Determination and monitoring of basal heart rate
A method and system for continuously monitoring basal heart rate are disclosed. The method comprises detecting a plurality of physiological signals of a user and in response to determining that the user is inactive, filtering the plurality of physiological signals to provide a set of data. The method further includes calculating the basal heart rate of the user using the set of data and an algorithmic process. The system includes at least one sensor to detect a plurality of physiological signals of a user, a processor coupled to the at least one sensor, and a memory device coupled to the processor, wherein the memory device includes an application that, when executed by the processor, causes the processor to carry out the steps of the method.
1. A method for continuously monitoring basal heart rate, the method comprising:
receiving, by an external relay, a plurality of physiological signals of a user detected by a wearable device, wherein the physiological signals includes: electrocardiogram (ECG) or photoplethysmogram (PPG) signals, and tri-axial acceleration signals;
calculating, by the external relay, heart rate (HR) values from the electrocardiogram (ECG) or photoplethysmogram (PPG) signals;
calculating, by the external relay, signal magnitude area (SMA) values using one second time windows of band-pass filtered tri-axial body acceleration signals as a sum of the absolute sums of a signal area in 3 axes;
normalizing, by the external relay, the SMA values to determine an activity level of the user;
in response to determining that the user is inactive, calculating, by the external relay, a basal heart rate (BHR) as a function of the calculated HR values and variability of the calculated HR values;
determining, by the external relay, basal heart rate variability from the calculated basal heart rate;
extracting, by a feature extraction module of the external relay, features of the calculated basal heart rate and the basal heart rate variability into blocks comprising a 24-hour variability block, a day-variability block, and a night-variability block,
wherein a time series of a 24-hour duration is utilized for the extraction of the features in the 24-hour variability block,
wherein the time series of the 24-hour duration is split into a day-duration and a bedtime duration,
wherein segmented HR and BHR time series for the day-duration and the bedtime duration are processed separately to derive a feature vector for the day-variability block and a feature vector for the night-variability block, respectively;
inputting, by the external relay, the derived feature vectors in a regression/prediction model module; and
predicting, by the regression/prediction model module, a cardiovascular health risk factor of the user from the inputted derived feature vectors.
2. The method of claim 1 , wherein the calculating the basal heart rate includes calculating a predetermined percentile value from the set of data.
3. The method of claim 2 , wherein the predetermined percentile value is a M th percentile.
4. The method of claim 3 , wherein the predetermined percentile value is the basal heart rate.
5. The method of claim 1 , wherein the calculating the basal heart rate includes calculating the basal heart rate by using a mean (MN) and a standard deviation (SD) of the heart rate values.
6. The method of claim 1 , wherein the wearable device is removably attached to the user.
7. The method of claim 6 , wherein the wearable device comprises:
at least one sensor to detect the plurality of physiological signals;
a processor coupled to the at least one sensor; and
a memory device coupled to the processor, wherein the memory device includes an application.
8. The method of claim 1 , wherein the calculating is automated, continuous, and over a predetermined time period comprising any of 24 hours, 48 hours, and one week.
9. The method of claim 1 , further comprises buffering the set of data and sorting the buffered set of data.
10. The method of claim 1 , further comprising:
utilizing the calculated basal heart rate, wherein utilizing the calculated basal heart rate comprises at least one of determining any of cardiovascular risks, cardiovascular diseases, heart attacks, metabolic disorders, energy expenditure, weight management metrics, athletic training measurements, fitness measurements, endurance, fatigue, acute stress, stress management metrics, core body temperature, hydration levels, therapeutics, sleep quality, relaxation regimes, longevity metrics, and overall health metrics.
11. The method of claim 1 , wherein the calculating the heart rate (HR) values include applying a parametric/nonparametric model based peak detection algorithm to the ECG or PPG signals to detect R wave peaks in the ECG signal or systolic peaks in the PPG signal.
12. A system for continuously monitoring basal heart rate, the system comprising:
a wearable device comprising at least one sensor to detect a plurality of physiological signals of a user, a processor coupled to the at least one sensor, and a memory device coupled to the processor, wherein the memory device includes an application that, when executed by the processor, causes the processor to:
detect a plurality of physiological signals of a user including: electrocardiogram (ECG) or photoplethysmogram (PPG) signals, and tri-axial acceleration signals; and
an external relay that:
receives the plurality of physiological signals from the wearable device;
calculates heart rate (HR) values from the electrocardiogram (ECG) or photoplethysmogram (PPG) signals;
calculates signal magnitude area (SMA) values using one second time windows of band-pass filtered tri-axial body acceleration signals as a sum of the absolute sums of a signal area in 3 axes;
normalizes the SMA values to determine an activity level of the user; and
in response to determining that the user is inactive, calculates a basal heart rate (BHR) as a function of the calculated HR values and variability of the calculated HR values;
determines basal heart rate variability from the calculated basal heart rate;
extracts features of the calculated basal heart rate and the basal heart rate variability into blocks comprising a 24-hour variability block, a day-variability block, and a night-variability block,
wherein a time series of a 24-hour duration is utilized for the extraction of the features in the 24-hour variability block,
wherein the time series of the 24-hour duration is split into a day-duration and a bedtime duration,
wherein segmented HR and BHR time series for the day-duration and the bedtime duration are processed separately to derive a feature vector for the day-variability block and a feature vector for the night-variability block, respectively;
inputs the derived feature vectors in a regression/prediction model module stored in the memory device; and
implements the regression/prediction model module to predict a cardiovascular health risk factor of the user.
13. The system of claim 12 , wherein the external relay calculates a predetermined percentile value from the set of data.
14. The system of claim 13 , wherein the predetermined percentile value is a M th percentile that is the basal heart rate.
15. The system of claim 12 , wherein the external relay calculates the basal heart rate by using a mean (MN) and a standard deviation (SD) of the heart rate values.
16. The system of claim 12 , wherein the basal heart rate calculation is automated, continuous, and over a predetermined time period including at least one of 24 hours, 48 hours, or one week.
17. The system of claim 12 ,
wherein the wearable device is removably attached to the user, and
wherein the plurality of physiological signals include heart rate measurements and activity level measurements.