On-line segmentation algorithm for continuously monitored data in intensive care units

  title={On-line segmentation algorithm for continuously monitored data in intensive care units},
  author={S. Charbonnier and G. Becq and L. Biot},
  journal={IEEE Transactions on Biomedical Engineering},
  • S. Charbonnier, G. Becq, L. Biot
  • Published 2004
  • Computer Science, Medicine
  • IEEE Transactions on Biomedical Engineering
  • An on-line segmentation algorithm is presented in this paper. It is developed to preprocess data describing the patient's state, sampled at high frequencies in intensive care units, with a further purpose of alarm filtering. The algorithm splits the signal monitored into line segments-continuous or discontinuous-of various lengths and determines on-line when a new segment must be calculated. The delay of detection of a new line segment depends on the importance of the change: the more important… CONTINUE READING
    A New Approach to the Abstraction of Monitoring Data in Intensive Care
    • 16
    Adaptive Trend Change Detection and Pattern Recognition in Physiological Monitoring
    • 2
    Trend extraction based on variable time window length median filter
    • 2
    • Highly Influenced


    Publications referenced by this paper.
    Knowledge-Based Event Detection in Complex Time Series Data
    • 97
    • PDF
    Statistical pattern detection in univariate time series of intensive care on-line monitoring data
    • 68
    • PDF
    A critical review of trend-detection methodologies for biomedical monitoring systems.
    • 48
    Alarms and their limits in monitoring
    • 25
    The multi-state Kalman Filter in medical monitoring.
    • 22
    Clinical monitoring using regression-based trend templates
    • 79