Wearable Device Including PPG and Inertial Sensors for Assessing Physical Activity and Biometric Parameters
A wearable device collects a plurality of photoplethysmography (PPG) waveforms from a PPG sensor in the wearable device and collects inertial data associated with subject motion from an inertial sensor in the wearable device. The wearable device processes the inertial data in an assessment processor of the wearable device to determine a data integrity of the plurality of PPG waveforms and, responsive to the determined data integrity, processes the plurality of PPG waveforms in the assessment processor using a neural network comprising thousands of coefficients to generate an assessment of the subject blood pressure.
1 . A wearable device configured to assess subject blood pressure, the wearable device comprising:
a photoplethysmography (PPG) sensor;
an inertial sensor configured to sense subject motion; and
an assessment processor operatively connected to the PPG sensor and the inertial sensor, the assessment processor being configured to:
process inertial signals output by the inertial sensor to determine a data integrity of a plurality of PPG waveforms output by the PPG sensor; and
responsive to the determined data integrity, process the plurality of PPG waveforms using a neural network comprising thousands of coefficients to generate an assessment of the subject blood pressure.
2 . The wearable device of claim 1 , wherein the assessment processor is further configured to change a polling of the PPG sensor responsive to the assessment processor detecting a steady subject cadence from the inertial signals output by the inertial sensor and/or a steady subject heart rate from the PPG waveforms output by the PPG sensor.
3 . The wearable device of claim 2 , wherein:
the assessment processor is further configured to create a spline for each of the plurality of PPG waveforms; and
the assessment processor is configured to generate the plurality of representations of the plurality of PPG waveforms from the splines.
4 . The wearable device of claim 1 , wherein:
the assessment processor is further configured to buffer the plurality of PPG waveforms and generate a plurality of representations of the plurality of PPG waveforms; and
to process the plurality of PPG waveforms, the assessment processor is configured to process the plurality of representations of the plurality of PPG waveforms using the neural network comprising thousands of coefficients to generate the assessment of the subject blood pressure.
5 . The wearable device of claim 4 , wherein to generate at least one of the plurality of representations, the assessment processor is configured to compute a derivative of at least one of the splines of the plurality of PPG waveforms.
6 . The wearable device of claim 4 , wherein to generate at least one of the plurality of representations, the assessment processor is configured to compute an integral of at least one of the splines of the plurality of PPG waveforms.
7 . The wearable device of claim 4 , wherein at least one of the plurality of representations comprises a spectral representation of at least one of the PPG waveforms.
8 . The wearable device of claim 1 , wherein:
the assessment processor is further configured to determine a spectral representation of at least one of the PPG waveforms; and
to process the plurality of PPG waveforms, the assessment processor is configured to, responsive to the determined data integrity, process the spectral representation using the neural network to generate the assessment of the subject blood pressure.
9 . The wearable device of claim 1 , wherein the assessment processor is further configured to change a sampling rate of the PPG sensor responsive to the assessment processor detecting a steady subject cadence from the inertial signals output by the inertial sensor and/or detecting a steady subject heart rate from the PPG waveforms output by the PPG sensor.
10 . The wearable device of claim 1 , wherein the wearable device comprises a device worn at the wrist, arm, leg, digits, nose, head, neck, or torso.
11 . A method of assessing subject blood pressure via wearable device, the method comprising:
collecting a plurality of photoplethysmography (PPG) waveforms from a PPG sensor in the wearable device;
collecting inertial data associated with subject motion from an inertial sensor in the wearable device;
process the inertial data in an assessment processor operatively connected to the PPG sensor and the inertial sensor to determine a data integrity of the plurality of PPG waveforms; and
responsive to the determined data integrity, processing the plurality of PPG waveforms in the assessment processor using a neural network comprising thousands of coefficients to generate an assessment of the subject blood pressure.
12 . The method of claim 11 , further comprising changing, by the assessment processor, a polling of the PPG sensor responsive to the assessment processor detecting a steady subject cadence from the inertial data and/or of a steady subject heart rate from the plurality of PPG waveforms.
13 . The method of claim 12 , further comprising creating, by the assessment processor, a spline for each of the plurality of PPG waveforms, wherein the generating the plurality of representations of the plurality of PPG waveforms comprises generating the plurality of representations of the plurality of PPG waveforms from the splines.
14 . The method of claim 11 , further comprising the assessment processor:
buffering the plurality of PPG waveforms; and
generating a plurality of representations of the plurality of PPG waveforms;
wherein the processing of the plurality of PPG waveforms comprises processing, by the assessment processor, the plurality of representations of the plurality of PPG waveforms using the neural network comprising thousands of coefficients to generate the assessment of the subject blood pressure.
15 . The method of claim 14 , wherein the generating the plurality of representations comprises computing a derivative of at least one of the splines of the plurality of PPG waveforms to generate at least one of the plurality of representations.
16 . The method of claim 14 , wherein the generating the plurality of representations comprises computing an integral of at least one of the splines of the plurality of PPG waveforms to generate at least one of the plurality of representations.
17 . The method of claim 14 , wherein at least one of the plurality of representations comprises a spectral representation of at least one of the plurality of PPG waveforms.
18 . The method of claim 11 , further comprising determining a spectral representation of at least one of the PPG waveforms, wherein the processing of the plurality of PPG waveforms comprises, responsive to the determined data integrity, processing in the assessment processor the spectral representation using the neural network to generate the assessment of the subject blood pressure.
19 . The method of claim 11 , further comprising the assessment processor changing a sampling rate of the PPG sensor responsive to the assessment processor detecting a steady subject cadence from the inertial signals output by the inertial sensor and/or detecting a steady subject heart rate from the PPG waveforms output by the PPG sensor.
20 . The method of claim 11 , wherein:
the wearable device comprises a device worn at the wrist, arm, leg, digits, nose, head, neck, or torso; and
the collecting of the plurality of PPG waveforms comprises collecting the plurality of PPG waveforms from the wrist, arm, leg, digits, nose, head, neck, or torso of the subject.