Measuring representational motions in a medical context

• US 9,895,085 B2
• Filed: 06/18/2013
• Issued: 02/20/2018
• Est. Priority Date: 03/21/2007
• Status: Active Grant

• Current Assignee: Lahey Clinic Foundation Incorporated, Massachusetts Institute of Technology
• Original Assignee: Lahey Clinic Foundation Incorporated, Massachusetts Institute of Technology
• Inventors: Davis, Randall, Penney, Dana L.
• Primary Examiner(s): EISEMAN, ADAM JARED
• Application Number:
  US13/920,270
• Publication Number:
  US 20140031724A1
• Time in Patent Office: 1,708 Days
• CPC Class Codes: A61B 5/002 Monitoring the patient using a local or closed circuit, e.g. in a room or building A61B5/0017 takes precedence
• CPC Class Codes: A61B 5/1124 Determining motor skills
• CPC Class Codes: A61B 5/16 Devices for psychotechnics using teaching or educational appliances G09B1/00 - G09B7/00; Testing reaction times ; Devices for evaluating the psychological state
• CPC Class Codes: A61B 5/165 Evaluating the state of mind, e.g. depression, anxiety
• CPC Class Codes: A61B 5/4088 Diagnosing of monitoring cognitive diseases, e.g. Alzheimer, prion diseases or dementia
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: A61B 5/7475 User input or interface means, e.g. keyboard, pointing device, joystick
• CPC Class Codes: G06Q 10/101 Collaborative creation, e.g. joint development of products or services
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: G16H 15/00 ICT specially adapted for medical reports, e.g. generation or transmission thereof
• CPC Class Codes: G16H 40/63 for local operation
• CPC Class Codes: G16H 50/00 ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

A method includes receiving data representing graphomotor motion during a succession of executions of graphomotor diagnostic tasks performed in a medical context by a subject, processing the received data using a computer, including determining a first set of quantitative features from a first execution of a task by the subject, and determining a second set of quantitative features from a second execution of a task by the subject, determining one or more metrics based on a comparison to the successive executions, including using at least the first set of quantitative features and the second set of quantitative features to determine said metrics, and providing a diagnostic report associated with neurocognitive mechanisms underlying the subject'"'"'s execution of the tasks based on the determined metrics.

Claims

1. A computer implemented method comprising:

receiving data representing graphomotor motion during a succession of executions of graphomotor diagnostic tasks performed in a medical context by a subject, the graphomotor diagnostic tasks comprising maze-following tasks;

processing the received data using a computer, including determining a first set of quantitative features from a first execution of a task by the subject, and determining a second set of quantitative features from a second execution of a task by the subject;

determining one or more metrics based on a comparison to the successive executions, including using at least the first set of quantitative features and the second set of quantitative features to determine said metrics; and

providing a diagnostic report associated with neurocognitive mechanisms underlying the subject'"'"'s execution of the tasks based on the determined metrics,

wherein the maze-following tasks comprise a first maze following task corresponding to the first set of quantitative features, and a second maze-following task corresponding to the second set of quantitative features, and

the second maze-following task is executed after the first maze-following task, and wherein the first and second maze following tasks share a common solution, and wherein the second maze following task has a greater number of decision points in the solution than the first maze following task.

2. The method of claim 1 wherein the first set of quantitative features includes an execution time for the first task and the second set of quantitative features includes an execution time for the second task, and wherein the one or more metrics includes a comparison of said execution times.

3. The method of claim 1 wherein processing the received data using a computer includes determining a first set of qualitative features from the first execution of the task by the subject, and determining a second set of qualitative features from the second execution of the task by the subject;

and determining the one or more metrics based on the comparison to the successive executions, includes using at least the first set of qualitative features and the second set of qualitative features to determine said metrics.

4. The method of claim 1 wherein the first set of quantitative features includes a rate of occurrence of graphomotor motion elements during the first execution of the task and the second set of quantitative features includes a rate of occurrence of graphomotor motion elements during the second execution of the task.

5. The method of claim 4 wherein the graphomotor motion elements include hooklets.

6. The method of claim 1 wherein at least some of the executions of graphomotor diagnostic tasks are performed by the subject using a stylus.

7. The method of claim 1 wherein at least some of the executions of graphomotor diagnostic tasks are performed by the subject using the subject'"'"'s finger.

8. The method of claim 1 wherein the common solution shared by the first and second maze following tasks comprises a path traversing mazes associated with the first and second maze following tasks.

9. The method of claim 8 wherein the path extends from a maze entrance point common to the first and second maze following tasks to a maze exit point common to the first and second maze following tasks.

10. The method of claim 1 further comprising presenting the first maze following task and the second maze following task to the subject.

