CLIAMS:1. A device (104) for measuring blood pressure of a subject, the device (104) comprising:
a processor (108); and
a blood pressure measurement (BPM) module (126) coupled to the processor (108) to,
obtain a plurality of photoplethysmogram (PPG) features associated with the subject;
ascertain one or more latent parameters associated with the subject based on the plurality of PPG features and a reference model, wherein the reference model indicates a correlation between the plurality of PPG features and the one or more latent parameters; and
determine blood pressure of the subject based on the one or more latent parameters and the plurality of PPG features.
2. The device (104) as claimed in claim 1, wherein the BPM module (126) further is to analyze a PPG waveform associated with the subject for obtaining the plurality of PPG features.
3. The device (104) as claimed in claim 2, wherein each PPG feature from amongst the plurality of PPG features is extracted in one of a time domain and a frequency domain.
4. The device (104) as claimed in claim 1, wherein the one or more latent parameters associated with the subject comprises at least an arterial compliance and a peripheral resistance of the subject.
5. A method for measuring blood pressure of a subject, the method comprising:
obtaining a plurality of photoplethysmogram (PPG) features associated with the subject;
ascertaining one or more latent parameters associated with the subject based on the plurality of PPG features and a reference model, wherein the reference model indicates a correlation between the plurality of PPG features and the one or more latent parameters; and
determining blood pressure of the subject based on the one or more latent parameters and the plurality of PPG features.
6. The method as claimed in claim 5, wherein the one or more latent parameters associated with the subject comprises at least an arterial compliance and a peripheral resistance of the subject.
7. The method as claimed in claim 5, wherein each PPG feature from amongst the plurality of PPG features is extracted in one of a time domain and a frequency domain.
8. A modeling system (102) for measuring blood pressure of a subject, the modeling system comprising:
a processor (108); and
an analysis module (118) coupled to the processor (108) to,
obtain a sample dataset comprising physiological data associated with each of a test subject from amongst a plurality of test subjects, wherein the physiological data comprises at least one ground truth value of blood pressure associated with the test subject and a PPG waveform associated with the test subject;
process, for each of the plurality of test subjects, the physiological data associated with the test subject to obtain a plurality of PPG features;
compute, for each of the plurality of test subjects, one or more latent parameters associated with the test subject based on the plurality of PPG features and the at least one ground truth value; and
determine, based on the one or more latent parameters and the PPG features associated with each of the plurality of test subjects, a reference model for measuring blood pressure of the subject in real time, wherein the reference model indicates a correlation between the one or more latent parameters and the PPG features associated with each of the plurality of test subjects.
9. The modeling system (102) as claimed in claim 8, wherein the analysis module (118) further is to determine the reference model based on a machine learning technique.
10. The modeling system (102) as claimed in claim 8, wherein the analysis module (118) further is to extract the plurality of PPG features from the PPG waveform in one of a time domain and a frequency domain.
11. A method for measuring blood pressure of a subject, the method comprising:
receiving a sample dataset comprising physiological data associated with each of a test subject from amongst a plurality of test subjects, wherein the physiological data comprises at least one ground truth value of blood pressure associated with the test subject and a PPG waveform associated with the test subject;
processing, for each of the plurality of test subjects, the physiological data associated with the test subject to obtain a plurality of PPG features;
computing, for each of the plurality of test subjects, one or more latent parameters associated with the test subject based on the plurality of PPG features and the at least one ground truth value; and
determining, based on the one or more latent parameters and the PPG features associated with each of the plurality of test subjects, a reference model for measuring blood pressure of the subject in real time, wherein the reference model indicates a correlation between the one or more latent parameters and the PPG features associated with each of the plurality of test subjects.
12. The method as claimed in claim 11, wherein the determining the reference model is based on a machine learning technique.
13. The method as claimed in claim 11, wherein the processing comprises extracting the plurality of PPG features from the PPG waveform in one of a time domain and a frequency domain.
14. A non-transitory computer readable medium having a set of computer readable instructions that, when executed, cause a device (104) to:
obtain a plurality of photoplethysmogram (PPG) features associated with the subject;
ascertain one or more latent parameters associated with the subject based on the plurality of PPG features and a reference model, wherein the reference model indicates a correlation between the plurality of PPG features and the one or more latent parameters; and
determine blood pressure of the subject based on the one or more latent parameters and the plurality of PPG features.
,TagSPECI:As Attached