Determining reliability for ECG data using signal-to-noise ratio

1. A computer-implemented method for determining reliability of electrocardiogram (ECG) data, comprising:

receiving ECG data comprising waveform data for a patient;

determining an amplitude associated with an R-wave in the waveform data;

identifying a first baseline region in the waveform data and a second baseline region in the waveform data, each relating to the R-wave, comprising:

identifying an R-R interval in the waveform data, and

receiving a fraction of the R-R interval to use in identifying the first baseline region and the second baseline region;

determining a signal-to-noise ratio (SNR) relating to the waveform data, based on the amplitude, the first baseline region, and the second baseline region; and

using the SNR in medical treatment for the patient, wherein the medical treatment comprises: (i) providing instructions to the patient relating to the medical treatment, (ii) providing instructions to a care provider for the patient relating to the medical treatment, (iii) providing notification to the patient relating to a detected heartbeat, or (iv) providing notification to the care provider relating to the detected heartbeat.

2. The computer-implemented method of claim 1 , wherein determining the SNR for the waveform data relating to the waveform data comprises determining a ratio between the amplitude and an average baseline amplitude relating to the first and second baseline regions.

3. The computer-implemented method of claim 2 , wherein the average baseline amplitude relating to the first baseline region comprises a first average amplitude across a first portion of the first baseline region and wherein the average baseline amplitude relating to the second baseline region comprises a second average amplitude across a second portion of the second baseline region.

4. The computer-implemented method of claim 3 , wherein the amplitude is a peak amplitude, and wherein the SNR for the waveform data is determined using the formula SNR=10*log(signal 2 /noise 2 ) where the signal relates to the peak amplitude and where the noise relates to the average baseline amplitude.

5. The computer-implemented method of claim 1 , wherein identifying the first baseline region in the waveform data and the second baseline region in the waveform data further comprises:

determining a first boundary of the first baseline region in the waveform data using the fraction; and

determining a second boundary of the second baseline region in the waveform data using the fraction.

6. The computer-implemented method of claim 5 , wherein the R-wave is associated with a heartbeat, wherein the first baseline region excludes a P wave associated with the heartbeat, and wherein the second baseline region excludes a T wave associated with the heartbeat.

7. The computer-implemented method of claim 1 , further comprising:

determining a confidence metric relating to the waveform data, based on the determined SNR.

8. The computer-implemented method of claim 7 , wherein determining the confidence metric relating to the waveform data, based on the determined SNR, comprises determining at least one of a per-heartbeat confidence metric relating to a heartbeat associated with the R-wave or a per-sample confidence metric relating to a plurality of heartbeats comprising the heartbeat associated with the R-wave.

9. The computer-implemented method of claim 7 , wherein the confidence metric relating to the waveform data relates to confidence in at least one of automated detection or automated classification of a heartbeat.

10. A computer program product for determining reliability of electrocardiogram (ECG) data, the computer program product comprising:

a computer-readable storage medium having computer-readable program code embodied therewith, the computer-readable program code executable by one or more computer processors to perform an operation, the operation comprising:

receiving ECG data comprising waveform data for a patient;

determining an amplitude associated with an R-wave in the waveform data;

identifying a first baseline region in the waveform data and a second baseline region in the waveform data, each relating to the R-wave;

determining a signal-to-noise ratio (SNR) relating to the waveform data, based on the amplitude, the first baseline region, and the second baseline region by determining a ratio between the amplitude and an average baseline amplitude relating to the first and second baseline regions; and

using the SNR in medical treatment for the patient, wherein the medical treatment comprises: (i) providing instructions to the patient relating to the medical treatment, (ii) providing instructions to a care provider for the patient relating to the medical treatment, (iii) providing notification to the patient relating to a detected heartbeat, or (iv) providing notification to the care provider relating to the detected heartbeat.

11. The computer program product of claim 10 , wherein identifying the first baseline region in the waveform data and the second baseline region in the waveform data comprises:

identifying an R-R interval in the waveform data;

receiving a fraction of the R-R interval to use in identifying the first baseline region and the second baseline region;

determining a first boundary of the first baseline region in the waveform data using the fraction; and

determining a second boundary of the second baseline region in the waveform data using the fraction.

12. The computer program product of claim 11 , wherein the R-wave is associated with a heartbeat, wherein the first baseline region excludes a P wave associated with the heartbeat, and wherein the second baseline region excludes a T wave associated with the heartbeat.

13. The computer program product of claim 10 , wherein the average baseline amplitude relating to the first baseline region comprises a first average amplitude across a first portion of the first baseline region and wherein the average baseline amplitude relating to the second baseline region comprises a second average amplitude across a second portion of the second baseline region.

14. A system, comprising:

a processor; and

a memory storing a program, which, when executed on the processor, performs an operation, the operation comprising:

receiving ECG data comprising waveform data for a patient;

determining an amplitude associated with an R-wave in the waveform data;

identifying a first baseline region in the waveform data and a second baseline region in the waveform data, each relating to the R-wave, comprising:

identifying an R-R interval in the waveform data, and

receiving a fraction of the R-R interval to use in identifying the first baseline region and the second baseline region;

determining a signal-to-noise ratio (SNR) relating to the waveform data, based on the amplitude, the first baseline region, and the second baseline region; and

using the SNR in medical treatment for the patient, wherein the medical treatment comprises: (i) providing instructions to the patient relating to the medical treatment, (ii) providing instructions to a care provider for the patient relating to the medical treatment, (iii) providing notification to the patient relating to a detected heartbeat, or (iv) providing notification to the care provider relating to the detected heartbeat.

15. The system of claim 14 , wherein determining the SNR for the waveform data relating to the waveform data comprises determining a ratio between the amplitude and an average baseline amplitude relating to the first and second baseline regions.

16. The system of claim 15 , wherein the amplitude is a peak amplitude and wherein the SNR for the waveform data is determined using the formula SNR=10*log(signal 2 /noise 2 ) where the signal relates to the peak amplitude and where the noise relates to the average baseline amplitude.

17. The system of claim 14 , wherein identifying the first baseline region in the waveform data and the second baseline region in the waveform data comprises:

determining a first boundary of the first baseline region in the waveform data using the fraction; and

determining a second boundary of the second baseline region in the waveform data using the fraction.

18. The system of claim 17 , wherein the R-wave is associated with a heartbeat, wherein the first baseline region excludes a P wave associated with the heartbeat, and wherein the second baseline region excludes a T wave associated with the heartbeat.

19. The system of claim 14 , further comprising:

determining a confidence metric relating to the waveform data, based on the determined SNR.