Triggering of systolic arterial pressure alarms using statistics-based versus threshold alarms

Threshold systolic arterial pressure alarms often use pre-operative values as a guide for intra-operative values. Recently, two systems (normalisation and principal component analysis) have been described that use the 'current' systolic arterial pressure and the change in systolic arterial pressure over a preceding time interval to generate an alarm based on units of standard deviation. Normalisation and principal component analysis techniques should prioritize alarms for clinically significant changes and hence reduce overall activation of alarms. Our aim was to measure the change in alarm activation using these techniques compared with standard threshold alarms. Systolic blood pressure data, collected from 10 patients (a total of 2177 min at 100 Hz), were cleaned and submitted to analysis using threshold alarms, normalisation and principal component analysis. With the threshold alarms set at 100 mmHg (low) and 140 mmHg (high), and a 5-min window, the alarms were activated for 557 min; using statistics-based thresholds the alarms were activated for 169 min (normalisation) and 155 min (principal component analysis), a reduction of approximately 70-72%.