查看文章

In an intensive care unit (ICU), an accurate prognosis of comatose patients' recovery is critical for ongoing medical interventions. Patient prognosis guides decisions around continuation of care. Patients may recover from a coma despite poor initial prognosis; thus, more reliable predictors for recovery are needed. Electroencephalography (EEG)-based neurological markers may complement the current prognosis. The PhysioNet Challenge 2023 includes a dataset of EEG signals and clinical attributes from a total of 1020 adult patients in ICUs that remained in a coma after cardiac arrest, 607 of whom were dedicated to algorithmic training. We conceptualized a novel time-embedded feature space for continuous EEG followed by a bidirectional long short-term memory for learning any temporal patterns associated with comatose patients' recovery. We extracted EEG-related attributes: dynamic range, skewness, kurtosis, and …