logistic regression (sensitivity 33%, FPR 0%) and random forest models (sensitivity 13%, FPR, 0%) (p p ConclusionsA deep learning model outperformed logistic regression and random forest models for reliable, robust, EEG-based outcome prediction of comatose patients after cardiac arrest.
Databáze: OpenAIRE
Externí odkaz: