US 12,484,860 B2
Predictive fall event management system and method of using same
Justin R. Burwinkel, Eden Prairie, MN (US); Buye Xu, Sammamish, WA (US); Jason A. Galster, Studio City, CA (US); Peter J. Tetrick, Chaska, MN (US); and Sourav K. Bhunia, Shoreview, MN (US)
Assigned to Starkey Laboratories, Inc., Eden Prairie, MN (US)
Filed by Starkey Laboratories, Inc., Eden Prairie, MN (US)
Filed on Apr. 26, 2023, as Appl. No. 18/139,671.
Application 18/139,671 is a continuation of application No. 16/725,766, filed on Dec. 23, 2019, granted, now 11,638,563.
Claims priority of provisional application 62/785,295, filed on Dec. 27, 2018.
Prior Publication US 2023/0404490 A1, Dec. 21, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. A61B 5/00 (2006.01); A61B 5/11 (2006.01); G08B 21/04 (2006.01); G16H 50/30 (2018.01)
CPC A61B 5/7275 (2013.01) [A61B 5/1117 (2013.01); A61B 5/112 (2013.01); G08B 21/043 (2013.01); G08B 21/0446 (2013.01); G16H 50/30 (2018.01)] 20 Claims
OG exemplary drawing
 
1. A predictive fall event management system, comprising:
an ear-worn device; and
a controller operatively connected to the ear-worn device, wherein the controller is adapted to:
receive one or more of
physiological data representative of a physiological characteristic of a wearer of the ear-worn device over a monitoring time period; and
contextual data representative of context information of the wearer over the monitoring time period;
wherein the received data comprises at least one time-varying piece of data;
determine one or more future physiological states or contextual states based at least in part on one or more of the physiological data and the contextual data, wherein each future physiological state comprises a confidence interval associated with a physiological state that is predicted to occur at a future time, and wherein each future contextual state comprises a confidence interval associated with a contextual state that is predicted to occur at a future time;
estimate a probability of a fall for a plurality of future time intervals based at least in part on one or more of the physiological data and the contextual data, wherein the probability of the fall changes as a function of time based at least in part on the at least one time-varying piece of data;
determine, for the plurality of future time intervals, whether a fall condition is satisfied based upon the one or more future physiological states or contextual states; and
generate a fall prevention output responsive to each satisfaction of the fall condition.