Systems for dynamic assessment of upper extremity impairments in virtual/augmented reality

1 . A method comprising:

providing a virtual environment to a user via an extended reality system comprising a head-mounted display and a plurality of body-worn motion sensors worn by the user;

receiving a target path;

presenting a sensory stimulus to the user within the virtual environment, the sensory stimulus instructing the user to follow the target path by moving one or more body parts of the user;

determining three-dimensional position information for the one or more body parts, the three-dimensional position information defining a recorded path;

wherein the determining the three-dimensional position information comprises fusing inertial measurement unit (IMU) data from the plurality of body-worn motion sensors with optical tracking data from the head-mounted display using a hardware-implemented sensor fusion algorithm to improve a spatial accuracy metric and a robustness metric of the recorded path;

determining a plurality of motion parameters corresponding to a user response to the sensory stimulus, wherein determining the plurality of motion parameters comprises:

comparing the recorded path to the target path;

determining a smoothness metric of the recorded path by:

determining a signal-to-noise ratio of the recorded path, and

applying a filter to the recorded path;

determining starting coordinates and ending coordinates of the recorded path;

determining a first time period from presentation of the sensory stimulus to when motion of the one or more body parts begins; and

determining a second time period for motion between the starting coordinates and the ending coordinates; and

determining at least one index indicative of upper extremity impairment from the plurality of motion parameters.

2 . The method of claim 1 , wherein the plurality of motion parameters comprises range of motion, quality of movement, response time, peak velocity, efficiency, fatigue, and/or tremor.

3 . The method of claim 1 , wherein determining the at least one index comprises providing the plurality of motion parameters to a learning system.

4 . The method of claim 3 , wherein the learning system is a trained classifier.

5 . The method of claim 3 , wherein the learning system is a trained artificial neural network.

6 . The method of claim 1 , wherein comparing the recorded path to the target path comprises determining similarity between the recorded path and the target path.

7 . The method of claim 1 , wherein determining the smoothness metric comprises determining an amplitude of noise in the recorded path.

8 . The method of claim 1 , wherein the determining the three-dimensional position information comprises mapping one or more joints of the user.

9 . The method of claim 8 , wherein the one or more joints comprise a shoulder or elbow, the method further comprising determining a change in kinematics of the one or more joints.

10 . The method of claim 1 , further comprising determining a ratio between a first length of a path of a hand from the recorded path and a second length associated with the target path.

11 . The method of claim 1 , wherein a velocity is determined based on the second time period, the starting coordinates, and the ending coordinates.

12 . The method of claim 1 , wherein the target path is received from a remote server.

13 . The method of claim 12 , wherein the remote server comprises an electronic medical record.

14 . A system comprising:

an extended reality system, adapted to display a virtual environment to a user, comprising:

a head-mounted display, and

a plurality of body-worn motion sensors worn by the user;

a computing node comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor of the computing node to cause the processor to perform a method comprising:

providing the virtual environment to the user via the extended reality system;

receiving a target path;

presenting a sensory stimulus to the user within the virtual environment, the sensory stimulus instructing the user to follow the target path by moving one or more body parts of the user;

determining, from the plurality of body-worn motion sensors, three-dimensional position information for the one or more body parts, the three-dimensional position information defining a recorded path;

wherein determining the three-dimensional position information comprises fusing inertial measurement unit (IMU) data from the plurality of body-worn motion sensors with optical tracking data from the head-mounted display using a hardware-implemented sensor fusion algorithm to improve a spatial accuracy metric and a robustness metric of the recorded path;

determining a plurality of motion parameters corresponding to a user response to the sensory stimulus from the plurality of body-worn motion sensors, wherein determining the plurality of motion parameters comprises:

comparing the recorded path to the target path;

determining a smoothness metric of the recorded path by:

determining a signal-to-noise ratio of the recorded path, and

applying a filter to the recorded path;

determining starting coordinates and ending coordinates of the recorded path;

determining a first time period from presentation of the sensory stimulus to when motion of the one or more body parts begins; and

determining a second time period for motion between the starting coordinates and the ending coordinates; and

determining at least one index indicative of upper extremity impairment from the plurality of motion parameters.

15 . A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform a method comprising:

providing a virtual environment to a user via an extended reality system comprising a head-mounted display and a plurality of body-worn motion sensors worn by the user;

receiving a target path;

presenting a sensory stimulus to the user within the virtual environment, the sensory stimulus instructing the user to follow the target path by moving one or more body parts of the user;

determining three-dimensional position information for the one or more body parts, the three-dimensional position information defining a recorded path;

wherein determining the three-dimensional position information comprises fusing inertial measurement unit (IMU) data from the plurality of body-worn motion sensors with optical tracking data from the head-mounted display using a hardware-implemented sensor fusion algorithm to improve a spatial accuracy metric and a robustness metric of the recorded path;

determining a plurality of motion parameters corresponding to a user response to the sensory stimulus, wherein determining the plurality of motion parameters comprises:

comparing the recorded path to the target path;

determining a smoothness metric of the recorded path by:

determining a signal-to-noise ratio of the recorded path, and

applying a filter to the recorded path;

determining starting coordinates and ending coordinates of the recorded path;

determining a first time period from presentation of the sensory stimulus to when motion of the one or more body parts begins; and

determining a second time period for motion between the starting coordinates and the ending coordinates; and

determining at least one index indicative of upper extremity impairment from the plurality of motion parameters.