Estimating physiological states based on changes in CRI
Novel tools and techniques are provided for assessing, predicting and/or estimating a physiological state of a patient, based on variance of the patient's compensatory reserve index (“CRI”) before, during, and/or after a physical perturbation. In some embodiments, the system might receive a first set of physiological data from one or more sensors at a first time relative to a physical perturbation of the patient, and might calculate a first set of CRI values of the patient. The system might receive a second set of physiological data at a second time relative to the physical perturbation, calculate a second set of CRI values, analyze the two sets of CRI values against a pre-existing model, estimate a physiological state (e.g., hydration, etc.) of the patient, and display the estimate on a display device. The system might also control an infusion device to infuse fluids into the patient based on estimated hydration state.
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 that, when executed by the one or more processors, causes the computer system to:
receive a first set of physiological data from the one or more sensors at a first time in relation to a physical perturbation of the patient;
calculate a first set of compensatory reserve index (“CRI”) values of the patient based on a comparison of the first set of physiological data to a model comprising a plurality of waveforms of reference data, each waveform of the plurality of waveforms corresponding to a respective CRI value determined from a ratio of intravascular volume loss at time t and intravascular volume loss at hemodynamic decompensation,
wherein the first set of physiological data includes waveform data of the patient at the first time, wherein waveform data of the patient at the first time includes one or more first patient waveforms,
wherein comparing the first set of physiological data against the model comprises comparing the waveform data of the patient against the plurality of waveforms of reference data, and determining a similarity between a respective first patient waveform of the one or more first patient waveforms and each of one or more waveforms of the plurality of waveforms of reference data individually, and
wherein calculating a respective first CRI value of the first set of CRI values of the patient corresponding to the respective first patient waveform is based at least in part on respective similarities of the respective first patient waveform to each of the one or more waveforms of the plurality of waveforms of reference data individually;
receive a second set of physiological data from the one or more sensors at a second time in relation to the physical perturbation of the patient;
calculate a second set of CRI values of the patient based on a comparison of the second set of physiological data to the model, wherein the second set of physiological data includes waveform data of the patient at the second time;
based at least in part on a change between the first and second sets of CRI values, estimate a hydration state of the patient, wherein the change between the first and second sets of CRI values is compared against a CRI model separate from the model comprising the plurality of waveforms of reference data, wherein the CRI model relates changes in CRI value to the hydration state of the patient; and
display on a display device, an estimate of the hydration state of the patient.
2. 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.
3. The hydration monitor of claim 1 , wherein estimating a hydration state of the patient comprises determining whether the patient needs more fluids.
4. The hydration monitor of claim 3 , wherein determining whether the patient needs more fluids comprises determining whether the patient has an increase in fluid requirements.
5. The hydration monitor of claim 3 , wherein determining whether the patient needs more fluids comprises estimating how much fluid is needed, based at least in part on how much fluid the patient has received between the first time and the second time in relation to the physical perturbation of the patient.
6. A method, comprising:
monitoring, with one or more sensors, physiological data of a patient, wherein the physiological data is cardiovascular data of the patient;
receiving a first set of physiological data from the one or more sensors at a first time in relation to a physical perturbation of the patient;
calculating a first set of compensatory reserve index (“CRI”) values of the patient based on a comparison of the first set of physiological data to a model comprising a plurality of waveforms of reference data, each waveform of the plurality of waveforms corresponding to a respective CRI value determined from a ratio of intravascular volume loss at time t and intravascular volume loss at hemodynamic decompensation,
wherein the first set of physiological data includes waveform data of the patient at the first time, wherein waveform data of the patient at the first time includes one or more first patient waveforms,
wherein comparing the first set of physiological data against the model comprises comparing the waveform data of the patient against the plurality of waveforms of reference data, and determining a similarity between a respective first patient waveform of the one or more first patient waveforms and each of one or more waveforms of the plurality of waveforms of reference data individually, and
wherein calculating a respective first CRI value of the first set of CRI values of the patient corresponding to the respective first patient waveform is based at least in part on respective similarities of the respective first patient waveform to each of the one or more waveforms of the plurality of waveforms of reference data individually;
receiving a second set of physiological data from the one or more sensors at a second time in relation to the physical perturbation of the patient;
calculating a second set of CRI values of the patient based on a comparison of the second set of physiological data to the model, wherein the second set of physiological data includes waveform data of the patient at the second time;
based at least in part on a change between the first and second sets of CRI values, estimating a physiological state of the patient, wherein the change between the first and second sets of CRI values is compared against a CRI model separate from the model comprising the plurality of waveforms of reference data,
wherein the CRI model relates changes in CRI value to the physiological state of the patient; and
displaying on a display device, an estimate of the physiological state of the patient.
