US 11,922,796 B2
Predicting critical alarms
Rohan Joshi, Eindhoven (NL)
Assigned to KONINKLIJKE PHILIPS N.V., Eindhoven (NL)
Appl. No. 17/297,910
Filed by KONINKLIJKE PHILIPS N.V., Eindhoven (NL)
PCT Filed Nov. 27, 2019, PCT No. PCT/EP2019/082739
§ 371(c)(1), (2) Date May 27, 2021,
PCT Pub. No. WO2020/109381, PCT Pub. Date Jun. 4, 2020.
Claims priority of application No. 18208606 (EP), filed on Nov. 27, 2018.
Prior Publication US 2022/0044548 A1, Feb. 10, 2022
Int. Cl. G08B 31/00 (2006.01); G16H 20/30 (2018.01); G16H 40/63 (2018.01)
CPC G08B 31/00 (2013.01) [G16H 20/30 (2018.01); G16H 40/63 (2018.01)] 15 Claims
OG exemplary drawing
 
1. A computer-implemented method of predicting the occurrence of a critical alarm for a subject undergoing physiological parameter monitoring, the computer-implemented method comprising:
receiving a non-critical alarm signal indicating that the subject has entered a clinically undesirable state at a time of occurrence; and
in response to the non-critical alarm signal:
obtaining a set of one or more pre-alarm values derived from and/or comprising one or more values of at least one monitored physiological parameter of the subject collected within a pre-alarm time window (TW1) of a first predetermined length, wherein the start time (ttw) of the pre-alarm time window depends upon the time of occurrence (to) of the non-critical alarm signal and wherein the pre-alarm time window ends before or at the time of occurrence of the non-critical alarm signal; and
processing, using a machine-learning algorithm, the set of one or more pre-alarm values to generate a predictive indicator indicating a probability that the non-critical alarm signal will be followed, within a post-alarm time window (TW2), by a critical alarm signal indicating that the subject has entered a clinically actionable state,
wherein the post-alarm time window is of a second predetermined length and begins at the time of occurrence of the non-critical alarm signal.