Systems and methods to improve sleep disordered breathing using closed-loop feedback

1. A system comprising:

a sensor implantable adjacent to an anterior lingual muscle in a subject and configured to record physiological data;

a computing device comprising:

a non-transitory memory storing instructions; and

a processor to access the non-transitory memory and execute the instructions to at least:

monitor the physiological data recorded by the sensor;

identify a trigger within the physiological data, wherein the trigger comprises a detected biomarker; and

apply a rule-based classification to the trigger to determine whether one or more parameters of a stimulation should be altered based on the trigger; and

an electrode implantable adjacent to a hypoglossal nerve and configured to deliver the stimulation to the hypoglossal nerve during a sleep period and to alter the one or more parameters of the stimulation in response to a signal from the computing device,

wherein the rule-based classification utilizes adaptive learning during the sleep period, or after the sleep period, or both during and after the sleep period to learn subject-specific biomarkers that correlate to sleep-related conditions in a manner personalized to the subject.

2. The system of claim 1 , wherein the physiological data comprises inspiration, sleep stage, body position, or combinations thereof.

3. The system of claim 2 , wherein the physiological data is obtained from EMG activity from the musculature of the anterior airway.

4. The system of claim 3 , wherein the EMG activity comprises characteristic signals that correlate to respiration, sleep position, sleep state, or combinations thereof.

5. The system of claim 1 , wherein the physiological data comprises phasic activity of the genioglossus muscle, tonic activity of the genioglossus muscle, or both.

6. The system of claim 1 , wherein the sensor and the electrode are on a neuromodulation lead.

7. The system of claim 1 , wherein the trigger comprises a change in at least one parameter of the physiological data.

8. The system of claim 7 , wherein the physiological data is related to respiration and the at least one parameter is indicative of inspiration.

9. The system of claim 1 , wherein at least one of the subject-specific biomarkers is related to a stage in a sleep cycle, wherein the stage in the sleep cycle is awake, non-REM stage 1 light sleep, non-REM stage 2 light sleep, non-REM stage 3 deep sleep, REM sleep, or combinations thereof.

10. The system of claim 1 , wherein initial rules of an algorithm used by the rule-based classification are determined based on historical values for a population, historical values for a patient, and/or patient derived values.

11. The system of claim 1 , wherein the trigger indicates a change in body position.

12. The system of claim 11 , wherein the rule-based classification determines whether the one or more parameters should be altered based on the change in body position.

13. The system of claim 1 , wherein at least one of the subject-specific biomarkers is related to an apneic event, a respiration rate, an inspiration, an expiration, a body position, and/or a chin position.

14. The system of claim 1 , wherein the one or more parameters of the stimulation comprise at least one selected from the group consisting of: when to apply the stimulation, stimulation pulse width, stimulation amplitude, stimulation frequency, stimulation waveform shape, electrode position, and electrode configuration.

15. A method of improving sleep disordered breathing (SDB) in a subject comprising:

monitoring, by a system comprising a processor, physiological data recorded by a sensor implanted proximal to an anterior lingual muscle;

identifying, by the system, a trigger within the physiological data, wherein the trigger comprises a detected biomarker;

applying, by the system, a rule-based classification to the trigger to determine whether one or more parameters of a stimulation during a sleep period should be altered based on the trigger, wherein the rule-based classification utilizes adaptive learning during the sleep period, or after the sleep period, or both during and after the sleep period to learn subject-specific biomarkers that correlate to sleep-related conditions in a manner personalized to the subject.

16. The method of claim 15 , further comprising sending, by the system, a signal comprising configuration or setting information for the parameters to an electrode located adjacent to the hypoglossal nerve.

17. The method of claim 15 , wherein the trigger comprises a change in at least one parameter of the physiological data.

18. The method of claim 15 , wherein the physiological data is related to respiration and the at least one parameter is indicative of inspiration.

19. The method of claim 15 , wherein at least one of the subject-specific biomarkers is a stage in a sleep cycle of the patient, wherein the stage in the sleep cycle is awake, non-REM stage 1 light sleep, non-REM stage 2 light sleep, non-REM stage 3 deep sleep, REM sleep, or combinations thereof.

20. The method of claim 15 , further comprising receiving, by the system, an indication of a change in body position, wherein the change in body position is used to identify the trigger.

21. The method of claim 15 , further comprising titrating the stimulation parameters based on the trigger.

22. The method of claim 21 , wherein the titrating optimizes airway muscle tone.

23. The method of claim 15 , wherein the one or more parameters of the stimulation comprise at least one selected from the group consisting of: when to apply the stimulation, stimulation pulse width, stimulation amplitude, stimulation frequency, stimulation waveform shape, electrode position, and electrode configuration.