7. The method of claim 6 , wherein the physical perturbation of the patient comprises performance of an exercise.
8. The method of claim 7 , wherein the exercise comprises a squat exercise.
9. The method of claim 7 , wherein the exercise comprises a sit-up exercise.
10. The method of claim 6 , wherein the physical perturbation comprises delivery of fluid to the patient.
11. The method of claim 6 , wherein the physical perturbation comprises introduction of positive or negative pressure to an airway of the patient.
12. The method of claim 6 , wherein the physiological state is a hydration state of the patient.
13. The method of claim 6 , wherein the physiological state is an estimated point of cardiovascular collapse of the patient.
14. The method of claim 6 , wherein the ratio of intravascular volume loss at time t and intravascular volume loss at hemodynamic decompensation is determined by the following formula:
CRI
(
t
)
=
1
-
BLV
(
t
)
BLV
HDD
,
where CRI(t) is the compensatory reserve index at time t, BLV(t) is an intravascular volume loss of the patient at time t, and BLV HDD is an intravascular volume loss of the patient at a point of hemodynamic decompensation.
15. The method of claim 14 , wherein the physiological data comprises waveform data, and wherein estimating a set of CRI values of the patient comprises comparing the waveform data with one or more sample waveforms generated by exposing each of one or more test subjects to a state of hemodynamic decompensation or near hemodynamic decompensation or to a series of states progressing towards hemodynamic decompensation, and monitoring physiological data of the test subjects.
16. The method of claim 14 , wherein determining the similarity between the respective first 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 first patient waveform and each of the one or more waveforms of the plurality of waveforms of reference data individually;
wherein estimating the respective first CRI value of the patient corresponding to the respective first patient waveform further comprises:
normalizing each of the one or more similarity coefficients for each of the one or more waveforms of the plurality of waveforms of reference data; and
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 first patient waveform, an estimated respective first CRI value for the patient.
17. The method of claim 6 , wherein at least one of the one or more sensors comprises at least one 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, or an electronic stethoscope.
18. The method of claim 6 , wherein the physiological data comprises blood pressure waveform data.
19. The method of claim 6 , wherein the physiological data comprises plethysmograph waveform data.
20. The method of claim 6 , wherein the physiological data comprises photoplethysmograph (“PPG”) waveform data.
21. The method of claim 6 , further comprising:
generating the model comprising the plurality of waveforms of reference data.
22. The method of claim 6 , wherein generating the model comprising the plurality of waveforms of reference data further comprises:
receiving data pertaining to one or more physiological parameters of a test subject to obtain a plurality of physiological data sets;
directly measuring one or more physiological states of the test subject with a reference sensor to obtain a plurality of physiological state measurements; and
correlating the received data with the physiological state measurements of the test subject.
23. The method of claim 22 , wherein the one or more physiological states comprises one or more states comprising at least one of reduced circulatory system volume, blood loss, added fluids to blood volume, dehydration, hydration state, cardiovascular collapse, near-cardiovascular collapse, euvolemia, or hypervolemia.
24. The method of claim 22 , wherein correlating the received data with the physiological state measurements 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 test subject, 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 most predictive 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 .
25. The method of claim 6 , wherein estimating a physiological state of the patient comprises estimating a hydration state of the patient and determining whether the patient needs more fluids.
26. The method of claim 25 , wherein determining whether the patient needs more fluids comprises determining whether the patient has an increase in fluid requirements.
