Detection of atrial fibrillation
Systems, methods, and computer software for detecting atrial fibrillation are described. Photoplethysmographic (PPG) signal data may be received as communicated by a PPG sensor of a wearable device worn by a user. Heartbeats from a portion of the PPG signal data may be determined and a heart rhythm type may be determined based on at least the heartbeats. A determination of whether the heart rhythm type includes Atrial Fibrillation (AF) may be made, and, when AF is detected, an AF detection alert may be displayed at the wearable device.
1. A computer program product,
said computer program product being configured to be in communication with a PPG sensor,
said computer program product comprising a non-transitory, machine-readable medium storing instructions which, when executed by at least one programmable processor, caused at least one programmable processor to perform operations comprising:
receiving photoplethysmographic (PPG) signal data communicated by the PPG sensor of a wearable device worn by a user;
determining a plurality of heartbeats from at least a portion of the PPG signal data;
determining a heart rhythm type based on at least the plurality of heartbeats;
determining whether the heart rhythm type includes Atrial Fibrillation (AF) comprising utilization of an occupancy metric, a distance metric, and an interval variability metric, classifying regions corresponding to particular heart rhythm types as set apart by one or more discrimination planes in a three-dimensional space defined by the occupancy metric, the distance metric, and the interval variability metric, wherein AF is identified on an AF side of at least one of the one or more discrimination planes; and
displaying, when an AF is detected, a detection alert at the wearable device.
2. The computer program product of claim 1 wherein determination of whether the heart rhythm type is AF involves analyzing a point as being on either an AF side or a normal sinus rhythm (NSR) side of an NSR-AF plane.
3. The computer program product of claim 2 wherein the heart rhythm type is determined to be AF when the point is on the AF side of the NSR-AF plane.
4. The computer program product of claim 2 wherein the heart rhythm type is determined to be NSR when the point is on the NSR side of the NSR-AF plane.
5. The computer program product of claim 1 determination of whether the heart rhythm type is AF involves analyzing a point as being on either an AF side or a not AF (NAF) side of an NAF-AF plane.
6. The computer program product of claim 5 wherein the heart rhythm type is determined to be AF when the point is on the AF side of the NAF-AF plane.
7. The computer program product of claim 5 wherein the heart rhythm type is determined to be NAF when the point is on the NAF side of the NAF-AF plane.
8. A computer program product,
said computer program product being configured to be in communication with a PPG sensor,
said computer program product comprising a non-transitory, machine-readable medium storing instructions which, when executed by at least one programmable processor, caused at least one programmable processor to perform operations comprising:
receiving photoplethysmographic (PPG) signal data communicated by the PPG sensor of a wearable device worn by a user;
determining a plurality of heartbeats from at least a portion of the PPG signal data;
determining a heart rhythm type based on at least the plurality of heartbeats;
determining whether the heart rhythm type includes Atrial Fibrillation (AF) comprising utilization of an occupancy metric, a distance metric, and an interval variability metric, classifying regions corresponding to particular heart rhythm types as set apart by at least two discrimination planes in a three-dimensional space defined by the occupancy metric, the distance metric, and the interval variability metric, utilizing at least a two-step analysis via a decision tree; and
displaying, when an AF is detected, a detection alert at the wearable device.
9. The computer program product of claim 8 wherein the decision tree involves first analyzing a point as being on either a not AF (NAF) side or a normal sinus rhythm (NSR) side of an NAF-NSR plane.
10. The computer program product of claim 9 wherein when a point is identified on the NSR side of the NAF-NSR plane, then analyzing whether the point is on an AF side or a NSR side of an NSR-AF plane.
11. The computer program product of claim 10 wherein the heart rhythm type is determined to be AF when the point is on the AF side of the NSR-AF plane.
12. The computer program product of claim 10 wherein the heart rhythm type is determined to be NSR when the point is on the NSR side of the NSR-AF plane.
13. The computer program product of claim 9 wherein when a point is identified on an NAF side of the NAF-NSR plane, then analyzing whether the point is on an AF side or a NAF side of an NAF-AF plane.
14. The computer program product of claim 13 wherein the heart rhythm type is determined to be AF when the point is on the AF side of the NAF-AF plane.
15. The computer program product of claim 13 wherein the heart rhythm type is determined to be NAF when the point is on the NAF side of the NAF-AF plane.