Seizure onset classification and stimulation parameter selection

• US 10,543,368 B2
• Filed: 10/04/2018
• Issued: 01/28/2020
• Est. Priority Date: 02/10/2015
• Status: Active Grant

• Current Assignee: Neuropace Inc.
• Original Assignee: Neuropace Inc.
• Inventors: Crowder, Tara Leigh, Arcot Desai, Sharanya, Morrell, Martha Jo, Tcheng, Thomas Kim, Kapur, Ritu
• Primary Examiner(s): Fairchild, Mallika D
• Application Number:
  US16/152,111
• Publication Number:
  US 20190030337A1
• Time in Patent Office: 481 Days
• CPC Class Codes: A61B 5/374 Detecting the frequency distribution of signals, e.g. detecting delta, theta, alpha, beta or gamma waves
• CPC Class Codes: A61B 5/4094 Diagnosing or monitoring seizure diseases, e.g. epilepsy
• CPC Class Codes: A61B 5/4836 Diagnosis combined with treatment in closed-loop systems or methods A61B5/0036 takes precedence
• 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 5/7282 Event detection, e.g. detecting unique waveforms indicative of a medical condition A61B5/4094, A61B5/4818, A61B5/349, A61B5/0823 take precedence
• CPC Class Codes: A61N 1/0529 Electrodes for brain stimulation
• CPC Class Codes: A61N 1/36064 Epilepsy
• CPC Class Codes: A61N 1/36139 with automatic adjustment
• CPC Class Codes: A61N 1/37241 providing test stimulations
• CPC Class Codes: A61N 1/37247 User interfaces, e.g. input or presentation means

Abstract

A neurostimulation system senses electrographic signals from the brain of a patient, extracts features from the electrographic signals, and when the extracted features satisfy certain criteria, detects a neurological event type. A mapping function relates the detected neurological event type to a stimulation parameter subspace and a default stimulation parameter set where the values of the stimulation parameters define an instance of stimulation therapy for the patient. The decision whether to implement a stimulation parameter subspace or a default stimulation parameter set may be informed by integrating other information about a state of the patient. A stimulation parameter subspace or stimulation parameter set may optimized by testing it against various thresholds until certain effectiveness criteria is satisfied. The neurological event type may be one of several electrographic seizure onset types.

Claims

1. A neurostimulation system comprising:

a neurostimulator having a control module configured to detect seizure onsets and to generate an instance of stimulation therapy for delivery to a patient to treat a neurological condition corresponding to epilepsy, the instance of stimulation therapy defined by a stimulation parameter set within a stimulation parameter subspace; and

an external component comprising;

a memory,

a table stored in the memory, which table correlates each of a plurality of seizure onset types to a stimulation parameter subspace;

one or more modules configured to compare a seizure onset detected by the neurostimulator to the plurality of seizure onset types in the table, to determine a ranking for the detected seizure onset corresponding to a probability that the detected seizure onset is a particular one of the plurality of seizure onset types, and to determine if the stimulation parameter set presently programmed into the neurostimulator is within a recommended stimulation parameter subspace, which recommended stimulation parameter subspace corresponds to the stimulation parameter subspace correlated in the table with the ranking for the detected seizure onset; and

a configuration module configured to provide an output signal to the control module of the neurostimulator when the stimulation parameter set presently programmed into the neurostimulator is not within the recommended stimulation parameter subspace, the output signal comprising the recommended stimulation parameter subspace.

2. The neurostimulation system of claim 1, wherein the external component further comprises an integration module configured to determine whether the neurostimulator should (a) ignore the output signal, or (b) receive the output signal as a recommendation, the integration module comprising:

an integrator configured to receive one or more physiological metrics of the patient and to establish a state of the patient based on one or more physiological metrics,

a comparator configured to compare the state of the patient to a threshold corresponding to one or more undesirable patient states, and to;

if the patient is in one of the one or more undesirable patient states, establish the recommended stimulation parameter subspace as the stimulation parameter subspace for the neurostimulator; and

if the patient is not in one of the one or more undesirable patient states, ignore the output signal.

3. The neurostimulation system of claim 2, wherein the one or more physiological metrics may be selected from a group of metrics including:

a pH level of neural tissue, an oxygenation level of neural tissue, and a neurotransmitter level of neural tissue.

4. The neurostimulation system of claim 2, wherein the one or more physiological metrics may be selected from a group of metrics including:

a rate at which the neurostimulator detects a particular seizure onset type, a rate at which the patient reports the neurological condition being treated, or a symptom thereof, and a duration of a particular seizure onset type.

5. The neurostimulation system of claim 1, further comprising an optimization module configured to test a present stimulation parameter set against a criterion related to an effectiveness of the present stimulation parameter set, and when the criterion is not met, cause the neurostimulator to generate instances of stimulation therapy in accordance with a new stimulation parameter set until the criterion is met.

