Noninvasive hydration monitoring
Novel tools and techniques for assessing, predicting and/or estimating effectiveness of hydration of a patient and/or an amount of fluid needed for effective hydration of the patient, in some cases, noninvasively.
1. A hydration monitor, comprising:
one or more sensors to obtain physiological data from a patient, wherein the physiological data is cardiovascular data of the patient; and
a computer system in communication with the one or more sensors, the computer system comprising:
one or more processors; and
a computer readable medium in communication with the one or more processors, the computer readable medium having encoded thereon a set of instructions executable by the computer system to cause the computer system to:
receive the physiological data from the one or more sensors;
estimate one or more compensatory reserve index (“CRT”) values by comparing the physiological data to a pre-existing model, the pre-existing model comprising a plurality of waveforms of reference data, each waveform of the plurality of waveforms corresponding to a respective CRT value determined by the following formula:
CRI
(
t
)
=
1
-
BLV
(
t
)
BLV
HDD
where CRI(t) is the compensatory reserve at time t, BLV(t) is an intravascular volume loss of the patient at time t, and BLV HDD is an intravascular volume loss at a point of hemodynamic decompensation of the patient,
wherein the physiological data includes waveform data of the patient, wherein waveform data of the patient includes one or more patient waveforms,
wherein comparing the physiological data against the pre-existing model comprises comparing the waveform data of the patient against the plurality of waveforms of reference data, and determining a similarity between a respective patient waveform of the one or more patient waveforms and each of one or more waveforms of the plurality of waveforms of reference data individually, and
wherein estimating the one or more CRI values of the patient is based, at least in part, on respective similarities of the respective patient waveform to each of the one or more waveforms of the plurality of waveforms of reference data individually;
assess effectiveness of hydration of the patient, wherein the effectiveness of hydration is a numeric value based, at least in part, on the one or more CRI values, wherein the numeric value is related to a respective CRI value of the one or more CRI values by a hydration model relating the hydration effectiveness value to the respective CRI value, wherein the hydration model is generated empirically based on a test population;
display, on a display device, an assessment of the effectiveness of hydration of the patient;
determine, based on the assessment of the effectiveness of hydration of the patient, whether the patient requires further hydration; and
automatically control operation of a therapeutic device based on the assessment of the effectiveness of hydration of the patient and based on a determination that the patient requires further hydration, wherein automatically controlling operation of the therapeutic device comprises at least one of controlling dispensation of a drink from a drink dispenser, controlling an alarm on a drink dispenser, or controlling a drip rate of an intravenous drip.
2. The hydration monitor of claim 1 , further comprising the therapeutic device.
3. The hydration monitor of claim 1 , wherein the one or more sensors comprise a finger cuff comprising a fingertip photoplethysmograph and wherein the computer system comprises a wrist unit in communication with the fingertip photoplethysmograph, the wrist unit further comprising a wrist strap.
4. A method, comprising:
monitoring, with one or more sensors, physiological data of a patient, wherein the physiological data is cardiovascular data of the patient;
estimating one or more compensatory reserve index (“CRT”) values by comparing the physiological data to a pre-existing model, the pre-existing model comprising a plurality of waveforms of reference data, each waveform of the plurality of waveforms corresponding to a respective CRT value determined by the following formula:
CRI
(
t
)
=
1
-
BLV
(
t
)
BLV
HDD
where CRI(t) is the compensatory reserve at time t, BLV(t) is an intravascular volume loss of the patient at time t, and BLV HDD is an intravascular volume loss at a point of hemodynamic decompensation of the patient,
wherein the physiological data includes waveform data of the patient, wherein waveform data of the patient includes one or more patient waveforms,
wherein comparing the physiological data against the pre-existing model comprises comparing the waveform data of the patient against the plurality of waveforms of reference data, and determining a similarity between a respective patient waveform of the one or more patient waveforms and each of one or more waveforms of the plurality of waveforms of reference data individually, and
wherein estimating the one or more CRI values of the patient is based, at least in part, on respective similarities of the respective patient waveform to each of the one or more waveforms of the plurality of waveforms of reference data individually;
assessing effectiveness of hydration of the patient, wherein the effectiveness of hydration is a numeric value based, at least in part, on the one or more CRI values, wherein the numeric value is related to a respective CRI value of the one or more CRI values by a hydration model relating the hydration effectiveness value to the respective CRI value, wherein the hydration model is generated empirically based on a test population;
displaying, on a display device, an assessment of the effectiveness of hydration of the patient;
determining, based on the assessment of the effectiveness of hydration of the patient, whether the patient requires further hydration; and
automatically controlling operation of a therapeutic device based on the assessment of the effectiveness of hydration of the patient and based on a determination that the patient requires further hydration, wherein automatically controlling operation of the therapeutic device comprises at least one of controlling dispensation of a drink from a drink dispenser, controlling an alarm on a drink dispenser, or controlling a drip rate of an intravenous drip.
