IP Library Granted Patent US 12676060
Granted Patent B1
US 12676060 · App. 18/748,016 · Granted Jul 7, 2026

Systems and methods for a fall prevention system

Inventors: Albert Biemond (San Francisco, CA); Trent Maruyama (San Francisco, CA)
Assignee: Dignity Health
G08B21/02B25J11/009G03H1/0005G06T7/70G06V10/774G06V20/52G06V40/10G06V40/23G08B7/06G06T2207/20081G06T2207/30196G06T2207/30232
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12676060
App. No.
18/748,016
Granted
Jul 7, 2026
Kind
B1
Abstract

A fall prevention system provides intervention and distraction to attempt to prevent a “fall risk” patient from falling from bed while providing alerts to caregivers. The system provides verbal, visual and tactile interventions to create a distraction and time for a nurse or caregiver to intervene and prevent a fall.

Claims (42)

1 . A system, comprising:

a processor in communication with a memory and the intervention element, the memory including instructions executable by the processor to:

access temporally adjacent sensor observations obtained from a sensor array in communication with the processor, the sensor array being positioned within the space designated for the patient;

determine, using time-dependent analysis of the temporally adjacent sensor observations, that a position-change pattern of a patient is indicative of the patient attempting to stand; and

apply, based on the position-change pattern, a control signal to the intervention element to initiate a patient-facing interactive engagement performed locally by the intervention element that: (i) establishes a two-way exchange with the patient via audio and/or visual modalities, (ii) elicits and receives assistance-need information from the patient via spoken or non-verbal inputs, and (iii) provides, via the intervention element, an audible, visual, or tactile acknowledgment that assistance has been notified.

2 . The system of claim 1 , the memory further including instructions executable by the processor to:

generate, based on the temporally adjacent sensor observations, an alert signal for communication to an alert device associated with a supervising individual.

3 . The system of claim 2 , the alert device including one or more haptic display elements, one or more audio display elements, and/or one or more visual display elements.

4 . The system of claim 1 , the memory further including instructions executable by the processor to:

capture the assistance-need information received from the patient; and

communicate the assistance-need information to a supervising individual through an alert device.

5 . The system of claim 1 , the sensor array including one or more pressure sensors.

6 . The system of claim 5 , the memory further including instructions executable by the processor to:

apply the temporally adjacent sensor observations as input to a machine learning model, the machine learning model being trained to detect the position-change pattern based on pressure distribution measurable across the one or more pressure sensors.

7 . The system of claim 1 , the sensor array including one or more video capture devices.

8 . The system of claim 7 , the memory further including instructions executable by the processor to:

apply the temporally adjacent sensor observations as input to a machine learning model, the machine learning model being trained to detect the position-change pattern based on a pose of the patient as captured by the one or more video capture devices.

9 . The system of claim 1 , the intervention element including a robot.

10 . The system of claim 9 , the control signal being applied to the robot to cause the robot to move from a first location to a second location, the second location being associated with the patient.

11 . The system of claim 1 , the intervention element including a holographic projector, and the control signal being applied to the holographic projector to display a holographic image.

12 . The system of claim 1 , the intervention element including an audio output device and the control signal being applied to the audio output device to initiate playback of an audio message.

13 . The system of claim 1 , the intervention element including a light emitting device that alters a lighting condition of the space responsive to the control signal.

14 . The system of claim 1 , the intervention element including a motorized element positionable within the space responsive to the control signal.

15 . The system of claim 1 , the intervention element including an interactive display device that establishes communication between the patient and a communication device associated with a supervising individual based on the control signal.

16 . The system of claim 1 , wherein the patient-facing interactive engagement is executed at the intervention element by presenting a prompt via the intervention element, receiving patient inputs via the intervention element, and interpreting the patient inputs using at least one of: (i) natural-language processing applied to speech and/or text inputs; (ii) processing of non-verbal inputs provided via a user interface of the intervention element.

17 . A method, comprising:

accessing temporally adjacent sensor observations obtained from a sensor array in communication with a processor, the sensor array being positioned within a space designated for a patient;

determining, using time-dependent analysis of the temporally adjacent sensor observations, that a position-change pattern of the patient is indicative of the patient attempting to stand; and

applying, based on the position-change pattern, a control signal to an intervention element to initiate a patient-facing interactive engagement performed locally by the intervention element that: (i) establishes a two-way exchange with the patient via audio and/or visual modalities, (ii) elicits and receives assistance-need information from the patient via spoken or non-verbal inputs, and (iii) provides, via the intervention element, an audible, visual, or tactile acknowledgment that assistance has been notified.

18 . The method of claim 17 , further comprising:

generating, based on the temporally adjacent sensor observations, an alert signal for communication to an alert device associated with a supervising individual.

19 . The method of claim 17 , further comprising:

applying the temporally adjacent sensor observations as input to a machine learning model, the machine learning model being trained to detect the position-change pattern based on pressure distribution measurable across one or more pressure sensors of the sensor array.

20 . The method of claim 17 , further comprising:

applying the temporally adjacent sensor observations as input to a machine learning model, the machine learning model being trained to detect the position-change pattern based on a pose of the patient as captured by one or more video capture devices of the sensor array.

21 . The method of claim 17 , further comprising:

recording the assistance-need information received from the patient; and

communicating the assistance-need information to a supervising individual through an alert device.

22 . The method of claim 17 , further comprising executing the patient-facing interactive engagement at the intervention element by:

presenting a prompt via the intervention element,

receiving patient inputs via the intervention element, and

interpreting the patient inputs using at least one of: (i) natural-language processing applied to speech and/or text inputs; (ii) processing of non-verbal inputs provided via a user interface of the intervention element.