Systems and methods for predicting atrial arrhythmia
Systems and methods for assessing a cardiac arrhythmia risk of a patient, such as a risk for developing atrial fibrillation, are disclosed. An exemplary medical-device system includes an arrhythmia predictor circuit configured to receive physiologic information of a patient, and in an absence of atrial tachyarrhythmia in the patient, determine a risk of the patient developing future atrial tachyarrhythmia using the physiologic information. In accordance with the arrhythmia risk indication, the system can generate an alert, or initiate more aggressive monitoring of a patient identified as having a high atrial tachyarrhythmia risk.
1. A system for assessing a cardiac arrhythmia risk of a patient, the system comprising:
an arrhythmia predictor circuit configured to:
receive physiologic information sensed from the patient including two or more of heart sounds (HS) information, thoracic impedance information, or respiration information; and
in an absence of prior and present atrial tachyarrhythmia, determine a composite atrial arrhythmia risk of the patient developing a future atrial tachyarrhythmia, the determination including applying a trained machine-learning model to a plurality of signal metrics obtained from two or more of the HS information, the thoracic impedance information, or the respiration information.
2. The system of claim 1 , wherein the physiologic information does not include electrocardiograph or electrogram information.
3. The system of claim 1 , wherein the determination of the composite atrial arrhythmia risk does not include using a history of atrial tachyarrhythmias in that patient.
4. The system of claim 1 , wherein the arrhythmia predictor circuit is configured to generate a composite signal metric using the plurality of signal metrics, and to generate an indication of arrhythmia risk when the composite signal metric exceeds a threshold or falls within a value range.
5. The system of claim 1 , wherein the received physiologic information includes heart sounds (HS) information.
6. The system of claim 5 , wherein the plurality of signal metrics include one or more HS metrics including:
a first (S1) heart sound intensity;
a third (S3) heart sound intensity; or
a normalized S3 intensity with respect to S1 intensity.
7. The system of claim 1 , wherein the plurality of signal metrics include one or more thoracic impedance metrics or one or more respiration metrics.
8. The system of claim 1 , comprising an output circuit configured to present the composite atrial arrhythmia risk to a user, or to generate an alert according to the composite atrial arrhythmia risk.
9. The system of claim 1 , comprising a therapy circuit configured to generate or adjust a therapy according to the composite atrial arrhythmia risk.
10. The system of claim 1 , wherein the arrhythmia predictor circuit is configured to determine the composite atrial arrhythmia risk further using patient demographic information or patient medical history information.
11. The system of claim 1 , wherein the arrhythmia predictor circuit is configured to, in response to the composite atrial arrhythmia risk satisfying a condition, update the received physiologic information or tune an arrhythmia risk stratification parameter.
12. A method of assessing a cardiac arrhythmia risk of a patient, the method comprising, via an arrhythmia predictor circuit of a medical-device system:
receiving physiologic information sensed from the patient including two or more of heart sounds (HS) information, thoracic impedance information, or respiration information; and
in an absence of prior and present atrial tachyarrhythmia, determining a composite atrial arrhythmia risk of the patient developing a future atrial tachyarrhythmia, the determination including applying a trained machine-learning model to a plurality of signal metrics obtained from two or more of the HS information, the thoracic impedance information, or the respiration information.
13. The method of claim 12 , comprising generate a composite signal metric using the plurality of signal metrics, and generating an indication of arrhythmia risk when the composite signal metric exceeds a threshold or falls within a value range.
14. The method of claim 12 , comprising generating or adjusting a therapy according to the composite atrial arrhythmia risk.
15. The method of claim 12 , wherein determining the composite atrial arrhythmia risk further includes using patient demographic information or patient medical history information.
16. The method of claim 12 , comprising presenting the composite atrial arrhythmia risk to a user, or generating an alert according to the composite atrial arrhythmia risk.
17. The method of claim 12 , comprising updating the received physiologic information or tuning an arrhythmia risk stratification parameter when the composite atrial arrhythmia risk satisfies a condition.
18. The system of claim 1 , wherein the plurality of signal metrics include two or more of a first (S1) heart sound intensity, a third (S3) heart sound intensity, a respiration rate, a rapid-shallow breathing index (RSBI), or a thoracic impedance magnitude.
19. The system of claim 11 , wherein the arrhythmia predictor circuit is configured to, in response to the composite atrial arrhythmia risk exceeds a risk threshold, adjust a parameter to increase a sensitivity for detecting a future atrial tachyarrhythmia event.
20. The method of claim 17 , comprising, in response to the composite atrial arrhythmia risk exceeding a risk threshold, adjusting an arrhythmia detection parameter to increase a sensitivity for detecting a future atrial tachyarrhythmia event.