5. The method of claim 4 , wherein assessing effectiveness of hydration of the patient comprises estimating the effectiveness of hydration of the patient at a current time.
6. The method of claim 4 , wherein assessing effectiveness of hydration of the patient comprises predicting the effectiveness of hydration of the patient at a future time.
7. The method of claim 4 , wherein assessing effectiveness of hydration of the patient comprises estimating an amount of fluid needed for effective hydration of the patient.
8. The method of claim 4 , wherein determining, based on the assessment of the effectiveness of hydration of the patient, whether the patient requires further hydration comprises estimating a probability that the patient requires fluids.
9. The method of claim 4 , wherein the physiological data includes waveform data and the pre-existing model includes one or more sample waveforms, wherein estimating each of the one or more CRI values of the patient comprises comparing the waveform data with the one or more sample waveforms generated by exposing one or more test subjects to a state of hemodynamic decompensation or near hemodynamic decompensation, or a series of states progressing towards hemodynamic decompensation, and monitoring physiological data of the test subjects.
10. The method of claim 4 , wherein determining the similarity between the respective patient waveform and each of the one or more waveforms of the plurality of waveforms of reference data individually further comprises:
producing one or more similarity coefficients, each similarity coefficient of the one or more similarity coefficients expressing a respective similarity between the respective patient waveform and each waveform of the one or more waveforms of the of the plurality of waveforms of reference data individually;
wherein estimating the one or more CRI values of the patient further comprises:
normalizing the one or more similarity coefficients of the one or more waveforms of the plurality of waveforms of reference data;
summing each respective CRI value, corresponding to a respective individual waveform of the one or more waveforms of the plurality of waveforms of reference data, weighted by the normalized similarity coefficient corresponding to the respective individual waveform of the one or more waveforms of the plurality of waveforms of reference data, for each of the one or more waveforms of the plurality of waveforms of reference data; and
determining, for the respective patient waveform, an estimated CRI value for the patient based on the sum of each of the CRI values as weighted by the the normalized similarity coefficients.
11. The method of claim 4 , wherein assessing effectiveness of hydration of a patient comprises assessing effectiveness of hydration of a patient based on a fixed time history of monitoring the physiological data of the patient.
12. The method of claim 4 , wherein assessing effectiveness of hydration of a patient comprises assessing effectiveness of hydration of a patient based on a dynamic time history of monitoring the physiological data of the patient.
13. The method of claim 4 , wherein at least one of the one or more sensors is selected from the group consisting of a blood pressure sensor, an intracranial pressure monitor, a central venous pressure monitoring catheter, an arterial catheter, an electroencephalograph, a cardiac monitor, a transcranial Doppler sensor, a transthoracic impedance plethysmograph, a pulse oximeter, a near infrared spectrometer, a ventilator, an accelerometer, and an electronic stethoscope.
14. The method of claim 4 , wherein the physiological data comprises blood pressure waveform data.
15. The method of claim 4 , wherein the physiological data comprises plethysmograph waveform data.
16. The method of claim 4 , wherein the physiological data comprises photoplethysmograph (PPG) waveform data.
17. The method of claim 4 , further comprising:
generating the pre-existing model.
