Predicting occupant exit from support apparatus

Patent metadata

Field	Value
Publication number	US-11883158-B2
Application number	US-202117322031-A
Country	US
Kind code	B2
Filing date	May 17, 2021
Priority date	Jun 5, 2020
Publication date	Jan 30, 2024
Grant date	Jan 30, 2024

Abstract

An exit prediction system for a support apparatus receives data inputs from one or more force sensors without zeroing the one or more force sensors. Changes in the data inputs are detected to determine whether the detected changes indicate a movement trend. An exit prediction is determined based at least partially on the movement trend, and without combining the data inputs from the one or more force sensors to determine the occupant's weight. A notification is generated based on the exit prediction.

First claim

What is claimed is:

1. An exit prediction system comprising:
a bed including:
a frame;
one or more force sensors positioned on the frame; and
a computing device included on the bed, the computing device including:
a processing unit; and
a memory in communication with the processing unit; the memory storing machine-readable instructions that, when executed by the processing unit, cause the processing unit to:
receive data inputs from the one or more force sensors, the data inputs being received without zeroing the one or more force sensors, wherein the data inputs are analog-to-digital (A/D) counts;
detect changes in the data inputs from the one or more force sensors, wherein the detected changes in the data inputs are detected changes in the A/D counts received from each of the force sensors individually;
store predefined changes in A/D counts associated with movement trends, wherein the movement trends are associated with movements performed by occupants in order to exit the bed;
determine whether the detected changes indicate a movement trend by comparing the detected changes to the predefined changes to determine whether the detected changes are indicative of the movement trend;
determine an exit prediction based at least partially on the movement trend, the exit prediction being determined without combining the data inputs from the one or more force sensors to determine a weight of an occupant of the bed; and
generate a notification based on the exit prediction, wherein the notification is generated on the bed.

2. The system of claim 1 , wherein the A/D counts are derived from analog signals received from the one or more force sensors.

3. The system of claim 2 , wherein the analog signals are voltages that correspond to forces applied to the one or more force sensors.

4. The system of claim 3 , further comprising an analog-to-digital converter that converts the analog signals from the one or more force sensors into the A/D counts.

5. The system of claim 1 , wherein control rules are applied to the movement trend to determine the exit prediction, and the control rules include Shewhart control logic.

6. The system of claim 1 , further comprising one or more siderail sensors that detect a position of one or more siderails of the bed, and wherein the exit prediction is at least partially based on the movement trend and the position of the one or more siderails.

7. The system of claim 6 , wherein the one or more siderail sensors detect whether a footboard is attached to the bed, and wherein the exit prediction is at least partially based on the movement trend and whether the footboard is attached to the bed.

8. A method of predicting an occupant exit from a support apparatus, the method comprising:
receiving data inputs detected from one or more force sensors positioned on a frame of the support apparatus, wherein the data inputs are analog-to-digital (A/D) counts representing voltage or current magnitudes of the one or more force sensors, and the data inputs are received without zeroing the one or more force sensors;
detecting changes in the data inputs from the one or more force sensors without combining the data inputs to determine a weight of an occupant of the support apparatus, the detected changes in the data inputs are detected changes in the A/D counts received from each of the force sensors individually;
storing predefined changes in A/D counts associated with movement trends, wherein the movement trends are associated with movements performed by occupants in order to exit the support apparatus;
determining whether the detected changes indicate a movement trend by comparing the detected changes to the predefined changes to determine whether the detected changes are indicative of the movement trend;
determining an exit prediction based at least partially on the movement trend, the exit prediction indicating a likelihood for the occupant exit from the support apparatus; and
generating a notification based on the exit prediction, wherein the notification is generated on the support apparatus.

9. The method of claim 8 , wherein the movement trend includes moving from a supine position to a sitting upright position, rolling from a right side to a left side, and rolling from the left side to the right side while being positioned on the support apparatus.

10. The method of claim 8 , further comprising:
using machine learning to recognize trends in the detected changes to determine whether the detected changes indicate the movement trend.

11. The method of claim 8 , further comprising:
applying control rules to determine the exit prediction from the movement trend, wherein the control rules include Shewhart control logic.

12. The method of claim 8 , further comprising:
detecting a position of one or more siderails of the support apparatus, the one or more siderails being positionable between deployed, intermediate, and stowed positions;
determining that the movement trend is directed toward a siderail of the one or more siderails that is in the stowed or intermediate position; and
generating an exit prediction that the occupant is likely to exit the support apparatus.

13. The method of claim 8 , further comprising:
detecting that a footboard has been removed from the support apparatus;
determining that the movement trend is directed toward a foot end of the support apparatus; and
generating an exit prediction that the occupant is likely to exit the support apparatus.

Assignees

• Hill Rom Services Inc

Inventors

• Bender Justin
• Choi Kin Meng
• Cohn Anthony
• Schultz Frederick Keith
• Seshadri Sridhar Karimpuzha
• Simpson Thomas L

Classifications

• A61B5/1115 Primary

  Monitoring leaving of a patient support, e.g. a bed or a wheelchair · CPC title

• A61B5/1126

  using a particular sensing technique · CPC title

• A61B5/7264

  Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems · CPC title

• A61B5/746

  Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms · CPC title

• A61B5/747

  in case of emergency, i.e. alerting emergency services · CPC title