Using the blood pressure waveform to reduce critical false ECG alarms

Intensive Care Unit (ICU) false alarm rates can be as high as 86%, leading to a desensitization of the clinical attending staff, slowing of response times and even ignoring true alarms. False alarms are commonly caused by single channel artifacts and could be avoided if information from other independent signals were fused to form a more robust hypothesis of the etiology of the alarm. We used a standard multi-parameter ICU database (PhysioNet´s MIMIC DB) to investigate the frequency of false critical (or ´life- threatening´) arrhythmia alarms produced by a commercial ICU monitoring system. Multiple expert reviews of the alarms were made using all the relevant files in the MIMIC DB (a total of 21 subjects and 800 hours of waveform data). We found that 25% of the 89 life-threatening alarms were considered false. We then implemented an algorithm to suppress false alarms, using information derived from the arterial blood pressure signal. This simple yet robust strategy was successful in suppressing all false alarms, without suppressing any true alarms.