A Multi-channel EEG Data Analysis for Poor Neuro-prognostication in Comatose Patients with Self and Cross-channel Attention Mechanism

Abstract

This work is part of the 'Predicting Neurological Recovery from Coma After Cardiac Arrest: The George B. Moody PhysioNet Challenge 2023' to investigate the predictive potential of bipolar electroencephalogram (EEG) recordings towards efficient prediction of poor neurological outcomes. A retrospective design using a hybrid deep learning approach is utilized to optimize an objective function aiming for high specificity, i.e., true positive rate (TPR) with reduced false positives (<0.05). A multichannel EEG array of 18 bipolar channel pairs from a randomly selected 5-minute segment in an hour is kept. In order to determine the outcome prediction, a combination of a feature encoder with 1-D convolutional layers, learnable position encoding, a context network with attention mechanisms, and finally, a regressor and classifier blocks are used. The feature encoder extricates local temporal and spatial features, while the following position encoding and attention mechanisms attempt to capture global temporal dependencies. Results: The proposed framework by our team, OUS_IVS, when validated on the challenge hidden test data, exhibited an unofficial score (not ranked) of 0.416 at 72 hours after the return of spontaneous circulation. The code for this paper is available on GitHub: https://github.com/HeminQadir/PhysioNet_OUS_IVS.