Contactless sensor-drive device, system, and method enabling assessment of pulse wave velocity
Certain embodiments of the present disclosure relate to a monitoring device that includes a housing, contactless sensors coupled to the housing, and a processing device disposed in the housing. In at least one embodiment, the monitoring device is configured to measure pulse wave velocity in a subject.
1. A method of measuring a pulse wave velocity (PWV) in a subject, the method comprising:
measuring a first pulse profile at a first location of the subject's body by a first contactless sensor, the first location corresponding to the chest of the subject, and the first contactless sensor comprising a radar sensor configured to detect displacement of the chest associated with contraction of the heart to identify a pulse wave source;
measuring a second pulse profile at a second location of the subject's body by a second contactless sensor, the second contactless sensor comprising a remote photoplethysmography (rPPG) enabled camera sensor configured to detect arrival of the pulse wave, wherein the arrival of the pulse wave is detectable in an image of the second location of the subject's body captured by the rPPG enabled camera sensor;
determining a distance between the first location and the second location;
determining a phase difference between the second pulse profile and the first pulse profile; and
computing the PWV based on the distance and phase difference.
2. The method of claim 1 , wherein the second location corresponds to a wrist of the subject.
3. The method of claim 1 , wherein the second location corresponds to the forehead of the subject.
4. The method of claim 1 , wherein the PWV is included with current vital signs of the subject, and wherein the method further comprises:
receiving user input indicative of a health condition of the user; and
determining, based on the user input, whether current vital signs meet baseline vital signs of the subject.
5. The method of claim 4 , further comprising:
training a machine learning model using data input comprising historical sensor data to generate a trained machine learning model, wherein determining whether the current vital signs meet the baseline vital signs comprises providing current sensor data to the trained machine learning model.
6. A pulse wave velocity (PWV) measurement device comprising:
a housing;
a plurality of contactless sensors coupled to the housing, the plurality of contactless sensors comprising a radar sensor and a remote photoplethysmography (rPPG) enabled camera sensor;
a processing device disposed in the housing, the processing device being coupled to the plurality of contactless sensors, wherein the processing device is configured to:
measure a first pulse profile at a first location of the subject's body by a first contactless sensor, the first location corresponding to the chest of the subject, and the first contactless sensor comprising the radar sensor configured to detect displacement of the chest associated with contraction of the heart to identify a pulse wave source;
measure a second pulse profile at a second location of the subject's body by a second contactless sensor, the second contactless sensor comprising the rPPG enabled camera sensor configured to detect arrival of the pulse wave, wherein the arrival of the pulse wave is detectable by the processing device in an image of the second location of the subject's body captured by the rPPG enabled camera sensor;
determine a distance between the first location and the second location;
determine a phase difference between the second pulse profile and the first pulse profile; and
compute the PWV based on the distance and phase difference.
7. The PWV measurement device of claim 6 , wherein the second location corresponds to a wrist of the subject.
8. The PWV measurement device of claim 6 , wherein the second location corresponds to the forehead of the subject.
9. The PWV measurement device of claim 6 , wherein the PWV is included with current vital signs of the subject, and wherein the processing device is further configured to:
receive user input indicative of a health condition of the user; and
determine, based on the user input, whether current vital signs meet baseline vital signs of the subject.
10. A system comprising:
memory; and
a processing device coupled to the memory, wherein the processing device is configured to:
receive a first pulse profile measured at a first location of the subject's body by a first contactless sensor, the first location corresponding to the chest of the subject, and the first contactless sensor comprising a radar sensor configured to detect displacement of the chest associated with contraction of the heart to identify a pulse wave source;
receive a second pulse profile measured at a second location of the subject's body by a second contactless sensor, the second contactless sensor comprising a remote photoplethysmography (rPPG) enabled camera sensor configured to detect arrival of the pulse wave, wherein the arrival of the pulse wave is detectable by the processing device in an image of the second location of the subject's body captured by the rPPG enabled camera sensor;
determine a distance between the first location and the second location;
determine a phase difference between the second pulse profile and the first pulse profile; and
compute a PWV based on the distance and phase difference.
11. The system of claim 10 , wherein the second location corresponds to a wrist of the subject.
12. The system of claim 10 , wherein the second location corresponds to the forehead of the subject.
13. The system of claim 10 , wherein the PWV is included with current vital signs of the subject, and wherein the processing device is further configured to:
receive user input indicative of a health condition of the user; and
determine, based on the user input, whether current vital signs meet baseline vital signs of the subject.
14. The system of claim 13 , wherein the processing device is further configured to:
train a machine learning model using data input comprising historical sensor data to generate a trained machine learning model, wherein determining whether the current vital signs meet the baseline vital signs comprises providing current sensor data to the trained machine learning model.