27. The method of claim 25 , wherein determining whether the patient needs more fluids comprises estimating how much fluid is needed, based at least in part on how much fluid the patient has received between the first time and the second time in relation to the physical perturbation of the patient.
28. An apparatus, comprising:
a non-transitory computer readable medium having encoded thereon a set of instructions executable by one or more computers to:
receive a first set of physiological data from one or more sensors at a first time in relation to a physical perturbation of a patient, the one or more sensors monitoring physiological data of the patient, wherein the physiological data is cardiovascular data of the patient;
calculate a first set of compensatory reserve index (“CRI”) values of the patient based on a comparison of the first set of physiological data to a model comprising a plurality of waveforms of reference data, each waveform of the plurality of waveforms corresponding to a respective CRI value determined from a ratio of intravascular volume loss at time t and intravascular volume loss at hemodynamic decompensation,
wherein the first set of physiological data includes waveform data of the patient at the first time, wherein waveform data of the patient at the first time includes one or more first patient waveforms,
wherein comparing the first set of physiological data against the model comprises comparing the waveform data of the patient against the plurality of waveforms of reference data, and determining a similarity between a respective first patient waveform of the one or more first patient waveforms and each of one or more waveforms of the plurality of waveforms of reference data individually, and
wherein calculating a respective first CRI value of the first set of CRI values of the patient corresponding to the respective first patient waveform is based at least in part on respective similarities of the respective first patient waveform to each of the one or more waveforms of the plurality of waveforms of reference data individually;
receive a second set of physiological data from the one or more sensors at a second time in relation to the physical perturbation of the patient;
calculate a second set of CRI values of the patient based on a comparison of the second set of physiological data to the model, wherein the second set of physiological data includes waveform data of the patient at the second time;
based at least in part on a change between the first and second sets of CRI values, estimate a physiological state of the patient, wherein the change between the first and second sets of CRI values is compared against a CRI model separate from the model comprising the plurality of waveforms of reference data, wherein the CRI model relates changes in CRI value to the physiological state of the patient; and
display on a display device, an estimate of the physiological state of the patient.
29. A system, comprising:
a processor; and
a non-transitory computer readable medium having encoded thereon a set of instructions that, when executed by the processor, causes the system to:
receive a first set of physiological data from one or more sensors at a first time in relation to a physical perturbation of a patient, the one or more sensors monitoring physiological data of the patient, wherein the physiological data is cardiovascular data of the patient;
calculate a first set of compensatory reserve index (“CRI”) values of the patient based on a comparison of the first set of physiological data to a model comprising a plurality of waveforms of reference data, each waveform of the plurality of waveforms corresponding to a respective CRI value determined from a ratio of intravascular volume loss at time t and intravascular volume loss at hemodynamic decompensation,
wherein the first set of physiological data includes waveform data of the patient at the first time, wherein waveform data of the patient at the first time includes one or more first patient waveforms,
wherein comparing the first set of physiological data against the model comprises comparing the waveform data of the patient against the plurality of waveforms of reference data, and determining a similarity between a respective first patient waveform of the one or more first patient waveforms and each of one or more waveforms of the plurality of waveforms of reference data individually, and
wherein calculating a respective first CRI value of the first set of CRI values of the patient corresponding to the respective first patient waveform is based at least in part on respective similarities of the respective first patient waveform to each of the one or more waveforms of the plurality of waveforms of reference data individually;
receive a second set of physiological data from the one or more sensors at a second time in relation to the physical perturbation of the patient;
calculate a second set of CRI values of the patient based on a comparison of the second set of physiological data to the model, wherein the second set of physiological data includes waveform data of the patient at the second time;
based at least in part on a change between the first and second sets of CRI values, estimate a physiological state of the patient, wherein the change between the first and second sets of CRI values is compared against a CRI model separate from the model comprising the plurality of waveforms of reference data, wherein the CRI model relates changes in CRI value to the physiological state of the patient; and
display on a display device, an estimate of the physiological state of the patient.