Key result
A video-based motion detection algorithm for ICU alarms achieved 87.0% sensitivity for true alarms and 87.2% specificity for false alarms, but had a critical 12.8% false-positive rate for false alarms.
Why the study?
Contemporary intensive care monitoring systems are sensitive to motion artifacts and cause excess false alarms, leading to alarm fatigue and hazardous desensitization.
Does a video-based motion detection algorithm accurately classify true versus false alarms in an intensive care setting?
Observational (n=45)
Blinded
Does a video-based motion detection algorithm accurately classify true versus false alarms in an intensive care setting?
A video-based motion detection algorithm showed high sensitivity for true alarms but requires additional layers to safely reduce false alarms in the ICU.
Answers are grounded in this paper and cite their sources.
May reduce ICU alarm fatigue but risks misclassification; leaves open prospective validation before adoption.
BACKGROUND: Contemporary monitoring systems are sensitive to motion artifacts and cause an excess of false alarms. This results in alarm fatigue and hazardous alarm desensitization. To reduce the number of false alarms, we developed and validated a novel algorithm to classify alarms, based on automatic motion detection in videos. METHODS: We considered alarms generated by the following continuously measured parameters: arterial oxygen saturation, systolic blood pressure, mean blood pressure, heart rate, and mean intracranial pressure. The movements of the patient and in his/her surroundings were monitored by a camera situated at the ceiling. Using the algorithm, alarms were classified into RED (true), ORANGE (possibly false), and GREEN alarms (false, i.e., artifact). Alarms were reclassified by blinded clinicians. The performance was evaluated using confusion matrices. RESULTS: A total of 2349 alarms from 45 patients were reclassified. For RED alarms, sensitivity was high (87.0%) and specificity was low (29.6%) for all parameters. As the sensitivities and specificities for RED and GREEN alarms are interrelated, the opposite was observed for GREEN alarms, i.e., low sensitivity (30.2%) and high specificity (87.2%). As RED alarms should not be missed, even at the expense of false positives, the performance was acceptable. The low sensitivity for GREEN alarms is acceptable, as it is not harmful to tag a GREEN alarm as RED/ORANGE. It still contributes to alarm reduction. However, a 12.8% false-positive rate for GREEN alarms is critical. CONCLUSIONS: The proposed system is a step forward toward alarm reduction; however, implementation of additional layers, such as signal curve analysis, multiple parameter correlation analysis and/or more sophisticated video-based analytics are needed for improvement.
No takes yet. Share an insight, caveat, or question.
Muroi et al. (2019) conducted an observational in Intensive care (n=45). Video-based automatic motion detection algorithm vs. Blinded clinicians was evaluated on Alarm classification accuracy (sensitivity and specificity). A video-based motion detection algorithm for ICU alarms achieved 87.0% sensitivity for true alarms and 87.2% specificity for false alarms, but had a critical 12.8% false-positive rate for false alarms.
Synapse has enriched 10 related papers. Consider them for comparative context: