Continuous detection and monitoring of heart arrhythmia using both wearable sensors and cloud-resident analyses
Systems and methods are provided for continuously monitoring a user to determine when cardiovascular events are likely occurring and to responsively provide a prompt to a user to engage in additional physiological assessment of the putative cardiovascular event. Additional assessment can include the user engaging an additional sensor to provide signals that are more accurate, lower noise, or otherwise improved relative to a continuously-monitoring sensor used to initially detect the cardiovascular event. Detection of cardiovascular events includes using a cardiovascular classifier to determine, based on the output of such a continuously-monitoring sensor, whether the event is likely occurring. Such a classifier can be received from a cloud computing service or other remote system based on sensor outputs sent to such a system. Use of such a classifier can facilitate reduced false-positive detection of cardiovascular events based on the continuously-monitoring sensor, and thus reduce extraneous prompts to the user.
1. A wearable device, comprising:
a housing, wherein the housing is mountable to an external body surface of a wearer;
a first electrical contact disposed on the housing, wherein the first electrical contact contacts the external body surface when the housing is mounted on the external body surface;
a second electrical contact;
a sensor;
a user interface;
a transceiver; and
a controller, wherein the controller comprises a computing device programmed to perform operations comprising:
detecting, using the sensor during a first period of time, a first signal;
transmitting, using the transceiver, an indication of the first signal to a remote server;
detecting, using the sensor during a second period of time, a second signal;
using a cardiovascular classifier stored in the controller to determine that the second signal is indicative of a cardiovascular event, wherein the cardiovascular classifier is based on the first signal;
responsive to determining that the second signal is indicative of the cardiovascular event, using the user interface to provide a prompt; and
after using the user interface to provide the prompt, detecting an electrocardiographic waveform from voltage fluctuations between the first electrical contact and the second electrical contact.
2. The wearable device of claim 1 , wherein the external body surface is a wrist location of a first arm of a wearer, and wherein the second electrical contact is configured to be contacted by skin of an external body surface of a second arm of the wearer.
3. The wearable device of claim 2 , further comprising a modular mount, wherein the modular mount comprises a band and a frame, wherein the housing is configured to be removably seated in the frame, wherein the band is configured to encircle a wrist of the first arm of the wearer, and wherein the second electrical contact is disposed on an outside surface of the modular mount.
4. The device of claim 1 , further comprising a further sensor, and wherein the operations further comprise:
detecting, using the further sensor during the first period of time, a third signal;
transmitting, using the transceiver, an indication of the third signal to the remote server, wherein the cardiovascular classifier is based on the first signal and the third signal; and
detecting, using the further sensor during the second period of time, a fourth signal, wherein using the cardiovascular classifier to determine that the second signal is indicative of a cardiovascular event comprises using the cardiovascular classifier to determine, based on the second signal and the fourth signal, that the second signal is indicative of a cardiovascular event.
5. The device of claim 4 , wherein using the cardiovascular classifier to determine, based on the second signal and the fourth signal, that the second signal is indicative of a cardiovascular event comprises:
determining, based on the fourth signal, a particular activity of the user during the second period of time; and
using the cardiovascular classifier to determine, based on the second signal and the determined particular activity of the user during the second period of time, that the second signal is indicative of a cardiovascular event.
6. The device of claim 5 , wherein the sensor comprises a photoplethysmographic sensor, and wherein the further sensor comprises at least one of an accelerometer or a gyroscope.
7. The device of claim 1 , wherein the sensor comprises at least one of an accelerometer or a gyroscope.
8. The device of claim 1 , wherein the sensor comprises a photoplethysmographic sensor.
9. The device of claim 1 , wherein the operations further comprise:
detecting that the first and second electrical contacts are in contact with skin, wherein detecting an electrocardiographic waveform from voltage fluctuations between the first electrical contact and the second electrical contact is performed responsive to detecting that the first and second electrical contacts are in contact with skin.
10. The device of claim 1 , wherein the operations further comprise:
determining, based on the detected electrocardiographic waveform, that the cardiovascular event is occurring; and
responsive to determining that the cardiovascular event is occurring, using the user interface to provide an indication of the cardiovascular event.
11. The device of claim 1 , wherein the operations further comprise:
transmitting, using the transceiver, an indication of the detected electrocardiographic waveform to the remote server.
12. The device of claim 1 , wherein the operations further comprise:
detecting, using the sensor during a third period of time, a third signal;
transmitting, using the transceiver, an indication of the third signal to a remote server;
detecting, using the sensor during a fourth period of time, a fourth signal;
using an updated cardiovascular classifier stored in the controller to determine that the fourth signal is indicative of a further cardiovascular event, wherein the updated cardiovascular classifier is based on the first signal and the third signal;
responsive to determining that the fourth signal is indicative of the further cardiovascular event, using the user interface to provide a further prompt; and
after using the user interface to provide the further prompt, detecting a further electrocardiographic waveform from voltage fluctuations between the first electrical contact and the second electrical contact.
13. A method comprising:
detecting, using a sensor of a wearable device during a first period of time, a first signal, wherein the wearable device further comprises:
a housing, wherein the housing is mountable to an external body surface of a wearer;
a first electrical contact disposed on the housing, wherein the first electrical contact contacts the external body surface when the housing is mounted on the external body surface;
a second electrical contact;
a user interface; and
a transceiver;
transmitting, using the transceiver, an indication of the first signal to a remote server;
detecting, using the sensor during a second period of time, a second signal;
using a cardiovascular classifier stored in the wearable device to determine that the second signal is indicative of a cardiovascular event, wherein the cardiovascular classifier is based on the first signal;
responsive to determining that the second signal is indicative of the cardiovascular event, using the user interface to provide a prompt; and
after using the user interface to provide the prompt, detecting an electrocardiographic waveform from voltage fluctuations between the first electrical contact and the second electrical contact.
14. The method of claim 13 , wherein the external body surface is a wrist location of a first arm of a wearer, and wherein the second electrical contact is configured to be contacted by skin of an external body surface of a second arm of the wearer.
15. The method of claim 13 , wherein the wearable device further comprises a further sensor, and wherein the method further comprises:
detecting, using the further sensor during the first period of time, a third signal;
transmitting, using the transceiver, an indication of the third signal to the remote server, wherein the cardiovascular classifier is based on the first signal and the third signal; and
detecting, using the further sensor during the second period of time, a fourth signal, wherein using the cardiovascular classifier to determine that the second signal is indicative of a cardiovascular event comprises using the cardiovascular classifier to determine, based on the second signal and the fourth signal, that the second signal is indicative of a cardiovascular event.
16. The method of claim 15 , wherein using the cardiovascular classifier to determine, based on the second signal and the fourth signal, that the second signal is indicative of a cardiovascular event comprises:
determining, based on the fourth signal, a particular activity of the user during the second period of time; and
using the cardiovascular classifier to determine, based on the second signal and the determined particular activity of the user during the second period of time, that the second signal is indicative of a cardiovascular event.
17. The method of claim 16 , wherein the sensor comprises a photoplethysmographic sensor, and wherein the further sensor comprises at least one of an accelerometer or a gyroscope.
18. The method of claim 13 , wherein the sensor comprises at least one of an accelerometer or a gyroscope.
19. The method of claim 13 , wherein the sensor comprises a photoplethysmographic sensor.
20. The method of claim 13 , further comprising:
detecting that the first and second electrical contacts are in contact with skin, wherein detecting an electrocardiographic waveform from voltage fluctuations between the first electrical contact and the second electrical contact is performed responsive to detecting that the first and second electrical contacts are in contact with skin.