PROJECT TITLE :

Real-time analysis for short-term prognosis in intensive care

ABSTRACT :

There's an incredible quantity of data offered to physicians at the point of care in intensive care environments; however, physicians don't have the tools to extract relevant clinical information in a timely manner. They largely depend upon manual inspection of the data to form diagnosis and prognosis. New software technologies build it attainable to automatically generate meaningful data in real-time from the physiological knowledge streams of patients. These real-time monitoring software technologies can support multiple concurrent patients and have been developed mainly to be applied in a reactive way, for the detection of patient complications. This paper proposes ways to extend these real-time monitoring technologies to assist intensive care become a lot of proactive. We have a tendency to present a system style and algorithms for a prototype system that produces in real-time short-term predictions of patient physiological information from live and historical patient data. One technique relies solely on the patient's own live data streams. The opposite technique is based on comparing the patient's physiological data streams with data streams of similar patients that have been monitored within the past. An extensive experimental study of this method is proposed to evaluate its predictive ability.