Neurostimulator devices using a machine learning method implementing a gaussian process optimization

• US 9,931,508 B2
• Filed: 06/30/2016
• Issued: 04/03/2018
• Est. Priority Date: 03/24/2011
• Status: Active Grant

• Current Assignee: California Institute of Technology, Institute of Technology (Select Education Group LLC), Regents of the University of California (University of California), University of Louisville
• Original Assignee: California Institute of Technology, NeuroRecovery Technologies, Inc. (GTX medical SA), Regents of the University of California (University of California), University of Louisville
• Inventors: Burdick, Joel W., Tai, Yu-Chong, Naber, John F., Keynton, Robert S., Edgerton, Victor Reggie, Roy, Roland R., Gerasimenko, Yury, Harkema, Susan J., Hodes, Jonathan, Angeli, Claudia A, Nandra, Mandheerej S., Desautels, Thomas Anthony, Upchurch, Steven L., Jackson, Douglas J., Terrafranca, Nicholas A., Chen, Yangsheng
• Primary Examiner(s): CAREY, MICHAEL JAMES
• Application Number:
  US15/199,580
• Publication Number:
  US 20160310739A1
• Time in Patent Office: 642 Days
• Field of Search: 607 48, 607 49, 607 60, 607 62, 607 66, 607 68, 607117
• CPC Class Codes: A61B 2505/09 Rehabilitation or training
• CPC Class Codes: A61B 5/1106 to assess neuromuscular blockade, e.g. to estimate depth of anaesthesia
• CPC Class Codes: A61B 5/296 for electromyography [EMG]
• CPC Class Codes: A61B 5/407 Evaluating the spinal cord A61B5/4896 takes precedence
• CPC Class Codes: A61B 5/4076 Diagnosing or monitoring particular conditions of the nervous system A61B5/4821, A61B5/4824 take precedence
• CPC Class Codes: A61B 5/4836 Diagnosis combined with treatment in closed-loop systems or methods A61B5/0036 takes precedence
• CPC Class Codes: A61N 1/0551 Spinal or peripheral nerve electrodes
• CPC Class Codes: A61N 1/0553 Paddle shaped electrodes, e.g. for laminotomy
• CPC Class Codes: A61N 1/36003 of motor muscles, e.g. for walking assistance
• CPC Class Codes: A61N 1/36007 of urogenital or gastrointestinal organs, e.g. for incontinence control
• CPC Class Codes: A61N 1/36067 Movement disorders, e.g. tremor or Parkinson disease stimulating motor muscle A61N1/36003
• CPC Class Codes: A61N 1/36082 Cognitive or psychiatric applications, e.g. dementia or Alzheimer's disease
• CPC Class Codes: A61N 1/36103 Neuro-rehabilitation; Repair or reorganisation of neural tissue, e.g. after stroke
• CPC Class Codes: A61N 1/36107 Sexual dysfunction stimulating genital organs A61N1/36007
• CPC Class Codes: A61N 1/3611 Respiration control stimulating respiratory organs A61N1/3601
• CPC Class Codes: A61N 1/36114 Cardiac control, e.g. by vagal stimulation stimulating the heart A61N1/362
• CPC Class Codes: A61N 1/36125 Details of circuitry or electric components
• CPC Class Codes: A61N 1/36139 with automatic adjustment

Abstract

Neurostimulator devices are described comprising: a stimulation assembly connectable to a plurality of electrodes, wherein the plurality of electrodes are configured to stimulate a spinal cord; one or more sensors; and at least one processor configured to modify at least one complex stimulation pattern deliverable by the plurality of electrodes by integrating data from the one or more sensors and performing a machine learning method implementing a Gaussian Process Optimization on the at least one complex stimulation pattern. Methods of use are also described.

Claims

1. A neurostimulator device comprising:

a stimulation assembly connectable to a plurality of electrodes, wherein the plurality of electrodes are configured to stimulate a spinal cord using an applied complex stimulation pattern;

one or more sensors configured to measure a response related to stimulation of the spinal cord; and

at least one processor configured to modify the applied complex stimulation pattern deliverable by the plurality of electrodes to create a modified complex stimulation pattern for subsequent stimulation of the spinal cord by integrating data from the one or more sensors and performing a machine learning method implementing a Gaussian Process Optimization (“

GPO”

) relation that describes a predicted mean and a variance of a motor performance function for a plurality of candidate complex stimulation patterns, including the applied complex stimulation pattern, based on at least on one of (i) previous data from the one or more sensors, and (ii) data derived in a previous stimulation study,

wherein the GPO relation includes an upper confidence bound rule for applying a weight to modify the applied complex stimulation pattern based on a number of times data is received from the one or more sensors regarding stimulation of the spinal cord, and

wherein the upper confidence bound rule modifies the applied complex stimulation pattern through convergence of the GPO relation toward an optimal candidate complex stimulation pattern.

2. The neurostimulator device of claim 1, wherein at least one of the applied complex stimulation pattern or the modified complex stimulation pattern comprises a first stimulation pattern followed by a second stimulation pattern.

3. The neurostimulator device of claim 1, wherein the at least one processor is configured to receive and record electrical signals from the plurality of electrodes.

4. The neurostimulator device of claim 1, wherein the at least one processor is configured to receive electrical signals from the plurality of electrodes, and modify the applied complex stimulation pattern based at least in part on the electrical signals received from the plurality of electrodes.

