An approach to intelligent ischaemia monitoring.

The paper describes an approach to intelligent ischaemia event detection based on ECG ST-T segment analysis. ST-T trends are processed by means of a Bayesian forecasting approach using the multistate Kalman filter. A complete procedure, intended for use in CCU/ICU monitoring areas, is proposed, in order to give the clinician an intelligent monitoring tool. The approach serves to describe trends and their changes in a symbolic way. A novel aspect is its ability to observe certain features of ST-T elevation/depression not detected by other means, and to reject artefacts and erroneous events. A sensitivity of 89.58% and a predictivity of 84.31% are obtained on selected records of the European ST-T database. Using a restriction on event amplitude, the predictivity is raised to 95.55%. An ischaemia sensitivity index of 1.2 was determined. The method has been shown to be a robust and practical trend analysis tool, and seems to be appropriate for numeric/symbolic transformations in next-generation intelligent monitoring systems.