General Electric Company
Methods and systems for patient monitoring
Last updated:
Abstract:
Systems and methods are provided for false alarm suppression in patient monitoring systems. In one embodiment, a method comprises inputting each electronic signal of a plurality of electronic signals into a corresponding predictor cloud of a plurality of predictor clouds, each predictor cloud comprising a long short-term memory neural network and a recurrent neural network, and responsive to an alarm generated based on at least one of the plurality of electronic signals, suppressing the alarm responsive to outputs of the plurality of predictor clouds indicating the alarm is false. In this way, patient monitors may be more reliable with fewer false alarms.
Status:
Grant
Type:
Utility
Filling date:
24 Jan 2017
Issue date:
6 Sep 2022