Stream computing and its application to critical care

Summary form only given. Intensive care units (ICUs) worldwide offer support for patients in need of critical care. They boast a range of state of the-art medical monitoring devices to monitor a patient's physiological parameters such as blood oxygen, blood pressure, and heart rate. Other devices such as ventilators offer mechanical life support. Recent clinical research has found that physiological parameters that are seemingly unrelated to a given diagnosis have been found to show certain behaviour changes prior to diagnosis, demonstrating the potential to create systems that process this data in real time once it is received from distributed sources. Several existing computing paradigms are challenged by the real-time requirements of critical care. In this tutorial a new paradigm of computing known as Stream Computing will be introduced as a means to implement architectures for real-time analysis of multiple patients using data that have varying frequencies to watch for onset of multiple diagnoses.