As the health sector adopts more and more technologies, the increased number of assistive devices from fans through power pumps to vital signs machines will bring with them their own warning alerts. Truth is that most do not require clinical intervention and are due to incorrect readings resulting from devices and alarms not configured for individual patients.
For example, patients with a low ECG voltage will trigger unnecessary alarms if the monitor does not adjust correctly. But among the endless bells and bells of the countless devices, how can caregivers discern from those true “wolf screams” from the false ones?
Artificial intelligence jumps on the scene
We mention that up to 99% of current alarm signals from patient monitoring devices are clinically negligible. Now imagine hearing 99% fewer alarms but just hearing the one that really requires medical attention. This is the promise that A.I. offers and has already been put into action.
Researchers have recently developed an A.I. solution to help caregivers cope with hearing overload. They implemented their reasoning algorithm to analyze a data set containing patient monitoring data and vital signs recorded during 32 surgical cases, which could then decide whether to group notifications instead of sending to prevent alarm fatigue. They published their findings in a paper that showed that their automatic reasoning mechanism helped reduce notifications received by caregivers by up to 99.3%!
As the authors noted, “almost all studies assume that a reduction in the number of total alarms and/or false alarms will reduce alarm fatigue.” However, the results are still in an experimental stage with more progress required before launching such an AI. in a clinical setting
