Spatiotemporal pattern recognition for neurological event detection and prediction in an implantable device
First Claim
1. An implantable medical device, comprising:
- a sensing subsystem configured to sense electrical activity from a patient'"'"'s brain;
a detection subsystem configured to detect a set of signal events based on the sensed electrical activity;
a configurable finite state machine comprising;
a representation of a set of states;
a representation of a set of transition events, wherein an occurrence of a first transition event of the set of transition events causes a first transition out of a first state, the first transition being one of an exclusive transition from the first state or a non-exclusive transition from the first state, and wherein an occurrence of a second transition event of the set of transition events may cause a second transition out of the first state; and
a representation of the set of signal events, wherein a first detected signal event of the set of signal events is mapped to the first transition event, a second detected signal event of the set of signal events is mapped to the second transition event, wherein the first detected signal event, once mapped to the first transition event, causes the first transition to occur, and the second detected signal event, once mapped to the second transition event, causes the second transition to occur when the first transition is a non-exclusive transition, and to not occur when the first transition is an exclusive transition;
a central processing unit configured, in conjunction with the configurable finite state machine, to determine whether at least two individual detected signal events of the set of signal events occur in at least one of a predetermined pattern and sequence representative of a neurological event,wherein the central processing unit selects a response, from a predetermined menu of possible responses, whenever the predetermined pattern and sequence of the at least two individual neurological events is determined to have occurred.
3 Assignments
0 Petitions
Accused Products
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.
-
Citations
10 Claims
-
1. An implantable medical device, comprising:
-
a sensing subsystem configured to sense electrical activity from a patient'"'"'s brain; a detection subsystem configured to detect a set of signal events based on the sensed electrical activity; a configurable finite state machine comprising; a representation of a set of states; a representation of a set of transition events, wherein an occurrence of a first transition event of the set of transition events causes a first transition out of a first state, the first transition being one of an exclusive transition from the first state or a non-exclusive transition from the first state, and wherein an occurrence of a second transition event of the set of transition events may cause a second transition out of the first state; and a representation of the set of signal events, wherein a first detected signal event of the set of signal events is mapped to the first transition event, a second detected signal event of the set of signal events is mapped to the second transition event, wherein the first detected signal event, once mapped to the first transition event, causes the first transition to occur, and the second detected signal event, once mapped to the second transition event, causes the second transition to occur when the first transition is a non-exclusive transition, and to not occur when the first transition is an exclusive transition; a central processing unit configured, in conjunction with the configurable finite state machine, to determine whether at least two individual detected signal events of the set of signal events occur in at least one of a predetermined pattern and sequence representative of a neurological event, wherein the central processing unit selects a response, from a predetermined menu of possible responses, whenever the predetermined pattern and sequence of the at least two individual neurological events is determined to have occurred. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10)
-
Specification