Systems for automatic assessment of fall risk

• US 10,206,630 B2
• Filed: 08/26/2016
• Issued: 02/19/2019
• Est. Priority Date: 08/28/2015
• Status: Active Grant

• Current Assignee: Foresite Healthcare, LLC
• Original Assignee: Foresite Healthcare, LLC
• Inventors: Stone, Erik E., Viragh, Donald A., Chronis, George
• Primary Examiner(s): La, Anh V
• Application Number:
  US15/248,810
• Publication Number:
  US 20170055917A1
• Time in Patent Office: 907 Days
• Field of Search: 3405731, 3405734, 3405737, 340540, 600300, 600301
• CPC Class Codes: A61B 2562/0247 Pressure sensors
• CPC Class Codes: A61B 5/1115 Monitoring leaving of a patient support, e.g. a bed or a wheelchair
• CPC Class Codes: A61B 5/1116 Determining posture transitions
• CPC Class Codes: A61B 5/112 Gait analysis
• CPC Class Codes: A61B 5/1128 using image analysis A61B5/1127 takes precedence
• CPC Class Codes: A61B 5/7275 Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
• CPC Class Codes: A61B 5/746 Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms alarms per se G08B
• CPC Class Codes: G16H 40/67 for remote operation
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/30 for calculating health indices; for individual health risk assessment

Abstract

Systems and methods for the automatic assessment of a person'"'"'s fall risk. The systems and methods utilize an objective standard and evaluation of a person'"'"'s gait and stance, among other factors, to determine such person'"'"'s current instantaneous likelihood of a fall, as well as such person'"'"'s future fall risk. The systems and methods utilize machine observations and calculations to reduce or eliminate bias and the use of subjective assessment criteria.

Claims

1. A method of assessing the risk of a human being falling, comprising:

providing a central sever system;

providing a plurality of sensors communicatively coupled to said central server system, none of said sensors being in physical contact with said human being at least one sensor in said plurality of sensors detecting that said human being attempting to exit a bed in which said human being is resting;

receiving at said central server system from said plurality of sensors data about said detected attempt of said human being to exit said bed;

said central server system extracting from said received data about said human being a plurality of data features including an indication of the human being'"'"'s bed exit procedure and the human being'"'"'s sit-to-stand time during said bed exit procedure;

said central server system determining a fall risk for said human being based at least in part on said extracted data features.

2. The method of claim 1, wherein each sensor in said plurality of sensors is selected from the group consisting of:

a depth sensor, a bed sensor, and a pressure map sensor.

3. The method of claim 2, wherein at least one sensor in said plurality of sensors is a depth sensor, and said depth sensor is an infrared camera.

4. The method of claim 1, further comprising:

providing an electronic medical records database communicatively coupled to said central computer server;

said central server system identifying in said electronic medical records database an electronic medical record for said human being, said identifying based at least in part on said extracted data features;

in said determining step, said central server system determining said fall risk for said human being further based at least in part on medical information about said human being in said identified electronic medical record.

5. The method of claim 1, further comprising:

said central server system causing to be stored a non-transitory computer-readable medium a data record of said plurality extracted features and said determined fall risk.

6. The method of claim 5, further comprising:

receiving at said central server system from said plurality of sensors additional data about said human being gathered by said plurality of sensors;

said central server system extracting from said received additional data about said human being a second plurality of data features;

said central server system determining a second fall risk for said human being based at least in part on said second extracted data features, and at least in part on said extracted data features in said data record of said non-transitory computer-readable medium.

7. The method of claim 1, further comprising:

providing a monitoring computer system communicatively coupled to said central computer server;

said central computer server transmitting to said monitoring computer system an indication of said determined fall risk;

said monitoring computer system displaying said transmitted indication of said determined fall risk.

8. The method of claim 7, wherein said monitoring computer system is a desktop computer system of a nurse station in a medical facility.

9. The method of claim 7, wherein said monitoring computer is a mobile device.

10. The method of claim 1, further comprising:

if said determined fall risk is above a predefined threshold, said central computer server causing a fall risk alert to be provided to said human being.

11. A system for assessing the risk of a human being falling, comprising:

a plurality of sensors, none of said sensors being in physical contact with said human being;

a central sever system communicatively coupled to said plurality of sensors, said central server system comprising a microprocessor and a non-transitory computer-readable medium having computer-executable program instructions thereon which, when executed by said microprocessor, cause said central server to perform the steps of;

receiving from said plurality of sensors data about said human being gathered by said plurality of sensors at least one sensor in said plurality of sensors detecting that said human being attempting to exit a bed in which said human being is resting and said data including data about said detected attempt of said human being to exit said bed;

extracting from said received data about said human being a plurality of data features including an indication of the human being'"'"'s bed exit procedure and the human being'"'"'s sit-to-stand time during said bed exit procedure;

determining a fall risk for said human being based at least in part on said extracted data features.

12. The system of claim 11, wherein each sensor in said plurality of sensors is selected from the group consisting of:

a depth sensor, a bed sensor, and a pressure map sensor.

13. The system of claim 12, wherein at least one sensor in said plurality of sensors is a depth sensor, and said depth sensor is an infrared camera.

14. The system of claim 11, further comprising:

an electronic medical records database communicatively coupled to said central computer server;

wherein said computer-executable program instructions, when executed by said microprocessor, further cause said central server to perform the step of identifying in said electronic medical records database an electronic medical record for said human being, said identifying based at least in part on said extracted data features;

wherein in said determining step, said central server system determining said fall risk for said human being further based at least in part on medical information about said human being in said identified electronic medical record.

15. The system of claim 11, wherein said computer-executable program instructions, when executed by said microprocessor, further cause said central server to perform the steps of:

storing on said non-transitory computer-readable medium a data record of said plurality extracted features and said determined fall risk;

receiving at said central server system from said plurality of sensors additional data about said human being gathered by said plurality of sensors;

extracting from said received additional data about said human being a second plurality of data features;

determining a second fall risk for said human being based at least in part on said second extracted data features, and at least in part on said extracted data features in said data record of said non-transitory computer-readable medium.

16. The system of claim 11, further comprising

a monitoring computer system communicatively coupled to said central computer server;

wherein said computer-executable program instructions, when executed by said microprocessor, further cause said central server to perform the steps of transmitting to said monitoring computer system an indication of said determined fall risk.