JMIR Publications

ABSTRACT

Background:

Although alarm safety is a critical issue that needs to be addressed to improve patient care, hospitals have not given serious consideration to how their staff should be responding to clinical alarms. Studies have indicated that 80 to 99 percent of alarms in hospital units are false or clinically insignificant, do not present a real danger to patients and lead caregivers to miss relevant alerts announcing significant harm or life-threatening events. The lack of use of any intelligent filter for detecting recurrent, irrelevant and/or false alarms before alerting health providers can culminate in a complex and overwhelmed scenario of a sensory overload for the medical team, known as Alarm Fatigue.

Objective:

This paper’s main goal is to propose a solution for mitigating alarm fatigue by using an automatic reasoning mechanism to decide how to calculate False Alarm Probability (FAP) for alarms and whether to include an indication of the FAP (FAP_LABEL) to a notification to be visualized by healthcare team members designed to help them prioritize which alerts they should respond to next. The aim is to reduce alarm fatigue consequences without compromising patient safety.

Methods:

The new approach we are presenting for coping with the alarm fatigue problem uses an automatic reasoner to decide how to notify caregivers about anomalies detected by a patient monitoring system, where a large number of warnings can lead to alarm fatigue with an indication of false alarm probability that can assist them on how to prioritize the next alert to attend.

Results:

The main contribution described in this paper is a reasoning algorithm that specifies how to detect false alarms and notify caregivers with an indication of false alarm probability to avoid alarm fatigue without compromising patient safety. Our reasoning algorithm decides how to calculate false alarm probability for alerts triggered by sensors and multi-parametric monitors in an ICU, based on false alarm indicators we defined in this work.

Conclusions:

Experiments were conducted to demonstrate that by providing an intelligent notification system we could reason about how to identify false alarms by analyzing alarm-context information. The Reasoner entity we described in this paper was able to attribute FAP values to alarms based on false alarm indicators, and to notify caregivers with a FAP LABEL indication without compromising patient safety.