The audibility and the identification of 23 auditory alarms in the intensive care unit (ICU) and 26 auditory alarms in the operating rooms (ORs) of a 214-bed Canadian teaching hospital were investigated. Digital tape recordings of the alarms were made and analysed using masked-threshold software developed at the Universit de Montral. The digital recordings were also presented to the hospital personnel responsible for monitoring these alarms on an individual basis in order to determine how many of the alarms they would be able to identify when they heard them. Several of the alarms in both areas of the hospital could mask other alarms in the same area, and many of the alarms in the operating rooms could be masked by the sound of a surgical saw or a surgical drill. The staff in the OR (anaesthetists, anaesthesia residents, and OR technologists) were able to identify a mean of between 10 and 15 of the 26 alarms found in their operating theatres. The ICU nurses were able to identify a mean of between 9 and 14 of the 23 alarms found in their ICU. Alarm importance was positively correlated with the frequency of alarm identification in the case of the OR, rho=0·411, but was not significantly correlated in the case of the ICU, rho=0·155. This study demonstrates the poor design of auditory warning signals in hospitals and the need for standardization of alarms on medical equipment.