Method of determining joint stress from sensor data

• US 10,121,066 B1
• Filed: 11/16/2017
• Issued: 11/06/2018
• Est. Priority Date: 11/16/2017
• Status: Active Grant

• Current Assignee: Newlight Capital, LLC
• Original Assignee: Blast Motion Incorporated
• Inventors: Cherveny, Patrick, Thornbrue, James R., Bose, Bhaskar
• Primary Examiner(s): Chu, Randolph I
• Application Number:
  US15/815,571
• Time in Patent Office: 355 Days
• Field of Search: None
• CPC Class Codes: A61B 2503/10 Athletes
• CPC Class Codes: A61B 2562/0219 Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
• CPC Class Codes: A61B 2562/04 Arrangements of multiple sensors of the same type
• 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 5/4528 Joints A61B5/4533, A61B5/4538 take precedence
• CPC Class Codes: A61B 5/458 Evaluating the elbow
• CPC Class Codes: A61B 5/4585 Evaluating the knee
• CPC Class Codes: A63B 2024/0009 Computerised real time comparison with previous movements or motion sequences of the user
• CPC Class Codes: A63B 2069/0006 for pitching
• CPC Class Codes: A63B 69/0002 for baseball
• CPC Class Codes: G06V 40/23 Recognition of whole body movements, e.g. for sport training
• CPC Class Codes: G06V 40/28 Recognition of hand or arm movements, e.g. recognition of deaf sign language static hand signs G06V40/113

Abstract

A method of calculating the stress on a joint by determining when a joint angle is outside the normal range of motion for the joint. Applications include analysis of elbow joint stress for baseball pitchers, for example to mitigate the risk of injury to the ulnar collateral ligament (UCL). During a movement such as a baseball pitch, sensor data is collected to track the position, orientation, or motion of body segments; joint angles are derived from this sensor data. Joint angles are then compared to a range of motion, which may be measured for each individual. Joint stress contributions from movements that exceed the range of motion may be combined over time to calculate cumulative joint fatigue. This joint fatigue measure may for example be used for pitchers to quantify recovery periods (days off) and future workloads (such as maximum pitch counts).

Claims

1. A method of determining joint stress from sensor data comprising:

obtaining a time series of sensor measurements from one or more sensors comprising

a first inertial sensor coupled to a first body part; and

,

a second inertial sensor coupled to a second body part;

measuring

one or more of position, orientation, or motion of said first body part of a subject using said first inertial sensor, and

one or more of position, orientation, or motion of said second body part of said subject using said second inertial sensor;

wherein

said first body part and said second body part are coupled to a body joint of said subject; and

,

said first body part and said second body part lie on opposite sides of said body joint;

processing said time series of sensor measurements to generate one or more joint angle time series for said body joint, wherein

each joint angle time series corresponds to a joint angle of said body joint; and

,

each said joint angle of said body joint corresponds to a rotational degree of freedom of said body joint;

obtaining one or more ranges of motion for said body joint, wherein

each range of motion of said one or more ranges of motion corresponds to said joint angle of said body joint; and

,

said each range of motion of said one or more ranges of motion comprises an interval of joint angles that are within said range of motion;

determining one or more passive range time intervals when said one or more joint angle time series has a joint angle value that is outside a corresponding range of motion associated with said joint angle corresponding to a time period when said body joint is in a passive range of motion;

calculating a joint stress contribution using a computer during said one or more passive range of motion time intervals that are outside of an active range of motion;

combining said joint stress contribution across a plurality of movements by said subject during a period of time to calculate a joint fatigue;

calculating a recovery time for said subject from said joint fatigue

or

calculating a workload limit for said subject during a future time period from said joint fatigue;

publishing or transmitting or displaying, or any combination thereof, using a computer, said recovery time or workload limit or both said recovery time and said workload limit.

2. The method of claim 1, wherein said calculating said joint stress contribution during said one or more time intervals comprises:

calculating an amount of time within said one or more time intervals.

3. The method of claim 1, wherein said calculating said joint stress contribution during said one or more time intervals comprises:

integrating or summing one or more functions of said joint angle value across said one or more time intervals.

4. The method of claim 3, wherein said one or more functions of said joint angle comprise one or more estimates of a passive joint torque as a function of said joint angle value.

5. The method of claim 1, wherein

said subject is a pitcher;

said body joint is an elbow of said pitcher; and

,

said plurality of movements comprise pitches by said pitcher.

6. The method of claim 1, further comprising:

obtaining or calculating

an initial orientation of said first body part relative to a reference frame; and

,

an initial orientation of said second body part relative to said reference frame.

7. The method of claim 6, wherein said processing said time series of sensor measurements to generate said one or more joint angle time series for said body joint comprises:

integrating said time series of sensor measurements using said initial orientation of said first body part and said initial orientation of said second body part as initial conditions, to generate

a time series of orientation of said first body part relative to said reference frame, and

a time series of orientation of said second body part relative to said reference frame;

calculating a time series of relative orientation of said second body part relative to said first body part from said time series of orientation of said first body part relative to said reference frame and said time series of orientation of said second body part relative to said reference frame;

calculating said one or more joint angle time series for said body joint from said time series of relative orientation of said second body part relative to said first body part.

8. The method of claim 1, wherein said one or more sensors further comprise

at least one video camera configured to capture a plurality of frames, each frame of said plurality of frames containing an image of one or both of said first body part and said second body part.

9. The method of claim 8, further comprising:

coupling a first visual marker to said first body part; and

,

coupling a second visual marker to said second body part;

wherein said plurality of frames contains one or more images of one or both of said first visual marker and said second visual marker.

10. The method of claim 8, further comprising:

using a sensor fusion algorithm to combine a time series of position and orientation information calculated from said plurality of frames with motion data from said first inertial sensor and said second inertial sensor, to generate a combined estimate of said one or more joint angle time series.