Event Detection on Patient Monitoring Data Using Causal Probabilistic Networks

Abstract

Applications are described of the knowledge-representation technique Causal Probabilistic Networks for the detection of events related to the patient and the monitoring equipment, in the context of intensive care patient monitoring. The purpose of the event detection is to reduce the number of false alarms generated by the patient monitor, and to generate alarms related to patient or equipment events rather than to threshold violation. A PC-based system has been developed and tested on patient data. A system for real-time use in patient monitoring is under development.