The University of British Columbia

The proposed algorithm is designed to detect changes in the heart rate trend signal which fits the dynamic linear model description. Based on this model, the interpatient and intraoperative variations are handled by estimating the noise covariances via an adaptive Kalman filter. An exponentially weighted moving average predictor switches between two different forgetting coefficients to allow the historical data to have a varying influence in prediction. The cumulative sum testing of the residuals identifies the change points online. The algorithm was tested on a substantial volume of real clinical data. Comparison of the proposed algorithm with Trigg's approach revealed that the algorithm performs more favorably with a shorter delay. The receiver operating characteristic curve analysis indicates that the algorithm outperformed the change detection by clinicians in real time