On‐line adaptive trend extraction of multiple physiological signals for alarm filtering in intensive care units

Abstract

This paper presents an alarm validation system dedicated to patient monitoring in intensive care units (ICU). Several physiological signals are continuously acquired and an on-line trend extraction method is implemented for each one. A trend is a succession of contiguous semi-quantitative episodes, expressing the time evolution of a signal with several symbols. The difference between the trend and the signal is considered as a residual. In this paper, trend extraction is based on several thresholds that are adapted on-line, following the signal variations. Multivariate change indices are further deduced from the trends and the residuals. They provide an indication of changes to patient hemodynamic and respiratory state. An alarm validation system based on these indices is then proposed, which uses fuzzy decision making. Whenever a monitoring system sets off an alarm, the system proposed carries out a backward analysis of the physiological variables monitored. The system enables various policies to be implemented: filtering of false alarms due to artifacts, confirmation of true alarms due to a patient state change. The system was tested on more than 50 h of data recorded on adult patients in an ICU unit, when 105 SpO 2 alarms were set off by a fixed threshold alarm system. The comparison between the decision made on-line by the validation system and the decision made by a medical expert for each of these alarms showed that the system is able to recognize 100% of true alarms and filter 50-80% of false alarms.

A self-tuning adaptive trend extraction method for process monitoring and diagnosis

“…The algorithm is tuned by 3 parameters the value of which depends on the signal analysed. In [32], an adaptive version of the algorithm is proposed to take into account changes in variance that may occur in physiological signals because of a change in the care context. The value of the tuning parameters are still fixed for each physiological signal but they switch between 2 sets of values, one set when the variance is high and one set when the variance is low.…”

Data Mining for Wearable Sensors in Health Monitoring Systems: A Review of Recent Trends and Challenges

“…Some of the papers considered finding irregular patterns in vital signs time series such as abnormal episodes in ECG pulses [31,32], SpO 2 signal [33] and blood glucose level [28], which mostly discover unusual temporal patterns in continuous data. Few of the papers have used domain knowledge and predefined information to detect anomalies for decision making such as anomaly detection in sleep episodes [34,35], and finding hazardous stress levels [36].…”

Signal processing for monitoring and diagnosis: Medical applications

“…In the third paper, Charbonnier and Gentil 6 propose an alarm validation system to reduce the number of false alarms generated by the threshold alarm system currently used to monitor the oxygen saturation rate on patients hospitalized in Intensive Care. The algorithm achieves an automatic assessment of the alarm situation, using several physiological variables.…”