Continuous monitoring of a user's health with a mobile device
Disclosed herein are devices, systems, methods and platforms for continuously monitoring the health status of a user, for example the cardiac health status. The present disclosure describes systems, methods, devices, software, and platforms for continuously monitoring a user's health-indicator data (for example and without limitation PPG signals, heart rate or blood pressure) from a user-device in combination with corresponding (in time) data related to factors that may impact the health-indicator (“other-factors”) to determine whether a user has normal health as judged by or compared to, for example and not by way of limitation, either (i) a group of individuals impacted by similar other-factors, or (ii) the user him/herself impacted by similar other-factors.
1. A smart watch to detect the presence of an abnormal health-indicator of a user, comprising:
a processing device;
a photoplethysmography (“PPG”) sensor operatively coupled to the processing device;
a motion sensor operatively coupled to the processing device; and
a memory operatively coupled with the processing device, the memory having instructions stored thereon that, when executed by the processing device, cause the processing device to:
receive a raw PPG waveform signal from the PPG sensor;
receive motion sensor data from the motions sensor;
input the raw PPG waveform signal into a machine learning algorithm trained to detect whether the user's health-indicator data is abnormal;
detect, by the machine learning algorithm, that the user's health-indicator data is abnormal; and
generate a notification of the detected abnormal health-indicator data.
2. The smart watch according to claim 1 , wherein the processing device is further configured to:
generate a heartrate waveform signal based on the raw PPG waveform; and
input the heartrate waveform signal into the machine learning algorithm with the raw PPG waveform signal.
3. The smart watch according to claim 1 , wherein the processing device is further configured to:
extract a heartrate variability (“HRV”) signal from the raw PPG waveform; and
input the HRV waveform signal with the raw PPG waveform into the machine learning algorithm.
4. The smart watch according to claim 1 , wherein the processing device is further configured to:
extract a one or more features from the raw PPG waveform signal; and
input the one or more features with the raw PPG waveform into the machine learning algorithm.
5. The smart watch according to claim 1 , further comprising an ECG sensor coupled to the processing device, wherein the processing device is further configured to record an ECG using the ECG sensor in response to detection of the presence of the abnormal health-indicator data.
6. The smart watch according to claim 1 , further comprising an ECO sensor coupled to the processing device, wherein the processing device is further configured to notify the user of the detected abnormal health-indicator and to record an ECG using the ECG sensor.
7. The smart watch according to claim 1 , wherein the abnormal health-indicator data is an indication of an arrhythmia.
8. A method to detect a health-indicator of a user, comprising:
receiving, by a processing device, a heart rate variability (HRV) signal from a PPG sensor;
inputting, by the processing device, the HRV signal into a machine learning algorithm trained to detect whether the user's health-indicator data is abnormal;
detecting, by the machine learning algorithm, that the user's health-indicator data is abnormal; and
generating a notification of the detected abnormal health-indicator data.
9. The method according to claim 8 , further comprising:
generating a heartrate signal based on a raw PPG waveform signal from the PPG sensor; and
inputting the heartrate waveform signal into the machine learning algorithm with the raw PPG waveform signal.
10. The method according to claim 8 , further comprising:
extracting a one or more features from a raw PPG waveform signal from the PPG sensor; and
inputting the one or more features with the raw PPG waveform into the machine learning algorithm.
11. The method according to claim 8 , further comprising recording an ECG using an ECG sensor in response to detection of the presence of the abnormal health-indicator data.
12. The method according to claim 8 , further comprising:
receiving a motion signal from the motion sensor, and
inputting the motion signal into the machine learning algorithm trained to detect abnormal health-indicator data.
13. The method according to claim 8 , further comprising notifying the user of the predicted abnormal health-indicator and to record an ECG using the ECG sensor.
14. The method according to claim 8 , wherein the abnormal health-indicator data is an indication of an arrhythmia.
15. A non-transitory computer-readable storage medium including instructions that, when executed by a processing device, cause the processing device to:
receive a raw photoplethysmography (“PPG”) waveform signal from a PPG sensor;
receive motion sensor data from a motion sensor
input the raw PPG waveform signal into a machine learning algorithm trained to detect whether the user's health-indicator data is abnormal;
detect, by the machine learning algorithm, that the user's health-indicator data is abnormal; and
generate a notification of the detected abnormal health-indicator data.
16. The non-transitory computer-readable storage medium of claim 15 , wherein the instructions further cause the processing device to:
generate a heartrate waveform signal based on the raw PPG waveform signal; and
input the heartrate waveform signal into the machine learning algorithm with the raw PPG waveform signal.
17. The non-transitory computer-readable storage medium of claim 15 , wherein the instructions further cause the processing device to:
extract a heartrate variability (“HRV”) signal from the raw PPG waveform signal; and
input the HRV waveform signal with the raw PPG waveform signal into the machine learning algorithm.
18. The non-transitory computer-readable storage medium of claim 15 , wherein the instructions further cause the processing device to record an ECG using a ECG sensor in response to detection of the presence of the arrhythmia.
19. The non-transitory computer-readable storage medium of claim 15 , wherein the instructions further cause the processing device to notify the user of the predicted arrhythmia and to record an ECG using an ECG sensor.
20. The non-transitory computer-readable storage medium of claim 15 , wherein to input the motion sensor data into the machine learning algorithm, the instructions further cause the processing device to generate an activity level signal based on the motion sensor data.