11. A computer implemented method comprising:

receiving data representing graphomotor motion during a succession of executions of graphomotor diagnostic tasks performed in a medical context by a subject, the graphomotor diagnostic tasks comprise maze-following tasks;

processing the received data using a computer, including determining a first set of quantitative features from a first execution of a task by the subject, and determining a second set of quantitative features from a second execution of a task by the subject;

determining one or more metrics based on a comparison to the successive executions, including using at least the first set of quantitative features and the second set of quantitative features to determine said metrics; and

providing a diagnostic report associated with neurocognitive mechanisms underlying the subject'"'"'s execution of the tasks based on the determined metrics,

wherein the maze-following tasks comprise a first maze following task corresponding to the first set of quantitative features, and a second maze-following task corresponding to the second set of quantitative features and the second maze-following task includes one or more decision points and the second set of quantitative features includes a characterization of a decision making time at the one or more decision points, a characterization of incorrect decisions made at the one or more decision points, and/or a characterization of over-corrections made in response to incorrect decisions made at the one or more decision points.

12. The method of claim 11 wherein each decision point of the one or more decision points is associated with a local characterization of a decision making time at the decision point, a local characterization of incorrect decisions made at the decision point, and/or a local characterization of over-corrections made in response to incorrect decisions made at the decision point.

13. A computer implemented method comprising:

receiving data representing graphomotor motion during an execution of a graphomotor diagnostic task performed in a medical context by a subject, the graphomotor diagnostic task including one or more decision points;

processing the received data using a computer, including determining a first set of quantitative features from the execution of the task by the subject, the first set of quantitative features characterizing the motion in a vicinity of the one or more decision points;

processing prior data characterizing motion during one or more prior executions of the diagnostic task to determine a second set of quantitative features from the one or more prior executions of the task, the second set of quantitative features characterizing the motion of the one or more prior executions of the diagnostic task in a vicinity of the one or more decision points;

determining one or more metrics based on a comparison to the prior executions, including using at least the first set of quantitative features and the second set of quantitative features to determine said metrics; and

providing a diagnostic report associated with neurocognitive mechanisms underlying the subject'"'"'s execution of the tasks based on the determined metrics

wherein the first set of quantitative features includes a decision making time in the vicinity of each of the one or more decision points during the execution of the task and the second set of quantitative features includes a representation of a decision making time in the vicinity of each of the one or more decision points during the one or more prior executions of the task.

14. The method of claim 13 the first set of quantitative features includes an overall execution time for the task and the second set of quantitative features includes a representation of overall execution times for the one or more prior executions of the task.

15. The method of claim 13 wherein

the first set of quantitative features includes a characterization of incorrect decisions made in the vicinity of the one or more decision points during the execution of the task and/or a characterization of over-corrections made in response to incorrect decisions made in the vicinity of the one or more decision points during the execution of the task;

and

the second set of quantitative features includes a characterization of incorrect decisions made in the vicinity of the one or more decision points during the one or more prior executions of the task and/or a characterization of over-corrections made in response to incorrect decisions made in the vicinity of the one or more decision points during the one or more prior executions of the task.

16. The method of claim 13 wherein at least some of the decision points are embedded decision points.

17. The method of claim 13 wherein the graphomotor diagnostic task includes a maze-following task and the one or more decision points include branch points in the maze drawing task.

18. The method of claim 17 wherein at least some of the one or more decision points include a different number of branch points than at least some other decision points of the one or more decision points.

19. The method of claim 17 wherein for each of at least some of the decision points, at least one of the branch points associated with the decision point leads to another, adjacent decision point and at least one of the branch points leads to a dead end in the maze and a distance from the decision point to the adjacent decision point is equal to a distance from the decision point to a dead end associated with the decision point.

20. The method of claim 13 wherein the first set of quantitative features includes a rate of occurrence of graphomotor motion elements during the execution of the task and the second set of quantitative features includes a rate of occurrence of graphomotor motion elements during the one or more prior executions of the task.

21. The method of claim 20 wherein the graphomotor motion elements include hooklets.

22. The method of claim 13 wherein at least some of the executions of graphomotor diagnostic tasks are performed by the subject using a stylus.

23. The method of claim 13 wherein at least some of the executions of graphomotor diagnostic tasks are performed by the subject using the subject'"'"'s finger.

24. The method of claim 13 wherein the one or more decision points include a first decision point having a first path extending therefrom and a second path extending therefrom, the first path leading to a first dead end and the second path leading to a second dead end, wherein a length of the first path is substantially equal to a length of the second path.

25. The method of claim 13 wherein the one or more decision points include a first decision point having a first path extending therefrom and a second path extending therefrom, the first path leading to a second decision point and the second path leading to a dead end, wherein a length of the first path is substantially equal to a length of the second path.

26. The method of claim 13 wherein the one or more decision points include a first decision point having a first path extending therefrom and a second path extending therefrom, the first path leading to a first second decision point and the second path leading to a third decision point, wherein a length of the first path is substantially equal to a length of the second path.

27. The method of claim 13 wherein the one or more decision points include a first decision point having a first degree and a second decision point having a second degree, greater than the first degree, wherein a first path extends from the first decision point to the second decision point.

28. The method of claim 27 wherein the one or more decision points include a third decision point having a third degree, greater than the first degree and the second degree, wherein a second path extends from the second decision point to the third decision point.

29. The method of claim 27 wherein a second path extends from the first decision point to a first dead end and all paths extending from the second decision point extend from the second decision point to corresponding dead ends.