Vital signs monitoring system and method
A vital signs monitoring system includes a peak pattern detection module configured to output a peak prediction signal from sensor signals based on a peak prediction algorithm; a vital sign estimating module configured to estimate a vital sign based on the peak prediction signal; an activity and context detector module configured to output a context signal based on at least one environmental condition and/or activity level of the person; and a concept drift detection module configured to output a drift signal based on drift detected in the estimated vital sign. The peak pattern prediction module is configured to update the peak prediction algorithm based on the context signal and the drift signal.
1. A vital signs monitoring system configured to be worn or carried on a body of a person, the system comprising:
at least one accelerometer configured to detect at least one vital sign parameter in a person and to output sensor signals indicative of the at least one vital sign parameter, the sensor signals having at least two axes; and
a processor configured to:
detect a peak pattern in the sensor signals and output a peak prediction signal according to a peak prediction algorithm, the peak prediction algorithm being configured to detect the peak pattern based on (i) the sensor signals, (ii) a context signal, and (iii) a concept drift signal, using probability density functions of the at least two axes of the sensor signals;
estimate a vital sign based on the peak prediction signal;
receive an input indicating environmental conditions and activity levels of the person;
detect, based on the input, changes in the environmental conditions and the activity levels of the person and output the context signal indicating the changes in the environmental conditions and the activity levels of the person; and
detect drift in the estimated vital sign and output the drift signal indicating the drift, the drift including changes in at least one of (i) the probability density functions of the at least two axes of the sensor signals, (ii) a joint probability of the at least two axes of the sensor signals, and (iii) a distribution of the peak pattern.
2. The system of claim 1 , wherein the drift signal is provided to a sensor calibration system, the sensor calibration system being configured to calibrate the at least one accelerometer based on the drift signal.
3. The system of claim 1 , wherein the processor is configured to receive the input indicating the environmental conditions and the activity levels via a user interface.
4. The system of claim 1 , wherein the vital sign is blood pressure.
5. The system of claim 1 , wherein the at least one accelerometer is configured to detect at least one or more of electrocardiogram (ECG) signal, a first motion signal, a second motion signal, a photoplethysmogram (PPG) signal, seismocardiogram signal (SCG) and ballistocardiogram (BCG) signal.
6. The system of claim 1 , wherein, using the peak prediction algorithm, the processor is configured to identify peaks indicating exact timestamps when the heart of the person contracts and/or when blood rushes through the Aorta of the heart.
7. The system of claim 1 , wherein the processor is configured to detect the drift using a hierarchical linear four rates approach.
8. A method of monitoring vital signs of a person, the method comprising:
detecting at least one vital sign parameter in the person using at least one accelerometer, the at least one vital sign parameter having at least two axes;
generating a peak prediction signal based on the detected vital sign parameter according to a peak prediction algorithm using a processor, the peak prediction algorithm being configured to detect the peak pattern based on (i) the detected vital sign parameter, (ii) a context signal, and (iii) a concept drift signal, using probability density functions of the at least two axes of the detected vital sign parameter;
estimating a vital sign of the person based on the peak prediction signal using the processor;
outputting an estimated vital sign signal;
receiving an input indicating environmental conditions and activity levels of the person;
generating a context signal indicative of changes in the environmental condition and the activity levels of the person detected using the processor; and
generating a drift signal indicative of drift detected in the estimated vital sign signal using the processor, the drift including changes in at least one of (i) the probability density functions of the at least two axes of the sensor signals, (ii) a joint probability of the at least two axes of the sensor signals, and (iii) a distribution of the peak pattern.
9. The method of claim 8 , further comprising:
supplying the drift signal to a sensor calibration system; and
calibrating the at least one accelerometer based on the drift signal.
10. The method of claim 8 , further comprising:
receiving the input indicating the environmental conditions and the activity levels of the person via a user interface.
11. The method of claim 8 , wherein the vital sign is blood pressure.
12. The method of claim 8 , wherein the at least one accelerometer is configured to detect at least one or more of electrocardiogram (ECG) signal, a first motion signal, a second motion signal, a photoplethysmogram (PPG) signal, seismocardiogram signal (SCG) and ballistocardiogram (BCG) signal.
13. The method of claim 8 , wherein the peak prediction algorithm is configured to identify peaks indicating exact timestamps when the heart of the person contracts and/or when blood rushes through the Aorta of the heart.
14. The method of claim 8 , wherein the drift is detected using a hierarchical linear four rates approach.