5. The neurostimulator device of claim 1, wherein the one or more sensors include an electromyography sensor, an evoked potential sensor, a joint angle sensor, a flex sensor, an accelerometer, a gyroscope sensor, a flow sensor, a pressure sensor, a load sensor, a temperature sensor, or a combination thereof.

6. The neurostimulator device of claim 1 configured to aid a patient having a neurologically derived paralysis in a portion of the patient'"'"'s body affected by a lesion to the spinal cord, wherein the spinal cord includes at least one selected spinal circuit that has a first stimulation threshold representing a minimum amount of stimulation required to activate the at least one selected spinal circuit, and a second stimulation threshold representing an amount of stimulation above which the at least one selected spinal circuit is fully activated,

wherein when at least one of the applied complex stimulation pattern or the modified complex stimulation pattern is applied to a portion of the spinal cord of the patient, the at least one complex stimulation pattern is below the second stimulation threshold such that the at least one selected spinal circuit is at least partially activatable by the addition of at least one of (a) neurological signals originating from the portion of the patient'"'"'s body having the paralysis, and (b) supraspinal signals.

7. The neurostimulator device of claim 1 configured to stimulate the spinal cord and improve or restore voluntary movement, an autonomic function, motor function, metabolic function, or a combination thereof.

8. The neurostimulator device of claim 1, wherein at least one of the response or the motor performance function is based on at least one of voluntary movement of muscles involved in standing, voluntary movement of muscles involved in stepping, voluntary movement of muscles involved in reaching, voluntary movement of muscles involved in grasping, voluntarily changing positions of one or both legs, voluntarily changing positions of one or both arms, voiding the subject'"'"'s bladder, sexual function, voiding the subject'"'"'s bowel, postural activity, locomotor activity, cardiovascular function, respiratory function, digestive function, autonomic function, motor function, vasomotor function, cognitive function, body temperature, metabolic processes, or a combination thereof.

9. The device neurostimulator of claim 1, wherein the plurality of electrodes include more than four groups of electrodes.

10. The device neurostimulator of claim 9, wherein at least one of the applied complex stimulation pattern or the modified complex stimulation pattern comprises different electrical stimulation for each of the groups of electrodes.

11. The device neurostimulator of claim 1, wherein at least one electrode of the plurality of electrodes is configured to deliver a stimulus 1 microsecond apart.

12. The device neurostimulator of claim 1, further comprising a system including a plurality of muscle electrodes.

13. The device neurostimulator of claim 1, wherein one electrode of the plurality of electrodes is located at neural tissue and another electrode of the plurality of electrodes is located at an end organ.

14. A method of improving neurologically derived paralysis, the method comprising:

applying a first complex stimulation pattern to a spinal cord of a patient using a neurostimulator device that includes a stimulation assembly connectable to a plurality of electrodes for stimulating the spinal cord;

measuring with one or more sensors a response related to stimulation of the spinal cord; and

modifying, via a processor, the first complex stimulation pattern to create a second complex stimulation pattern for subsequent stimulation of the spinal cord by integrating data from the one or more sensors and performing a machine learning method implementing a Gaussian Process Optimization (“

GPO”

) relation that describes a predicted mean and a variance of a motor performance function for a plurality of candidate complex stimulation patterns, including the first complex stimulation pattern, based on at least on one of (i) previous data from the one or more sensors, and (ii) data derived in a previous stimulation study,

wherein the GPO relation includes an upper confidence bound rule for applying a weight to modify the first complex stimulation pattern based on a number of times data is received from the one or more sensors regarding stimulation of the spinal cord, and

wherein the upper confidence bound rule modifies the first complex stimulation pattern through convergence of the GPO relation toward an optimal candidate complex stimulation pattern.

15. The method of claim 14, wherein stimulation of the spinal cord and improves or restores at least one of voluntary movement of muscles involved in standing, voluntary movement of muscles involved in stepping, voluntary movement of muscles involved in reaching, voluntary movement of muscles involved in grasping, voluntarily changing positions of one or both legs, voluntarily changing positions of one or both arms, voiding the subject'"'"'s bladder, sexual function, voiding the subject'"'"'s bowel, postural activity, locomotor activity, cardiovascular function, respiratory function, digestive function, autonomic function, motor function, vasomotor function, cognitive function, body temperature, metabolic processes, or a combination thereof.

16. The method of claim 14, wherein the one or more sensors include an electromyography sensor, an evoked potential sensor, a joint angle sensor, a flex sensor, an accelerometer, a gyroscope sensor, a flow sensor, a pressure sensor, a load sensor, a temperature sensor, or a combination thereof.

17. The method of claim 14, wherein when at least one of the first complex stimulation pattern and the second complex stimulation pattern is below a stimulation threshold such that at least one selected spinal circuit is at least partially activatable by addition of at least one of (a) neurological signals originating from a portion of the patient'"'"'s body having the paralysis, and (b) supraspinal signals.

18. The method of claim 14, wherein the plurality of electrodes includes more than four groups of electrodes.

19. The method of claim 18, wherein at least one of the first complex stimulation pattern and the second complex stimulation pattern comprises different electrical stimulation for each of the groups of electrodes.

20. The method of claim 14, further comprising:

subjecting the patient to physical training using a training device.