Timing is everything: Combining EEG and MRI to predict neurological recovery after cardiac arrest

Combination strategy for prognostication in patients undergoing post-resuscitation care after cardiac arrest

This study investigated the prognostic performance of combination strategies using a multimodal approach in patients treated after cardiac arrest. Prospectively collected registry data were used for this retrospective analysis. Poor outcome was defined as a cerebral performance category of 3-5 at 6 months. Predictors of poor outcome were absence of ocular reflexes (PR/CR) without confounding factors, a highly malignant pattern on the most recent electroencephalography, defined as suppressed background with or without periodic discharges and burst-suppression, high neuron-specific enolase (NSE) after 48 h, and diffuse injury on imaging studies (computed tomography or diffusion-weighted imaging [DWI]) at 72-96 h. The prognostic performances for poor outcomes were analyzed for sensitivity and specificity. A total of 130 patients were included in the analysis. Of these, 68 (52.3%) patients had poor outcomes. The best prognostic performance was observed with the combination of absent PR/CR, high NSE, and diffuse injury on DWI [91.2%, 95% confidence interval (CI) 80.7-97.1], whereas the combination strategy of all available predictors did not improve prognostic performance (87.8%, 95% CI 73.8-95.9). Combining three of the predictors may improve prognostic performance and be more efficient than adding all tests indiscriminately, given limited medical resources.

Design of MRI structured spiking neural networks and learning algorithms for personalized modelling, analysis, and prediction of EEG signals

This paper proposes a novel method and algorithms for the design of MRI structured personalized 3D spiking neural network models (MRI-SNN) for a better analysis, modeling, and prediction of EEG signals. It proposes a novel gradient-descent learning algorithm integrated with a spike-time-dependent-plasticity algorithm. The models capture informative personal patterns of interaction between EEG channels, contrary to single EEG signal modeling methods or to spike-based approaches which do not use personal MRI data to pre-structure a model. The proposed models can not only learn and model accurately measured EEG data, but they can also predict signals at 3D model locations that correspond to non-monitored brain areas, e.g. other EEG channels, from where data has not been collected. This is the first study in this respect. As an illustration of the method, personalized MRI-SNN models are created and tested on EEG data from two subjects. The models result in better prediction accuracy and a better understanding of the personalized EEG signals than traditional methods due to the MRI and EEG information integration. The models are interpretable and facilitate a better understanding of related brain processes. This approach can be applied for personalized modeling, analysis, and prediction of EEG signals across brain studies such as the study and prediction of epilepsy, peri-perceptual brain activities, brain-computer interfaces, and others.