6. The neurostimulation system of claim 5, wherein the criterion is related to at least one of:

a change in a rate at which the neurostimulator detects a particular seizure onset type, a change in a rate at which the patient reports the neurological condition being treated, or a symptom thereof, and a change in a duration of a particular seizure onset type.

7. The neurostimulation system of claim 1, wherein the plurality of seizure onset types comprises a low-voltage-fast seizure onset, a high-voltage-beta seizure onset, a hypersynchronous seizure onset, a spike-and-wave seizure onset, a multiple seizure onset, an attenuation seizure onset, and a neurological event type identified by a clustering process.

8. The neurostimulation system of claim 1, wherein the external component further comprises:

a communications module configured to establish a communications link with the neurostimulator,

wherein the output signal is transmitted to the neurostimulator over the communications link.

9. The neurostimulation system of claim 8, wherein the external component further comprises, a user interface configured to allow a user to select one or more stimulation parameter sets from within the recommended stimulation parameter subspace, wherein the communications module is configured to transmit instructions to the neurostimulator comprising the one or more selected stimulation parameter sets.

10. An implantable neurostimulator having a control module configured to detect seizure onsets and to generate an instance of stimulation therapy for delivery to a patient, the instance of stimulation therapy defined by a stimulation parameter set within a stimulation parameter subspace, and the implantable neurostimulator including a processing system comprising:

a memory;

a table stored in the memory, which table correlates each of a plurality of seizure onset types to a stimulation parameter subspace;

one or more modules configured to compare a seizure onset detected by the implantable neurostimulator to the plurality of seizure onset types in the table, to determine a ranking for the detected seizure onset corresponding to a probability that the detected seizure onset is a particular one of the plurality of seizure onset types, and to determine if the stimulation parameter set presently in used by the neurostimulator is within a recommended stimulation parameter subspace, which recommended stimulation parameter subspace corresponds to the stimulation parameter subspace correlated in the table with the ranking for the detected seizure onset; and

a configuration module configured to provide an output signal to the control module of the implantable neurostimulator when the stimulation parameter set presently programmed into the neurostimulator is not within the recommended stimulation parameter subspace, the output signal comprising the recommended stimulation parameter subspace.

11. The implantable neurostimulator of claim 10, wherein the processing system further comprises an integration module configured to determine whether the implantable neurostimulator should (a) ignore the output signal, or (b) receive the output signal as a recommendation, the integration module comprising:

an integrator configured to receive one or more physiological metrics of the patient and to establish a state of the patient based on one or more physiological metrics,

a comparator configured to compare the state of the patient to a threshold corresponding to one or more undesirable patient states, and to;

if the patient is in one of the one or more undesirable patient states, establish the recommended stimulation parameter subspace as the stimulation parameter subspace for the neurostimulator; and

if the patient is not in one of the one or more undesirable patient states, ignore the output signal.

12. The implantable neurostimulator of claim 10, further comprising an optimization module configured to:

test a present stimulation parameter set against a criterion related to an effectiveness of the present stimulation parameter set; and

when the criterion is not met, generate instances of stimulation therapy in accordance with a new stimulation parameter set until the criterion is met.

13. A method of defining values of parameters used by a neurostimulator having a control module configured to detect seizure onsets and to generate an instance of stimulation therapy for delivery to a patient, wherein the instance of stimulation therapy is defined by a stimulation parameter set within a stimulation parameter subspace, and the defining is performed by a processing system, the method comprising:

correlating each of a plurality of seizure onset types to a stimulation parameter subspace;

comparing a seizure onset detected by the neurostimulator to the correlated plurality of seizure onset types;

determining a ranking for the detected seizure onset corresponding to a probability that the detected seizure onset is a particular one of the plurality of seizure onset types;

determining if the stimulation parameter set presently programmed into the neurostimulator is within a recommended stimulation parameter subspace, which recommended stimulation parameter subspace corresponds to the stimulation parameter subspace correlated in the table with the ranking for the detected seizure onset; and

providing an output signal to the control module of the neurostimulator when the stimulation parameter set presently programmed into the neurostimulator is not within the recommended stimulation parameter subspace, the output signal comprising the recommended stimulation parameter subspace.

14. The method of claim 13, further comprising determining whether the neurostimulator should (a) ignore the output signal, or (b) receive the output signal as a recommendation.

15. The method of claim 14, wherein determining comprises:

receiving one or more physiological metrics of the patient;

establishing a state of the patient based on one or more physiological metrics;

comparing the state of the patient to a threshold corresponding to one or more undesirable patient states;

if the patient is in one of the one or more undesirable patient states, establishing the recommended stimulation parameter subspace as the stimulation parameter subspace for the neurostimulator; and

if the patient is not in one of the one or more undesirable patient states, ignoring the output signal.

16. The method of claim 15, further comprising:

testing a present stimulation parameter set against a criterion related to an effectiveness of the present stimulation parameter set; and

when the criterion is not met, causing the neurostimulator to generate instances of stimulation therapy in accordance with a new stimulation parameter set until the criterion is met.