IP Library › Granted Patent US 10,226,629
Granted Patent B2
US 10,226,629 · App. 14/744,053 · Granted Mar 12, 2019

Analyzer for behavioral analysis and parameterization of neural stimulation

Inventors: Guillermo A. Cecchi (New York, NY); James R. Kozloski (New Fairfield, CT); Clifford A. Pickover (Yorktown Heights, NY); Irina Rish (Rye Brook, NY)
Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
A61N1/36139A61N1/36067A61N1/36071A61N1/36082A61N1/37282
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,226,629
App. No.
14/744,053
Granted
Mar 12, 2019
Kind
B2
Abstract

Embodiments are directed to a computer implemented neural stimulation system having a first module configured to derive neural data from muscle contractions or movements of a subject. The system further includes a second module configured to derive a neural state assessment of the subject based at least in part on the neural data. The system further includes a third module configured to derive at least one neural stimulation parameter based at least in part on the neural state assessment. The system further includes a fourth module configured to deliver neural stimulations to the subject based at least in part on the at least one neural stimulation parameter.

Claims (62)

1. A non-transitory computer readable medium having program instructions for implementing a neural stimulation method comprising:

deriving, by a processor, neural data from muscle contractions or movements of a subject;

deriving, by a graphical text analyzer of said processor, neural state assessment data that represents a neural state assessment of said subject based at least in part on said neural data, wherein said graphical text analyzer comprises a graphical text analysis module, a learning engine and a predictive engine;

wherein said neural state assessment comprises a prediction that the subject will transition into a state of psychiatric dysfunction;

deriving, by said processor, based at least in part on said neural state assessment data, at least one neural stimulation parameter of an electrical neural stimulation; and

delivering said neural stimulation having said at least one neural stimulation parameter through an electrode to said subject;

wherein deriving said neural state assessment data that represents a neural state assessment of said subject based at least in part on said neural data comprises converting said neural data to a graphical set of vectors;

wherein said vectors categorize a neural state of said subject.

2. The method of claim 1 , wherein:

said neural data comprises text;

said muscle contractions or movements produce speech; and

said deriving neural data from muscle contractions or movements comprises converting speech to text.

3. The method of claim 1 , wherein said deriving said neural state assessment data that represents a neural state assessment of said subject based at least in part on said neural data further comprises:

providing a first category of a cognitive state of said subject; and

using said first category to predict a cognitive trajectory and to update said at least one neural stimulation parameter.

4. The method of claim 3 , wherein:

said deriving neural data from muscle contractions or movements of said subject comprises deriving additional neural data samples;

said additional neural data samples provide predictions of additional cognitive trajectories within said graphical set of vectors; and

said additional neural data samples comprise at least one of:

a written text;

an electroencephalogram (EEG);

a deep brain electrophysiology; and

at least one behavior of said subject.

5. The method of claim 4 wherein:

said deriving said neural state assessment data that represents a neural state assessment of said subject based at least in part on said neural data comprises calculating a probability that any of said cognitive trajectory and said additional cognitive trajectories was produced by a particular Markov chain.

6. The method of claim 4 , wherein:

said additional data samples comprise said at least one neural stimulation parameter;

a second classification of cognitive state comprises a determination that a change in said neural state of said subject was beneficial; and

said deriving said at least one neural stimulation parameter comprises selecting said at least one neural stimulation parameter based on an assessment that said at least one neural stimulation parameter has achieved a reclassification of said neural state of said subject.

7. A non-transitory computer readable medium having program instructions for implementing a neural stimulation method comprising:

deriving, by a processor, neural data from muscle contractions or movements of a subject;

deriving, by a graphical text analyzer of said processor, neural state assessment data that represents a neural state assessment of said subject based at least in part on said neural data;

deriving, by said processor, at least one neural stimulation parameter based at least in part on said neural state assessment data; and

delivering neural stimulations through an electrode to said subject based at least in part on said at least one neural stimulation parameter;

wherein said deriving said neural state assessment data that represents a neural state assessment of said subject based at least in part on said neural data comprises converting said neural data to a graphical set of vectors;

wherein said vectors categorize a neural state of said subject.

8. The method of claim 7 , wherein:

said neural data comprises text;

said muscle contractions or movements produce speech; and

said deriving neural data from muscle contractions or movements comprises converting speech to text.

9. A non-transitory computer readable medium having program instructions for implementing a neural stimulation method comprising:

deriving, by a processor, neural data from muscle contractions or movements of a subject;

deriving, by a graphical text analyzer of said processor, neural state assessment data that represents a neural state assessment of said subject based at least in part on said neural data;

deriving, by said processor, at least one neural stimulation parameter based at least in part on said neural state assessment data; and

delivering neural stimulations through an electrode to said subject based at least in part on said at least one neural stimulation parameter;

wherein said deriving said neural state assessment data that represents a neural state assessment of said subject based at least in part on said neural data further comprises:

providing a first category of a cognitive state of said subject; and

using said first category to predict a cognitive trajectory and to update said at least one neural stimulation parameter.

10. The method of claim 9 , wherein:

said deriving neural data from muscle contractions or movements of said subject comprises deriving additional neural data samples;

said additional neural data samples provide predictions of additional cognitive trajectories within said graphical set of vectors; and

said additional neural data samples comprise at least one of:

a written text;

an electroencephalogram (EEG);

a deep brain electrophysiology; and

at least one behavior of said subject.

11. The method of claim 9 wherein:

said deriving a neural state assessment data that represents a neural state assessment of said subject based at least in part on said neural data comprises calculating a probability that any of said cognitive trajectory and said additional cognitive trajectories was produced by a particular Markov chain.

12. The method of claim 9 , wherein:

said additional data samples comprise said at least one neural stimulation parameter;

a second classification of cognitive state comprises a determination that a change in said neural state of said subject was beneficial; and

said deriving said at least one neural stimulation parameter comprises selecting said at least one neural stimulation parameter based on an assessment that said at least one neural stimulation parameter has achieved a reclassification of said neural state of said subject.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 19, 2015
From: CECCHI, GUILLERMO A.; KOZLOSKI, JAMES R.; PICKOVER, CLIFFORD A.; RISH, IRINA
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 035946/0402 →
Continuity (2)
Continuation 14637519 · Mar 4, 2015
Related Publication 20160256691A1 · Sep 8, 2016