Abstract
Audible medical alarms are ubiquitous in acute healthcare environments, but caregivers cannot reliably identify them. Furthermore, background noise and psychoacoustic factors can interfere with alarm recognition and contribute to alarm fatigue. We developed and validated an acoustic digital signal processing algorithm for the automatic identification of audible medical alarms. The algorithm uses the short-time Fourier transform to decompose audio signals and extract the alarm sounds' fundamental frequencies, harmonics, and periodicity. This information is then used to classify and recognize these sounds. The identification algorithm demonstrates robust performance (F1 score of 93% to 100%) and 100% negative predictive value in identifying single or multiple medical audible alarms under both quiet and noisy conditions. The algorithm we developed represents a robust approach for the identification of audible medical alarms that perform with high accuracy in noisy environments. It can be used to identify and classify alarms in medical settings for research and clinical purposes.
