Methods and systems for automatically identifying detection parameters for an implantable medical device
An initial set of parameters for operating one or more detection tools is automatically derived and subsequently adjusted so that each detection tool is more or less sensitive to signal characteristics in a region of interest. Detection tool(s) may be applied to physiological signals sensed from a patient (such as EEG signals) and may be configured to run in an implanted medical device that is programmable with the parameters to look for rhythmic activity, spiking, and power changes in the sensed signals, etc. A detection tool may be selected and parameter values derived in a logical sequence and/or in pairs based on a graphical representation of an activity type which may be selected by a user, for example, by clicking and dragging on the graphic via a GUI. Displayed simulations allow a user to assess what will be detected with a derived parameter set and then to adjust the sensitivity of the set or start over as desired.
1. A method of deriving a detection tool that detects for an event in electrographic signals, the detection tool to be implemented in an implantable medical device implanted in a patient, the method comprising:
a. processing a region of interest in an electrographic signal sensed by the implantable medical device to determine a candidate parameter set that configures a candidate detection tool to detect the event;
b. configuring the candidate detection tool based on the candidate parameter set;
c. applying the candidate detection tool to a plurality of available electrographic signals to determine an event detection rate for the candidate detection tool, wherein the plurality of available electrographic signals are signals of other patients with one or more demographics in common with the patient;
d. comparing the event detection rate to a criterion corresponding to a desired detection rate; and
e. in response to the criterion being satisfied, implementing the candidate detection tool as the detection tool in the implantable medical device.
2. The method of claim 1 , wherein the plurality of available electrographic signals further comprise signals of the patient that are sensed and stored by the implantable medical device.
3. The method of claim 1 , wherein the plurality of available electrographic signals further comprise signals of the patient that are sensed in real time by the implantable medical device.
4. The method of claim 1 , further comprising:
in response to the criterion not being satisfied, adjusting a value of one or more of the parameters of the candidate parameter set; and
repeating steps b, c, d, and e.
5. A method of deriving a detection tool that detects for an event in electrographic signals, the detection tool to be implemented in an implantable medical device implanted in a patient, the method comprising:
a. processing a region of interest in an electrographic signal sensed by the implantable medical device to determine a candidate parameter set that configures a candidate detection tool to detect the event;
b. configuring the candidate detection tool based on the candidate parameter set;
C. applying the candidate detection tool to a plurality of available electrographic signals to determine an event detection rate for the candidate detection tool;
d. comparing the event detection rate to a criterion corresponding to a desired detection rate; and
e. in response to the criterion being satisfied, implementing the candidate detection tool as the detection tool in the implantable medical device,
wherein processing a region of interest in an electrographic signal comprises:
analyzing the region of interest to determine from among a plurality of different activity types, a determined activity type with which to characterize the region of interest; and
based on the determined activity type, automatically selecting the candidate detection tool from among a plurality of different types of detection tools.
6. The method of claim 5 , wherein the electrographic signal sensed by the implantable medical device comprises an event corresponding to a seizure onset and the region of interest is at or near the seizure onset.
7. The method of claim 5 , wherein the plurality of different types of detection tools comprises a half wave detector configured to look for rhythmic activity, a half wave detector configured to look for spiking activity and a line length detector configured to look for a power change.
8. The method of claim 5 , wherein the plurality of different activity types comprises rhythmic activity, spiking activity, and a change in power of the electrographic signal compared to a predetermined norm.
9. The method of claim 8 , wherein the determined activity type is rhythmic activity, the detection tool is a half wave detector, and the parameter set comprises one or more of a half wave hysteresis parameter, a minimum half wave amplitude parameter, a minimum half wave width parameter, a half wave count criterion parameter, a half wave window size parameter, a qualified analysis window count parameter, and a detection analysis window size parameter.
10. The method of claim 8 , wherein the determined activity type is spiking activity, the detection tool is a half wave detector, and the parameter set comprise one or more of a half wave hysteresis parameter, a minimum half wave amplitude parameter, a minimum half wave width parameter, a half wave count criterion parameter, a half wave window size parameter, a qualified analysis window count parameter, and a detection analysis window size parameter.
11. The method of claim 8 , wherein the determined activity type is an activity corresponding to a change in power of the electrographic signal compared to a predetermined norm, the detection tool is a line length detector, and the parameter set comprises one or more of a value of a short term window size parameter, a value of a long term window size parameter, a value of a detection threshold parameter, a value of a threshold logic parameter, a value of a threshold mode parameter, a value of a sample count parameter, a value of an inter-sample interval parameter, and a value of a persistence parameter.
12. A system deriving a detection tool that detects for an event in electrographic signals, the detection tool to be implemented in an implantable medical device implanted in a patient, the system comprising:
a memory; and
a processor coupled to the memory and configured to:
a. process a region of interest in an electrographic signal sensed by the implantable medical device to determine a candidate parameter set that configures a candidate detection tool to detect the event;
b. configure the candidate detection tool based on the candidate parameter set;
c. apply the candidate detection tool to a plurality of electrographic signals to determine an event detection rate for the candidate detection tool, wherein the plurality of available electrographic signals are signals of other patients with one or more demographics in common with the patient;
d. compare the event detection rate to a criterion corresponding to a desired detection rate; and
e. in response to the criterion being satisfied, implement the candidate detection tool as the detection tool in the implantable medical device.
13. The system of claim 12 , wherein the plurality of available electrographic signals further comprise signals of the patient that are sensed and stored by the implantable medical device.
14. The system of claim 12 , wherein the plurality of available electrographic signals further comprise signals of the patient that are sensed in real time by the implantable medical device.
15. The system of claim 12 , wherein the processor is further configured to:
in response to the criterion not being satisfied, adjust a value of one or more of the parameters of the candidate parameter set; and
repeat steps b, c, d, and e.
16. A system deriving a detection tool that detects for an event in electrographic signals, the detection tool to be implemented in an implantable medical device implanted in a patient, the system comprising:
a memory; and
a processor coupled to the memory and configured to:
a. process a region of interest in an electrographic signal sensed by the implantable medical device to determine a candidate parameter set that configures a candidate detection tool to detect the event;
b. configure the candidate detection tool based on the candidate parameter set;
c. apply the candidate detection tool to a plurality of electrographic signals to determine an event detection rate for the candidate detection tool;
d. compare the event detection rate to a criterion corresponding to a desired detection rate; and
e. in response to the criterion being satisfied, implement the candidate detection tool as the detection tool in the implantable medical device,
wherein the processor processes a region of interest in an electrographic signals by being further configured to:
analyze the region of interest to determine from among a plurality of different activity types, a determined activity type with which to characterize the region of interest; and
based on the determined activity type, automatically select the candidate detection tool from among a plurality of different types of detection tools.
17. The system of claim 16 , wherein the electrographic signal sensed by the implantable medical device comprises an event corresponding to a seizure onset and the region of interest is at or near the seizure onset.
18. The system of claim 16 , wherein the plurality of different types of detection tools comprises a half wave detector configured to look for rhythmic activity, a half wave detector configured to look for spiking activity and a line length detector configured to look for a power change.
19. The system of claim 16 , wherein the plurality of different activity types comprises rhythmic activity, spiking activity, and a change in power of the electrographic signal compared to a predetermined norm.