This method enhances the accuracy of false alarm detection in ICUs by accounting for the synergistic power of signal attributes in the feature selection stage.
About
Description: False alarms are widely considered the number one hazard imposed by the use of medical technologies. Caregivers are usually overwhelmed with 350 alarm conditions per patient per day, of which 80-99% are meaningless or false. These false alarms can cause many problems, such as alarm fatigue among caregivers and the possibility of missing a true life-threatening event lost in a cacophony of multiple alarms. This invention describes a multifaceted false alarm reduction mechanism to effectively decompose the collected signals in multiple resolutions, filter the noise, and extract a set of additional geometric features describing the signal using an innovative transformation method in determining the predictors of false alarms. Potential applications: Clinical applications to reduce false alarms. Benefits and advantages: This method enhances the accuracy of false alarm detection in ICUs by accounting for the synergistic power of signal attributes in the feature selection stage. By utilizing information theory and game theory, this method accounts for inter-features mutual information in determining the most correlated predictors with respect to false alarm by calculating Banzhaf power of each feature.
Key Benefits
Benefits and advantages: This method enhances the accuracy of false alarm detection in ICUs by accounting for the synergistic power of signal attributes in the feature selection stage. By utilizing information theory and game theory, this method accounts for inter-features mutual information in determining the most correlated predictors with respect to false alarm by calculating Banzhaf power of each feature.
Applications
Potential applications: Clinical applications to reduce false alarms.