EEG-based outcome prediction after cardiac arrest with convolutional neural networks: Performance and visualization of discriminative features.

Jonas, Stefan; Rossetti, Andrea O; Oddo, Mauro; Jenni, Simon; Favaro, Paolo; Zubler, Frederic (2019). EEG-based outcome prediction after cardiac arrest with convolutional neural networks: Performance and visualization of discriminative features. Human brain mapping, 40(16), pp. 4606-4617. Wiley-Blackwell 10.1002/hbm.24724

	Text Jonas, 2019, Human Brain Mapping.pdf - Published Version Restricted to registered users only Available under License Publisher holds Copyright. Download (2MB)
Preview	Text Jonas_Version_Boris.pdf - Accepted Version Available under License Publisher holds Copyright. Download (653kB) | Preview

Prognostication for comatose patients after cardiac arrest is a difficult but essential task. Currently, visual interpretation of electroencephalogram (EEG) is one of the main modality used in outcome prediction. There is a growing interest in computer-assisted EEG interpretation, either to overcome the possible subjectivity of visual interpretation, or to identify complex features of the EEG signal. We used a one-dimensional convolutional neural network (CNN) to predict functional outcome based on 19-channel-EEG recorded from 267 adult comatose patients during targeted temperature management after CA. The area under the receiver operating characteristic curve (AUC) on the test set was 0.885. Interestingly, model architecture and fine-tuning only played a marginal role in classification performance. We then used gradient-weighted class activation mapping (Grad-CAM) as visualization technique to identify which EEG features were used by the network to classify an EEG epoch as favorable or unfavorable outcome, and also to understand failures of the network. Grad-CAM showed that the network relied on similar features than classical visual analysis for predicting unfavorable outcome (suppressed background, epileptiform transients). This study confirms that CNNs are promising models for EEG-based prognostication in comatose patients, and that Grad-CAM can provide explanation for the models' decision-making, which is of utmost importance for future use of deep learning models in a clinical setting.

Interest & Impact

Downloads

186 since deposited on 22 Nov 2019
53 in the past 12 months

Citations

5 Citations in Web of Science ®
6 Citations in Scopus

Search

in Google Scholar™

Services

Actions (login required)

Edit item

Actions (login required)

Edit item