Apparatus, system, and method for monitoring physiological signs
An apparatus, system, and method monitors the motion, breathing, heart rate and sleep state of subjects, e.g., humans, in a convenient, non-invasive/non-contact, and low-cost fashion. More particularly, the motion, breathing, and heart rate signals are obtained through processing applied to a raw signal obtained in a non-contact fashion, typically using a radio-frequency sensor. Periods of sleep disturbed respiration, or central apnea can be detected through analysis of the respiratory signal. The mean heart rate, and derived information, such as the presence of cardiac arrhythmias can be determined from the cardiac signal. Motion estimates can be used to recognize disturbed sleep and periodic limb movements. The sleep state may be determined by applying a classifier model to the resulting streams of respiratory, cardiac and motion data. A means for display of the sleep state, respiratory, cardiac, and movement status may also be provided.
1. A system for alerting a subject in sleep, the system comprising:
a first sensor configured to detect a portion of a first output signal reflected from the subject, the first output signal reflected from the subject comprising radio frequency energy generated by a transmitter collocated with the first sensor, the detected portion of the first output signal being processed to obtain a bodily motion signal and a respiratory signal; and
one or more processors configured to:
derive a plurality of statistical features for a first time period and a second time period, the plurality of derived statistical features comprising statistical bodily motion features derived from the bodily motion signal, the plurality of derived statistical features further comprising statistical respiratory features derived from the respiratory signal;
selectively combine two or more of the plurality of derived statistical features to estimate one or more parameters that provide a measure concerning sleep, the one or more parameters comprising a parameter that provides a measure of sleep state;
control emitting output by the system comprising a visual indication, the visual indication comprising an adjustable level of light; and
control emitting further output by the system in response to at least one parameter of the one or more parameters having a predetermined classification, the further output comprising an audible alarm.
2. The system of claim 1 , wherein at least one processor of the one or more processors is collocated with the first sensor in a monitoring unit.
3. The system of claim 2 , wherein the at least one processor controls the emitting of the visual indication based on the parameter that provides the measure of sleep state.
4. The system of claim 2 , wherein the at least one processor is configured to control the emitting of the audible alarm.
5. The system of claim 2 , further comprising auxiliary sensors in the monitoring unit, the auxiliary sensors including one or more of a temperature sensor, a humidity sensor, or a light sensor, and wherein the at least one processor is configured to determine environmental measurements with the auxiliary sensors.
6. The system of claim 1 , wherein the one or more processors are configured to run a classifier model to determine the parameter that provides the measure of sleep state.
7. The system of claim 1 , wherein the one or more processors are configured to run a classifier model and to determine a sleep state by combining motion signals or respiratory signals using the classifier model.
8. The system of claim 1 , wherein the statistical features comprise any one or more of signal variance, spectral components, peak values, power spectral density (PSD) of an event time, standard deviation of event times, serial correlation of event times, count of activities, mean amplitude of activity counts, variance of activity counts, dominant respiratory frequency, respiratory power, respiratory rate, variability of respiratory rate, or a spectrum of the respiratory signal.
9. The system of claim 1 , wherein the two or more of the plurality of derived statistical features comprises at least one of the statistical respiratory features.
10. The system of claim 9 , wherein the one or more processors are further configured to calculate an amplitude of the respiratory signal, and wherein one or more of the statistical respiratory features are derived from the amplitude of the respiratory signal.
11. The system of claim 9 , wherein one or more processors are further configured to determine periodic respiratory patterns by calculating a power spectral density (PSD) of epochs of the respiratory signal and isolating frequency component values in a predetermined frequency band.
12. The system of claim 5 , wherein the one or more processors are further configured to combine at least one environmental parameter with the two or more of the plurality of derived statistical features to estimate a parameter that provides a measure of sleep disturbance.
13. The system of claim 1 , wherein the sleep state comprises at least one of awake, non-REM sleep, or REM sleep.
14. The system of claim 1 , wherein at least one processor of the one or more processors is remote from the first sensor and is configured for wireless communication with the first sensor.
15. The system of claim 14 , wherein the remote at least one processor implements a classifier model that combines the two or more of the plurality of derived statistical features to estimate the one or more parameters.
16. The system of claim 15 , wherein the remote at least one processor is a component of a remote processing and display unit that is connected in wireless communication with the first sensor.
17. The system of claim 16 , further comprising at least one additional sensor that is collocated with the first sensor, wherein the at least one additional sensor comprises at least one of a temperature sensor, a humidity sensor, or a light sensor.
18. The system of claim 1 wherein the visual indication comprises a light emitting diode.
19. A method for alerting a subject in sleep, the method comprising:
detecting, with a sensor, a portion of a first output signal reflected from the subject, the first output signal reflected from the subject comprising radio frequency energy being generated by a transmitter collocated with the sensor, the detected portion of the first output signal being processed to obtain a bodily motion signal and a respiratory signal; and
deriving, with one or more processors, a plurality of statistical features for a first time period and a second time period, the plurality of derived statistical features comprising statistical bodily motion features derived from the bodily motion signal, the plurality of derived statistical features further comprising statistical respiratory features derived from the respiratory signal;
selectively combining, with the one or more processors, two or more of the plurality of derived statistical features to estimate one or more parameters that provide a measure concerning sleep, the one or more parameters comprising a parameter that provides a measure of sleep state;
controlling emitting output comprising a visual indication, the visual indication comprising an adjustable level of light; and
controlling emitting further output in response to at least one parameter of the one or more parameters having a predetermined classification, the further output comprising an audible alarm.
20. A non-transitory computer readable storage medium containing program instructions for causing at least one processing device to perform a method for alerting a subject in sleep, the method comprising:
obtaining a signal reflected from the subject using at least one sensor, the signal reflected from the subject comprising radio frequency energy being generated by a transmitter collocated with the at least one sensor;
processing the obtained signal to obtain a bodily motion signal and a respiratory signal;
deriving a plurality of statistical features for a first time period and a second time period, the plurality of derived statistical features comprising statistical bodily motion features derived from the bodily motion signal, the plurality of derived statistical features further comprising statistical respiratory features derived from the respiratory signal;
selectively combining two or more of the plurality of derived statistical features to estimate one or more parameters that provide a measure concerning sleep, the one or more parameters comprising a parameter that provides a measure of sleep state;
controlling emitting output comprising a visual indication, the visual indication comprising an adjustable level of light; and
controlling emitting further output in response to at least one parameter of the one or more parameters having a predetermined classification, the further output comprising an audible alarm.