The goal of this proposed study is to develop a computational platform that can analyze BedMaster streaming data for early cardiac arrest detection (CAD) in the pediatric cardiac intensive care unit (CICU). Cardiac arrest in the pediatric ICU is high with the 2.12/1000 rate in 2013. After multiple years of effort, the survival-to-hospital-discharge rate is only around 43% in 2014, and many of these cardiac arrest survivors have neurodevelopmental issues and other secondary organ damage post the episode. The main challenge is the abruptness of a cardiac arrest episode. Thus, our long-term goal is to provide early intervention decision support for CICU physicians by predicting cardiac arrest from analyzing bedside monitor streaming data, and to improve overall survival-to-hospital-discharge rates of patients in CICU. The short-term objective is to develop a computational pipeline starting from high-resolution streaming data acquisition using the BedMaster system, followed by extracting cardiac arrest-related features from the streaming data for early cardiac arrest detection.