More than 6 million cardiac arrests happen every year worldwide,and physicians are asked to offer a prognosis followinng the cardiac arrest.But the prognosis of neurological recovery after cardiac arrest given by doctors in clinical practice is subjective.A good prognosis results in continued care, and a poor prognosis typically leads to the withdrawal of life support and death. And the automated analysis of continuous EEG data has the potential to improve prognostic accuracy.Therefore,in this study, we used basic clinical information and continuous EEG recordings to predict the level of neurological recovery in patients with cardiac arrest.We developed a multiscale DNN combining convolutional neural networks (CNN) and long short-term memory (LSTM) using EEG and Patient information includes information recorded at the time of admission (age, sex), location of arrest (out or in-hospital), type of cardiac rhythm recorded at the time of resuscitation (shockable rhythms include ventricular fibrillation or ventricular tachycardia and non-shockable rhythms include asystole and pulseless electrical activity), and the time between cardiac arrest and ROSC.The CNN learns EEG feature representations while the multiscale LSTM captures short-term and long-term EEG dynamics on multiple time scales.Poor outcome is defined as a Cerebral Performance Category (CPC) score of 3-5 and good outcome as CPC score 1-2. We got the 0.3 true positive rate (TPR=0.6) for predicting a poor outcome (CPC of 3, 4, or 5) given a false positive rate (FPR) of less than or equal to 0.05 at 72 hours.