Spatiotemporal pattern recognition for neurological event detection and prediction in an implantable device

• US 9,314,182 B2
• Filed: 11/16/2012
• Issued: 04/19/2016
• Est. Priority Date: 09/13/2002
• Status: Active Grant

• Current Assignee: Neuropace Inc.
• Original Assignee: Neuropace Inc.
• Inventors: Wingeier, Brett M., Tcheng, Thomas K.
• Primary Examiner(s): NEGIN, RUSSELL SCOTT
• Application Number:
  US13/679,925
• Publication Number:
  US 20130072810A1
• Time in Patent Office: 1,250 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: A61B 5/0031 Implanted circuitry
• CPC Class Codes: A61B 5/076 Permanent implantations telemetry using implanted circuitry A61B5/0031; implanted stimulators for therapy A61N1/3605, A61N1/362, A61N1/372
• CPC Class Codes: A61B 5/165 Evaluating the state of mind, e.g. depression, anxiety
• CPC Class Codes: A61B 5/369 Electroencephalography [EEG] devices for psychotechnics A61B5/16
• 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 5/377 using evoked responses
• CPC Class Codes: A61B 5/4094 Diagnosing or monitoring seizure diseases, e.g. epilepsy
• CPC Class Codes: A61B 5/7257 using Fourier transforms

Abstract

A system and method for detecting and predicting neurological events with an implantable device uses a relatively low-power central processing unit in connection with signal processing circuitry to identify features (including half waves) and calculate window-based characteristics (including line lengths and areas under the curve of the waveform) in one or more electrographic signals received from a patient'"'"'s brain. The features and window-based characteristics are employed within the framework of a programmable finite state machine to identify patterns and sequences in and across the electrographic signals, facilitating early and reliable detection and prediction of complex spatiotemporal neurological events in real time, and enabling responsive action by the implantable device.

Claims

1. An active implantable medical device comprising:

a plurality of electrodes configured to sense electrical signals from a patient;

a detection subsystem comprising at least one sensing channel and at least one detection channel, the at least one sensing channel configured to receive the electrical signals from the plurality of electrodes and to provide a signal input to the at least one detection channel, the at least one detection channel configured to provide at least one output resulting from the application of at least one detection tool to the signal input, the at least one output in the form of a discrete signal event; and

a processor and memory configured to detect one of an occurrence of a neurological event of interest or an absence of the neurological event of interest based on a sequence and timing of discrete signal events, the processor and memory comprising a state machine configured to receive the at least one discrete signal event as an input and to have a plurality of possible states including an initial state, an end state corresponding to the absence of the neurological event of interest, a detection state corresponding to the occurrence of the neurological event of interest, and a sequence of at least two noninitial possible states intermediate the initial state and the detection state,

wherein at least one first possible discrete signal event input resulting from a detection of a first type of electrical activity from the patient causes a transition out of the initial state into a first state of the at least two noninitial possible states, at least one second possible discrete signal event input resulting from a detection of a second type of electrical activity from the patient within a first period of time causes a transition out of the first state into a second state of the at least two noninitial possible states, and at least one third possible discrete signal event input resulting from a detection of a third type of electrical activity from the patient within a second period of time causes a transition out of the second state into the detection state, and

wherein an absence of the detection of the second type of electrical activity from the patient within the first period of time causes a transition out of the first state into the end state, and an absence of the detection of the third type of electrical activity from the patient within the second period of time causes a transition out of the second state into the end state.

2. The active implantable medical device of claim 1, wherein each of the first type of electrical activity, the second type of electrical activity and the third type of electrical activity correspond to abnormal electrical activity.

3. The active implantable medical device of claim 2, wherein the sequence of the first type of electrical activity, followed by the second type of electrical activity and followed by the third type of electrical activity corresponds to a neurological event of interest.

4. The active implantable medical device of claim 3, wherein the neurological event of interest precedes a seizure.

5. The active implantable medical device of claim 1, wherein the implantable medical device is configured to perform an action upon transition into the detection state, the action comprising one or more of providing responsive stimulation to the patient, changing operation modes, and recording a record entry.

6. The active implantable medical device of claim 5, wherein the processor is configured to reset the state machine to the initial state subsequent to performing the action.

7. The active implantable medical device of claim 6, wherein the processor is configured to reset the state machine a delay time after performing the action.

8. The active implantable medical device of claim 1, wherein the processor is configured to reset the state machine to the initial state subsequent to transitioning into the end state.

9. The active implantable medical device of claim 8, wherein the processor is configured to reset the state machine a delay time after transitioning into the end state.