Detecting seizures based on heartbeat data

1. A method comprising:

receiving heartbeat data of a patient;

receiving accelerometer data of the patient;

determining, using the accelerometer data, that the patient is transitioning from a sleep state to an awake state;

decreasing a weighting factor based on the transition;

determining modified heartbeat data by applying the weighting factor to at least a portion of the heartbeat data; and

detecting a seizure event based on the modified heartbeat data.

2. The method of claim 1 , wherein determining the modified heartbeat data includes determining a background (BG) heart rate based on a previously-determined BG heart rate, a most recent R-R interval, and the weighting factor.

3. The method of claim 2 , wherein the BG heart rate is determined as a sum of a first value and a second value, wherein the first value is the weighting factor times the previously-determined BG heart rate and the second value is one minus the weighting factor times the most recent R-R interval.

4. The method of claim 2 , wherein determining the modified heartbeat data further includes determining a foreground (FG) heart rate based on one or more R-R intervals of the heartbeat data.

5. The method of claim 4 , wherein detecting the seizure event comprises comparing a ratio of the FG heart rate and the BG heart rate to a seizure detection threshold.

6. The method of claim 1 , wherein the heartbeat data of the patient includes electrocardiogram data.

7. The method of claim 6 , wherein the electrocardiogram data indicates a timing related to a plurality of R-waves.

8. The method of claim 1 , further comprising causing, in response to the detection of the seizure event, initiation of at least one of a stimulation to tissue of the patient, a reporting of the occurrence of the seizure event, or a recording of the seizure event.

9. A medical device comprising:

a first interface to receive heartbeat data of a patient;

a second interface to receive acceleration data of the patient; and

a processor configured to:

determine, using the accelerometer data, that the patient is transitioning from a sleep state to an awake state;

decrease a weighting factor based on the transition;

determine modified heartbeat data by applying the weighting factor to at least a portion of the heartbeat data; and

detect a seizure event based on the modified heartbeat data.

10. The medical device of claim 9 , wherein determining the modified heartbeat data includes determining a background (BG) heart rate based on a previously-determined BG heart rate, a most recent R-R interval, and the weighting factor.

11. The medical device of claim 10 , wherein the BG heart rate is determined as a sum of a first value and a second value, wherein the first value is the weighting factor times the previously-determined BG heart rate and the second value is one minus the weighting factor times the most recent R-R interval.

12. The medical device of claim 10 , wherein determining the modified heartbeat data further includes determining a foreground (FG) heart rate based on one or more R-R intervals of the heartbeat data, wherein the seizure event is detected by comparing a ratio of the FG heart rate and the BG heart rate to a seizure detection threshold.

13. The medical device of claim 9 , wherein the processor, in response to the detection of the seizure event, provides a signal to at least one of stimulation device disposed to provide stimulation to tissue of the patient, a signal indicating the occurrence of the seizure event, and a signal initiating the recording of the seizure event.

14. A non-transitory computer-readable medium storing instructions that are executable by a processor to cause the processor to perform operations including:

receiving heartbeat data of a patient;

receiving accelerometer data of the patient;

determining, using the accelerometer data, that the patient is transitioning from a sleep state to an awake state;

decreasing a weighting factor based on the transition;

determining modified heartbeat data by applying the weighting factor to at least a portion of the heartbeat data; and

detecting a seizure event based on the modified heartbeat data.

15. The non-transitory computer-readable medium of claim 14 , wherein determining the modified heartbeat data includes determining a background (BG) heart rate based on a previously-determined BG heart rate, a most recent R-R interval, and the weighting factor.

16. The non-transitory computer-readable medium of claim 15 , wherein the BG heart rate is determined as a sum of a first value and a second value, wherein the first value is the weighting factor times the previously-determined BG heart rate and the second value is one minus the weighting factor times the most recent R-R interval.

17. The non-transitory computer-readable medium of claim 15 , wherein determining the modified heartbeat data further includes determining a foreground (FG) heart rate based on one or more R-R intervals of the heartbeat data, wherein the seizure event is detected by comparing a ratio of the FG heart rate and the BG heart rate to a seizure detection threshold.

18. The non-transitory computer-readable medium of claim 14 , wherein the processor, in response to the detection of the seizure event, provides a signal to at least one of stimulation device disposed to provide stimulation to tissue of the patient, a signal indicating the occurrence of the seizure event, and a signal initiating the recording of the seizure event.