Systems and methods for using primary and redundant devices for detecting falls

Patent metadata

Field	Value
Publication number	US-11468758-B2
Application number	US-202117339706-A
Country	US
Kind code	B2
Filing date	Jun 4, 2021
Priority date	Nov 13, 2020
Publication date	Oct 11, 2022
Grant date	Oct 11, 2022

Abstract

In some instances, a fall detection system comprising a first fall detection device and a user device is provided. The fall detection device is configured to: detect an occurrence of a fall event associated with an individual based on sensor information from the one or more sensors and a fall detection model; and provide a first indication indicating the occurrence of the fall event. The user device is configured to: receive the first indication; cause display of a prompt requesting user feedback as to whether the individual fell based on the first indication and a second indication from a second fall detection device; provide update information indicating for the first fall detection device to update the fall detection model based on the user feedback; and provide user fall information associated with the occurrence of the fall event based on the user feedback.

First claim

The invention claimed is:

1. A fall detection system, comprising:
an enterprise computing system, comprising:
one or more first processors; and
a first non-transitory computer-readable medium having first processor-executable instructions stored thereon, wherein the first processor-executable instructions, when executed, facilitate:
training one or more machine learning (ML) datasets;
obtaining, from a user device associated with an individual, user fall information indicating the individual has fallen;
obtaining prescription information indicating one or more medical prescriptions for the individual;
subsequent to training the one or more ML datasets, inputting the user fall information and the prescription information into the one or more ML datasets to determine causation information indicating whether the one or more medical prescriptions caused the individual to fall; and
providing the causation information to a second computing device.

2. The fall detection system of claim 1 , wherein the user fall information comprises a user identifier (ID) indicating an identity of the individual, and
wherein the first processor-executable instructions, when executed, facilitate:
providing the user ID to a healthcare computing device, and
wherein obtaining the prescription information is in response to providing the user ID to the healthcare computing device.

3. The fall detection system of claim 1 , wherein the user fall information comprises information indicating a time stamp associated with the individual falling,
wherein the prescription information indicates a time for the individual to take a medication, and
wherein inputting the user fall information and the prescription information into the one or more ML datasets comprises inputting the time stamp and the time for the individual to take the medication into the one or more ML datasets to determine the causation information.

4. The fall detection system of claim 1 , further comprising:
a fall detection device comprising:
one or more second processors; and
a second non-transitory computer-readable medium having second processor-executable instructions stored thereon, wherein the second processor-executable instructions, when executed, facilitate:
detecting an occurrence of a fall event associated with the individual based on first sensor information from one or more sensors and a fall detection model; and
providing, to the user device, an indication indicating the occurrence of the fall event; and

the user device comprising:
one or more third processors; and
a third non-transitory computer-readable medium having third processor-executable instructions stored thereon, wherein the third processor-executable instructions, when executed, facilitate:
based on the indication, causing display of a prompt requesting user feedback as to whether the individual fell;
based on the user feedback, providing, to the fall detection device, update information indicating for the fall detection device to update the fall detection model.

5. The fall detection system of claim 4 , wherein the fall detection model is a Hidden Markov Model (HMM).

6. The fall detection system of claim 5 , wherein the first sensor information comprises movement information indicating movement of the individual and height information indicating a height corresponding to the fall detection device, and
wherein detecting the occurrence of the fall event comprises:
inputting the movement information and the height information into the HMM to determine the occurrence of the fall event.

7. The fall detection system of claim 5 , wherein the HMM comprises a plurality of coefficients associated with a transition probability and an emission probability, and
wherein detecting the occurrence of the fall event is based on the transition probability and the emission probability of the HMM.

8. The fall detection system of claim 7 , wherein the second processor-executable instructions, when executed, further facilitate:
updating, based on the update information, the plurality of coefficients associated with the transition probability and the emission probability.

9. The fall detection system of claim 8 , wherein the update information comprises a plurality of updated coefficients for updating the HMM.

10. The fall detection system of claim 4 , wherein the fall detection model is a Monte Carlo Simulation Model.

11. The fall detection system of claim 10 , wherein the first sensor information comprises movement information indicating movement of the individual and height information indicating a height corresponding to the fall detection device, and
wherein detecting the occurrence of the fall event comprises:
inputting the movement information and the height information into the Monte Carlo Simulation Model to determine the occurrence of the fall event.

12. The fall detection system of claim 4 , further comprising:
one or more environmental sensors configured to:
detect environmental sensor information associated with the individual; and
provide the environmental sensor information to the user device, and wherein the third processor-executable instructions, when executed, further facilitate:
receiving the environmental sensor information from the one or more environmental sensors, and
wherein causing display of the prompt requesting the user feedback as to whether the individual fell is further based on the environmental sensor information.

13. The fall detection system of claim 12 , wherein the one or more environmental sensors comprise one or more pressure sensors interwoven into a floor of a residence of the individual.

14. The fall detection system of claim 12 , wherein the one or more environmental sensors comprise one or more light motion sensors.

15. The fall detection system of claim 12 , wherein the one or more environmental sensors comprise one or more active sonar distance sensors.

16. A method, comprising:
training, by a fall detection system, one or more machine learning (ML) datasets;
obtaining, by the fall detection system and from a user device associated with an individual, user fall information indicating the individual has fallen;
obtaining, by the fall detection system, prescription information indicating one or more medical prescriptions for the individual;
subsequent to training the one or more ML datasets, inputting, by the fall detection system, the user fall information and the prescription information into the one or more learning ML datasets to determine causation information indicating whether the one or more medical prescriptions caused the individual to fall; and
providing, by the fall detection system, the causation information to a second computing device.

17. The method of claim 16 , wherein the user fall information comprises a user identifier (ID) indicating an identity of the individual, and wherein the method further comprises:
providing the user ID to a healthcare computing device, and
wherein obtaining the prescription information is in response to providing the user ID to the healthcare computing device.

18. The method of claim 16 , wherein the user fall information comprises information indicating a time stamp associated with the individual falling,
wherein the prescription information indicates a time for the individual to take a medication, and
wherein inputting the user fall information and the prescription information into the one or more ML datasets comprises inputting the time stamp and the time for the individual to take the medication into the o

Assignees

• Aetna Inc

Inventors

• Kurfirst Dwayne

Classifications

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G08B21/0446

  worn on the body to detect changes of posture, e.g. a fall, inclination, acceleration, gait · CPC title

• G06N20/00

  Machine learning · CPC title

• G08B21/043 Primary

  detecting an emergency event, e.g. a fall · CPC title

• G08B29/188

  Data fusion; cooperative systems, e.g. voting among different detectors · CPC title