Measuring representational motions in a medical context
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.
1. A computer-implemented method comprising:
providing a first task to a subject in a medical context;
monitoring a performance of the first task by the subject using one or more sensors;
collecting first data corresponding to individual representational motions made by the subject during the performance of the first task;
analyzing the first data, using a machine learning algorithm trained with a set of training data including prior performances of the first task, to classify the individual representational motions and identify a plurality of elements of the individual representational motions; and
evaluating one or more medical characteristics of the subject based on the plurality of elements of the individual representational motions.
2. The computer-implemented method of claim 1 , wherein the first task includes a graphomotor diagnostic task.
3. The computer-implemented method of claim 2 , wherein the graphomotor diagnostic task includes a clock drawing test.
4. The computer-implemented method of claim 3 , wherein at least some of the plurality of elements correspond to one or more element types including one or more of hour labels, an hour hand, a minute hand, a second hand, a clock face outline, and a clock face center point.
5. The computer-implemented method of claim 1 , wherein the one or more sensors include motion sensors configured to capture one or more aspects of the individual representational motions made by the subject during the performance of the first task.
6. The computer-implemented method of claim 5 , wherein at least one of the one or more sensors is physically associated with the subject during at least a portion of the performance of the first task.
7. The computer-implemented method of claim 5 , wherein at least one of the one or more sensors is associated with a surface upon which the first task is performed.
8. The computer-implemented method of claim 5 , wherein the first data comprises data representing subject motion characteristics, the subject motion characteristics including one or more of a change of position relative to a reference point, a velocity of the change of position, an acceleration of the velocity of the change of position, a first duration of a first motion relative to a second duration of a second motion, a distance between an observed initial position and an expected initial position, and a distance between an observed ending position and an expected ending position.
9. The computer-implemented method of claim 1 , wherein the one or more medical characteristics include at least one of motor skills or cognitive skills.
10. The computer-implemented method of claim 1 , wherein evaluating one or more medical characteristics of the subject includes providing a second task to the subject and comparing the performance of the first task with a performance of the second task.
11. A non-transitory computer-readable medium storing instructions that, when executed by one or more computing devices, cause the one or more computing devices to perform a method for assessing a subject by processing individual representational motions, the method comprising:
providing a first task to a subject in a medical context;
monitoring a performance of the first task by the subject using one or more sensors;
collecting first data corresponding to individual representational motions made by the subject during the performance of the first task;
analyzing the first data, using a machine learning algorithm trained with a set of training data including prior performances of the first task, to classify the individual representational motions and identify a plurality of elements of the individual representational motions; and
evaluating one or more medical characteristics of the subject based on the plurality of elements of the individual representational motions.
12. The non-transitory computer-readable medium of claim 11 , wherein the first task includes a graphomotor diagnostic task.
13. The non-transitory computer-readable medium of claim 12 , wherein the graphomotor diagnostic task includes a clock drawing test.
14. The non-transitory computer-readable medium of claim 13 , wherein at least some of the plurality of elements correspond to one or more element types including one or more of hour labels, an hour hand, a minute hand, a second hand, a clock face outline, and a clock face center point.
15. The non-transitory computer-readable medium of claim 11 , wherein the one or more sensors include motion sensors configured to capture one or more aspects of the individual representational motions made by the subject during the performance of the first task, and wherein at least one of the one or more sensors is physically associated with the subject during at least a portion of the performance of the first task.
16. The non-transitory computer-readable medium of claim 15 , wherein at least one of the one or more sensors is associated with a surface upon which the first task is performed.
17. The non-transitory computer-readable medium of claim 15 , wherein the first data comprises data representing subject motion characteristics, the subject motion characteristics including one or more of a change of position relative to a reference point, a velocity of the change of position, an acceleration of the velocity of the change of position, a first duration of a first motion relative to a second duration of a second motion, a distance between an observed initial position and an expected initial position, and a distance between an observed ending position and an expected ending position.
18. The non-transitory computer-readable medium of claim 11 , wherein evaluating one or more medical characteristics of the subject includes providing a second task to the subject and comparing the performance of the first task with a performance of the second task.
19. A system for assessing a subject by processing individual representational motions, the system including:
a data storage device that stores instructions for assessing a subject by processing individual representational motions; and
a processor configured to execute the instructions to perform a method including:
providing a graphomotor diagnostic task to a subject in a medical context;
monitoring a performance of the graphomotor diagnostic task by the subject using one or more sensors;
collecting first data corresponding to individual representational motions made by the subject during the performance of the graphomotor diagnostic task;
analyzing the first data, using a machine learning algorithm trained with a set of training data including prior performances of the graphomotor diagnostic task, to classify the individual representational motions and identify a plurality of elements of the individual representational motions; and
evaluating one or more medical characteristics of the subject based on the plurality of elements of the individual representational motions.
20. The system of claim 19 , wherein the one or more sensors include motion sensors configured to capture one or more aspects of the individual representational motions made by the subject during the performance of the graphomotor diagnostic task, and wherein:
at least one of the one or more sensors is configured to be physically associated with the subject during at least a portion of the performance of the graphomotor diagnostic task; and
at least one of the one or more sensors is associated with a surface upon which the graphomotor diagnostic task is performed.