Granted Patent B2

US 12,661,018 · App. 17/600,370 · Granted Jun 23, 2026

Inventors: Justin R. Burwinkel (Eden Prairie, MN); Buye Xu (Sammamish, WA); Jason A. Galster (Studio City, CA); Lauren Petley (Cincinnati, OH); Peter J. Tetrick (Chaska, MN); Sourav K. Bhunia (Shoreview, MN); Peggi S. Cross (Tucson, AZ); Martin McKinney (Minneapolis, MN)

Assignee: Starkey Laboratories, Inc.

A61B5/02055A61B3/113A61B5/0002A61B5/021A61B5/024A61B5/1112A61B5/1114A61B5/112A61B5/14532A61B5/14535A61B5/14551A61B5/16A61B5/4023A61B5/4076A61B5/4561A61B5/4875A61B5/7275A61B5/7282G08B21/043G08B21/0446A61B2562/0219

Abstract

Claims (52)

1 . A monitoring system comprising:

a first sensor adapted to detect a first characteristic of a subject and generate data representative of the first characteristic of the subject, wherein the first characteristic comprises a first physiological characteristic of the subject

a second sensor adapted to detect a second characteristic of the subject and generate data representative of the second characteristic of the subject;

a controller operatively connected to the first and second sensors, wherein the controller is adapted to:

receive data representative of the first characteristic of the subject from the first sensor;

determine statistics for a first condition substate of the subject over a monitoring time period based upon the data received from the first sensor;

receive data representative of the second characteristic of the subject from the second sensor;

determine statistics for a second condition substate of the subject over the monitoring time period based upon the data received from the second sensor;

compare the statistics of the first condition substate to the statistics of the second condition substate;

confirm the first condition substate of the subject when the first condition substate is substantially similar to the second condition substate; and

determine the statistics of an overall condition state of the subject over the monitoring time period based upon the confirmed first condition substate; and

utilize a machine learning model to determine a fall risk value based upon the determined overall condition state of the subject;

generate a fall prevention output when the fall risk value crosses a fall risk threshold, the fall prevention output comprising modifying, via mesh networks or the internet of things, the lighting within an area proximate to the subject;

wherein the machine learning model is further configured to predict a time at which the subject will ingest a particular medication based on location information, and to learn the effects that the particular medication has on the subject based on changes in the data representative of the first characteristic or data representative of the second characteristic in a time period after the time at which the subject is predicted to ingest the particular medication.

2 . The system of claim 1 , wherein each of the first and second condition substates comprises at least one of a body posture, mental, body motion, or sensory substate.

3 . The system of claim 1 , wherein the physiological characteristic comprises at least one of a determined fall risk statistic, inertial sensor data, heart rate information, blood pressure information, drug concentration information, blood sugar level, body hydration information, neuropathy information, blood oximetry information, hematocrit information, body temperature, age, sex, gait or postural stability attribute, vision, eye movement, geographic location, or head movement.

4 . The system of claim 1 , wherein the first sensor is operatively connected to the subject.

5 . The system of claim 1 , wherein the fall prevention output comprises a modification of an environmental context of the subject.

6 . The system of claim 1 , wherein the fall prevention output comprises transmission of the physiological data to one or more of a caregiver, a medical professional, a database, or the subject.

7 . The system of claim 1 , wherein the controller is further adapted to:

determine statistics for a third condition substate of the subject over a second monitoring time period based upon the data received from the first sensor;

determine statistics for a fourth condition substate of the subject over the second monitoring time period based upon the data received from the second sensor;

compare the statistics of the third condition substate to the statistics of the fourth condition substate;

confirm the third condition substate of the subject if the third condition substate is substantially similar to the fourth condition substate; and

determine the statistics of a second overall condition state of the subject over the second monitoring time period based upon the confirmed third condition substate.

8 . The system of claim 1 , wherein the controller is further adapted to determine a balance event of the subject when the statistics of the overall condition state indicates one or more of an unintentional loss of balance or postural stability and vestibular disturbance.

9 . The system of claim 1 , wherein the system is configured to update the machine learning model to include the effects that a specific medication has on an individual.

10 . The system of claim 1 , wherein the system is configured to update the machine learning model using specific data regarding the severity and timing of any observable changes to the subject that is collected, wherein the observable change can relate to one or more characteristics of the subject's gait and postural stability.

11 . The system of claim 1 , wherein the machine learning model is further configured to predict the time at which the subject will ingest the particular medication based on any of historical contextual data, scheduled reminders, and location information.

12 . The system of claim 1 , wherein the fall prevention output further comprises a modification of a temperature, oxygen mix, humidity, or air quality of the area proximate to the subject.

13 . The system of claim 1 , wherein the fall prevention output further comprises a modification of one or more features and actions of a mobility device, an assistive device, or an exoskeleton.

14 . A method comprising:

receiving data representative of a first characteristic of a subject from a first sensor, wherein the first sensor comprises an inertial measurement unit (IMU);

determining statistics for a first condition substate of the subject over a monitoring time period based upon the data received from the first sensor;

receiving data representative of a second characteristic of the subject from a second sensor, wherein the second sensor comprises an electroencephalography (EEG) sensor;

determining statistics for a second condition substate of the subject over the monitoring time period based upon the data received from the second sensor;

comparing the statistics of the first condition substate to the statistics of the second condition substate;

confirming the first condition substate of the subject when the first condition substate is substantially similar to the second condition substate;

differentiating between reflexive and voluntary control of the subject's posture and/or movement using the IMU and the EEG sensor;

suggesting a neurological problem of the subject when the first condition substate of the subject contradicts the second condition substate of the subject;

determining the statistics of an overall condition state of the subject over the monitoring time period based upon the confirmed first condition substate, wherein the controller is further adapted to utilize a machine learning model to determine a fall risk value based upon the determined overall condition state of the subject; and

generating a fall prevention output when the fall risk value crosses a fall risk threshold, the fall prevention output comprising modifying, via mesh networks or the internet of things, the lighting within an area proximate to the subject.

15 . The method of claim 14 , wherein each of the first and second condition substates comprises at least one of a body posture, mental substate, body motion, or sensory substate.

16 . The method of claim 14 , wherein the data representative of the first characteristic and the data representative of the second characteristic comprises at least one of physiological data and contextual information, wherein the fall prevention output comprises transmission of one or more of the physiological data and the contextual information to one or more of a caregiver, a medical professional, a database, or the subject.

17 . The method of claim 14 , further comprising:

determining statistics for a third condition substate of the subject over a second monitoring time period based upon the data received from the first sensor;

determining statistics for a fourth condition substate of the subject over the second monitoring time period based upon the data received from the second sensor;

comparing the statistics of a third condition substate to the statistics of a fourth condition substate;

confirming the third condition substate of the subject if the third condition substate is substantially similar to the fourth condition substate; and

determining the statistics of a second overall condition state of the subject over the second monitoring time period based upon the confirmed third condition substate.

18 . The method of claim 14 , further comprising determining a balance event of the subject when the statistics of the overall condition state indicates one or more of an unintentional loss of balance or postural stability and vestibular disturbance.

19 . The method of claim 14 , wherein the first sensor comprises a microphone and the second sensor comprises an eye movement sensor, the method further comprising suggesting Tullio's Phenomenon in the subject when postural adjustments are detected by the second sensor in response to a sound detected by the first sensor.

Assignments (1)

Continuity (2)

References Cited (400)