18. The method of claim 17 , wherein the plurality of waveforms of reference data is generated by inducing one or more test subjects to enter one or more physiological states, and obtaining physiological data from one or more test subjects while the one or more test subjects is in a respective physiological state of the one or more physiological states.
19. The method of claim 18 , further comprising correlating the physiological data of the test subject to the respective physiological state, wherein correlating the physiological data of the one or more test subjects with the physiological state of the test subject comprises:
identifying a most predictive set of signals S k out of a set of signals s 1 , s 2 , . . . , s D for each of one or more outcomes o k , wherein the most-predictive set of signals S k corresponds to a first data set representing a first physiological parameter of the physiological data of the one or more test subjects, and wherein each of the one or more outcomes o k represents a physiological state measurement of the one or more physiological states respectively;
autonomously learning a set of probabilistic predictive models ô k =M K (S K ), where ô k is a prediction of outcome o k derived from a model M k that uses as inputs values obtained from the set of signals S k ; and
repeating the operation of autonomously learning incrementally from data that contains examples of values of signals s 1 , s 2 , . . . , s D and corresponding outcomes o 1 , o 2 , . . . , o K .
20. An apparatus, comprising:
a non-transitory computer readable medium having encoded thereon a set of instructions executable by one or more computers to cause the apparatus to:
receive physiological data from one or more sensors;
analyze the physiological data against a pre-existing model;
estimate one or more compensatory reserve index (“CRI”) values by comparing the physiological data to the pre-existing model, the pre-existing model comprising a plurality of waveforms of reference data, each waveform of the plurality of waveforms corresponding to a respective CRI value determined by the following formula:
CRI
(
t
)
=
1
-
BLV
(
t
)
BLV
HDD
where CRI(t) is the compensatory reserve at time t, BLV(t) is an intravascular volume loss of a test subject at time t, and BLV HDD is an intravascular volume loss at a point of hemodynamic decompensation of the test subject,
wherein the physiological data includes waveform data of the patient, wherein waveform data of the patient includes one or more patient waveforms,
wherein comparing the physiological data against the pre-existing model comprises comparing the waveform data of the patient against the plurality of waveforms of reference data, and determining a similarity between a respective patient waveform of the one or more patient waveforms and each of one or more waveforms of the plurality of waveforms of reference data individually, and
wherein estimating the one or more CRI values of the patient is based, at least in part, on respective similarities of the respective patient waveform to each of the one or more waveforms of the plurality of waveforms of reference data individually;
assess effectiveness of hydration of the patient based at least in part on the one or more CRI values, wherein the effectiveness of hydration is a numeric value that is related to a respective CRI value of the one or more CRI values by a hydration model relating the hydration effectiveness value to the respective CRI value, wherein the hydration model relating the hydration effectiveness value to the respective CRI value is generated empirically based on a test population;
display, on a display device, an assessment of the effectiveness of hydration of the patient;
determine, based on the assessment of the effectiveness of hydration of the patient, whether the patient requires further hydration; and
automatically control operation of a therapeutic device based on the assessment of the effectiveness of hydration of the patient and based on a determination that the patient requires further hydration, wherein automatically controlling operation of the therapeutic device comprises at least one of controlling dispensation of a drink from a drink dispenser, controlling an alarm on a drink dispenser, or controlling a drip rate of an intravenous drip.
21. The method of claim 4 , wherein assessing effectiveness of hydration of the patient comprises estimating the effectiveness of hydration of the patient at a current time and predicting the effectiveness of hydration of the patient at a future time, the method further comprising:
estimating a probability that the patient requires fluids;
estimating a first amount of fluid needed for effective hydration of the patient at the current time; and
predicting a second amount of fluid needed for effective hydration of the patient at the future time.
22. The method of claim 4 , wherein the operations of monitoring physiological data of the patient, analyzing the physiological data against the pre-existing model, assessing effectiveness of hydration of the patient based at least in part on the one or more CRI values, displaying the assessment of the effectiveness of hydration of the patient, determining whether the patient requires further hydration, and automatically controlling operation of the therapeutic device based on the assessment of the effectiveness of hydration of the patient and based on a determination that the patient requires further hydration are automatically repeated iteratively.