Data collection and analysis for self-administered cognitive tests characterizing fine motor functions

• US 10,383,553 B1
• Filed: 10/14/2015
• Issued: 08/20/2019
• Est. Priority Date: 10/14/2014
• Status: Active Grant

• Current Assignee: The Cognitive Healthcare Company
• Original Assignee: The Cognitive Healthcare Company
• Inventors: Glenn, Shenly, Mefford, Joel
• Primary Examiner(s): Gebremichael, Bruk A
• Application Number:
  US14/883,450
• Time in Patent Office: 1,406 Days
• Field of Search: None
• 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: G09B 5/02 with visual presentation of the material to be studied, e.g. using film strip
• CPC Class Codes: G16H 10/20 for electronic clinical trials or questionnaires
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

The present invention is a system and method to collect and analyze data produced through biometric and psychometric tasks on interactive computing devices. The collected biometric data can be used to quantify motor skills and to generate statistics that correlate with or predict ability in other functional domains. The biometric data tasks and data collection can be incidental to user interaction with a computing device using a touchpad or other input device—such as users drawing lines to connecting screen elements while using the user interface of an application on a computing device.

Claims

1. A computer-implemented method for conducting self-administered tests, comprising:

configuring a touch-sensitive surface of a client device configured to present a computer-mediated, self-administered test to a user and starting the computer-mediated, self-administrated test;

receiving during the test, user inputs on the touch-sensitive surface of a client device and collecting motion data in response to the received user inputs;

generating a trace in response to the received user inputs based on the collected motion data;

determining a set of anchor points of the trace and constructing one or more reference paths for the trace based on the set of anchor points, a reference path connecting one or more anchor points of the determined set of anchor points; and

determining a set of diagnostic features of the trace by comparing the trace to the one or more constructed reference paths, wherein the determining the set of diagnostic features comprises determining a local curvature at the point of the trace, and wherein the determining the set of anchor points comprises comparing the local curvature at the point of the trace to a threshold and determining the point of the trace as an anchor point responsive to determining the local curvature greater than the threshold.

2. The computer-implemented method of claim 1, wherein the computer-mediated, self-administered test is configured to include objects for the user to connect, further comprising identifying one or more targets corresponding to the objects, wherein the set of anchor points comprises centers of the one or more targets.

3. The computer-implemented method of claim 1, wherein the constructing the one or more reference paths comprises constructing a linear path comprising a set of linear line segments connecting one or more anchor points.

4. The computer-implemented method of claim 3, wherein the determining the set of diagnostic features further comprises determining at least one of a difference between a length of the trace and a linear line segment between two anchor points and a sum of squared perpendicular distances from the trace to the linear line segment between the two anchor points.

5. The computer-implemented method of claim 1, wherein the constructing the one or more reference paths comprises constructing a smoothed path comprising a set of splines connecting one or more anchor points.

6. The computer-implemented method of claim 5, wherein the determining the set of diagnostic features further comprises at least determining one of a difference between a length of the trace and a spline between two anchor points and a sum of squared residuals from the spline to the trace.

7. The computer-implemented method of claim 5, wherein the set of splines comprises a cubic spline with a knot and wherein the constructing the reference path comprises constraining the cubic spline and the knot to connect the two anchor points and adjusts the cubic spline and the knot to reduce the sum of squared residuals less than a threshold value.

8. The computer-implemented method of claim 1, wherein the trace includes a first trace segment and a second trace segment, the first trace segment connecting a first anchor point and a second anchor point and the second trace segment connecting the second anchor point and a third anchor point, wherein the determining the set of diagnostic features further comprises determining at least one of a first angle between a first line segment connecting the first and second anchor points and a second line segment connecting the second and third anchor points and a second angle between a third line segment fit to 20 percent of the first trace segment most proximal to the second anchor point and a fourth line segment fit to 20 percent of the second trace segment most proximal to the second anchor point.

9. The computer-implemented method of claim 1, wherein the determining the set of diagnostic features further comprises determining at least one of a local speed at a point of the trace, an average speed of the user, a standard deviation of the local speed at the point of the trace, a maximum speed of the user, a local curvature at the point of the trace, an average curvature of the trace, and a standard deviation of the local curvature.

10. A non-transitory computer-readable storage medium storing executable computer instructions for self-administered tests that, when executed by a hardware processor, perform steps comprising:

configuring a touch-sensitive surface of a client device configured to present a computer-mediated, self-administered test to a user and starting the computer-mediated, self-administrated test;

receiving during the test, user inputs on the touch-sensitive surface of a client device and collecting motion data in response to the received user inputs;

generating a trace in response to the received user inputs based on the collected motion data;

determining a set of anchor points of the trace and constructing one or more reference paths for the trace based on the set of anchor points, a reference path connecting one or more anchor points of the determined set of anchor points; and

determining a set of diagnostic features of the trace by comparing the trace to the one or more constructed reference paths, wherein the determining the set of diagnostic features comprises determining a local curvature at the point of the trace, and wherein the determining the set of anchor points comprises comparing the local curvature at the point of the trace to a threshold and determining the point of the trace as an anchor point responsive to determining the local curvature greater than the threshold.

11. The non-transitory computer-readable storage medium of claim 10, wherein the computer-mediated, self-administered test is configured to include objects for the user to connect, further comprising instructions configured to cause the processor to perform identifying one or more targets corresponding to the objects, wherein the set of anchor points comprises centers of the one or more targets.

12. The non-transitory computer-readable storage medium of claim 10, wherein the constructing the one or more reference paths comprises constructing a linear path comprising a set of linear line segments connecting one or more anchor points.

13. The non-transitory computer-readable storage medium of claim 12, wherein the determining the set of diagnostic features further comprises determining at least one of a difference between a length of the trace and a linear line segment between two anchor points and a sum of squared perpendicular distances from the trace to the linear line segment between the two anchor points.

14. The non-transitory computer-readable storage medium of claim 10, wherein the constructing the one or more reference paths comprises constructing a smoothed path comprising a set of splines connecting one or more anchor points.

15. The non-transitory computer-readable storage medium of claim 14, wherein the determining the set of diagnostic features further comprises at least determining one of a difference between a length of the trace and a spline between two anchor points and a sum of squared residuals from the spline to the trace.

16. The non-transitory computer-readable storage medium of claim 14, wherein the set of splines comprises a cubic spline with a knot and wherein the constructing the reference path comprises constraining the cubic spline and the knot to connect the two anchor points and adjusts the cubic spline and the knot to reduce the sum of squared residuals less than a threshold value.

17. The non-transitory computer-readable storage medium of claim 10, wherein the trace includes a first trace segment and a second trace segment, the first trace segment connecting a first anchor point and a second anchor point and the second trace segment connecting the second anchor point and a third anchor point, wherein the determining the set of diagnostic features further comprises determining at least one of a first angle between a first line segment connecting the first and second anchor points and a second line segment connecting the second and third anchor points and a second angle between a third line segment fit to 20 percent of the first trace segment most proximal to the second anchor point and a fourth line segment fit to 20 percent of the second trace segment most proximal to the second anchor point.

18. The non-transitory computer-readable storage medium of claim 10, wherein the determining the set of diagnostic features further comprises determining at least one of a local speed at a point of the trace, an average speed of the user, a standard deviation of the local speed at the point of the trace, a maximum speed of the user, a local curvature at the point of the trace, an average curvature of the trace, and a standard deviation of the local curvature.