Predictive analysis of patient recovery from cardiac-respiratory arrest

Abstract

The severity of neuronal damages in comatose patients following anoxic brain injury can be probed by evoked auditory responses. However, it remains challenging to predict the return to full consciousness of post-anoxic coma of hospitalized patients. We presented here a method to predict the return to consciousness based on the analysis of periodic responses to auditory stimulations, recorded from surface cranial electrodes. The input data are event-related potentials (ERPs), recorded non-invasively with electro-encephalography (EEG). We extracted several novel features from the time series responses in a window of few hundreds of milliseconds from deviant and non-deviant auditory stimulations. We use these features to construct two-dimensional statistical maps, that show two separated clusters for recovered (conscience) and deceased patients, leading to a high classification success as tested by a cross-validation procedure. Finally, using Gaussian, K-neighborhood and SVM classifiers, we construct probabilistic maps to predict the outcome of post-anoxic coma. To conclude, statistics of deviant and non-deviant responses considered separately provide complementary and confirmatory predictions for the outcome of anoxic coma.