Blood pressure monitoring via in-ear device
An in-ear device (IED) of a wearable system captures audio data from within the ear canal of a user indicative of the user's heartbeat. The IED when worn occludes the user's ear canal, causing amplification of low frequency sounds due to the occlusion effect, and improving the ability of the acoustic sensor to detect the user's heartbeat sounds. The wearable system classifies the audio data to identify portions of the audio data corresponding to a first heart sound and a second heart sound, which correspond to different portions of the heartbeat of the user. The wearable system estimates a blood pressure level of the user based upon the identified heart sounds.
1 . A system comprising:
an in-ear device configured to be placed within an ear canal of a user, the in-ear device including:
an acoustic sensor configured to generate an audio signal from detected sounds within the ear canal of the user when the in-ear device is worn by the user, wherein the detected sounds are indicative of a heartbeat of the user; and
a controller configured to:
classify portions of the audio signal to identify a first heart sound and a second heart sound;
determine a ratio of an acoustic intensity of the first heart sound to an intensity of the second heart sound; and
estimate blood pressure of the user by using the acoustic intensity ratio derived from the audio signal as a predictive input to the blood pressure estimation.
2 . The system of claim 1 , wherein the controller is further configured to:
classify portions of the audio signal to identify at least a first heart sound and a second heart sound corresponding to different portions of the heartbeat of the user; and
estimate the blood pressure of the user based in part on the first heart sound and the second heart sound.
3 . The system of claim 2 , wherein the first heart sound corresponds to an onset of ventricular contraction, and the second heart sound corresponds to an end of ventricular systole and a beginning of ventricular relaxation.
4 . The system of claim 2 , wherein the acoustic sensor is configured to detect infrasounds.
5 . The system of claim 2 , wherein the controller is further configured to estimate the blood pressure of the user based upon a time delay between an onset of the first heart sound and an onset of the second heart sound.
6 . The system of claim 1 , wherein the controller is further configured to:
classify portions of the audio signal to identify at least a first heart sound and a second heart sound corresponding to different portions of the heartbeat of the user;
convert information corresponding to the second heart sound to a frequency domain to obtain spectral content of the second heart sound; and
analyze spectral content of the second sound in the frequency domain to estimate the blood pressure of the user.
7 . The system of claim 1 , wherein the in-ear device is configured to occlude the ear canal of the user.
8 . The system of claim 1 , wherein the controller is further configure to calibrate estimation of the blood pressure level of the user based upon a received blood pressure level measurement performed by a separate medical device.
9 . The system of claim 1 , wherein the controller is further configured to:
classify portions of the audio signal to identify at least a first heart sound and a second heart sound corresponding to different portions of the heartbeat of the user;
receive electrocardiogram (ECG) data of the user;
identify, from the received ECG data, an R-wave peak of the ECG data;
determine a time delay between the R-wave peak and an onset of the second heart sound; and
estimate the blood pressure of the user based on the determined time delay.
10 . The system of claim 9 , wherein:
the in-ear device further comprises:
at least one in-ear electrode configured to contact an inner surface of a user's ear when the in-ear device is worn by the user, and
wherein the controller is further configured to:
capture electrical signals corresponding to a heartbeat of the user at the at least one in-ear electrode; and
generate the ECG data based upon the captured electrical signals.
11 . The system of claim 1 , wherein at least a portion of the controller is located in the in-ear device.
12 . The system of claim 1 , wherein the controller is located in a headset.
13 . A method comprising:
receiving, from an in-ear device placed within an ear canal of a user, an audio signal based upon sounds detected within the ear canal of the user by an acoustic sensor of the in-ear device, wherein the detected sounds are indicative of a heartbeat of the user;
classifying portions of the audio signal to identify at least a first heart sound and a second heart sound corresponding to different portions of the heartbeat of the user;
determining a ratio of an acoustic intensity of the first heart sound to an intensity of the second heart sound; and
estimating blood pressure of the user by using the acoustic intensity ratio derived from the first heart sound or the second heart sound as a predictive input to the blood pressure estimation.
14 . The method of claim 13 , wherein the first heart sound corresponds to an onset of ventricular contraction, and the second heart sound corresponds to an end of ventricular systole and a beginning of ventricular relaxation.
15 . The method of claim 13 , wherein the acoustic sensor is configured to detect sound infrasounds.
16 . The method of claim 13 , wherein estimating blood pressure of the user comprises estimating the blood pressure of the user based upon a time delay between an onset of the first heart sound and an onset of the second heart sound.
17 . The method of claim 13 , further comprising:
classifying portions of the audio signal to identify at least a first heart sound and a second heart sound corresponding to different portions of the heartbeat of the user;
converting information corresponding to the second heart sound to a frequency domain to obtain spectral content of the second heart sound; and
analyzing spectral content of the second sound in the frequency domain to estimate the blood pressure of the user.
18 . The method of claim 13 , further comprising:
receiving electrocardiogram (ECG) data of the user;
identifying, from the received ECG data, an R-wave peak of the ECG data; and
determining a time delay between the R-wave peak and an onset of the second heart sound,
wherein estimating the blood pressure of the user based on the determined time delay.
19 . A non-transitory computer readable medium having a computer-executable program stored thereon, the program comprising instructions that, when executed by one or more processors of a device, cause the device to:
receive, from an in-ear device placed within an ear canal of a user, an audio signal based upon sounds detected within the ear canal of the user by an acoustic sensor of the in-ear device, wherein the detected sounds are indicative of a heartbeat of the user;
classify portions of the audio signal to identify at least a first heart sound and a second heart sound corresponding to different portions of the heartbeat of the user;
determine a ratio of an intensity of the first heart sound to an acoustic intensity of the second heart sound; and
estimate blood pressure of the user by using the acoustic intensity ratio derived from the first heart sound or the second heart sound as a predictive input to the blood pressure estimation.
20 . The non-transitory computer readable medium of claim 19 , wherein the instructions further cause the device to:
receive electrocardiogram (ECG) data of the user;
identify, from the received ECG data, an R-wave peak of the ECG data;
determine a time delay between the R-wave peak and an onset of the second heart sound; and
estimate the blood pressure based on the determined time delay.
21 . The system of claim 1 , wherein estimating the blood pressure further comprises estimating the blood pressure based on the acoustic intensity ratio of the first and second heart sounds, the blood pressure level having a positive correlation with the acoustic intensity ratio.
22 . The method of claim 13 , wherein estimating the blood pressure further comprises estimating the blood pressure based on the acoustic intensity ratio of the first and second heart sounds, the blood pressure level having a positive correlation with the acoustic intensity ratio.