Assessing effectiveness of CPR
Novel tools and techniques are provided for assessing, predicting and/or effectiveness of cardiopulmonary resuscitation (“CPR”), in some cases, noninvasively. In various embodiments, tools and techniques are provided for implementing rapid estimation of a patient's compensatory reserve index (“CRI”) before, during, and after CPR is performed, and using the CRI and variations in CRI values to determine, in some instances, in real-time, the effectiveness of CPR that is performed.
1. A method for non-invasively determining the effectiveness of cardiopulmonary resuscitation (CPR) on a patient, comprising:
retrieving, by one or more computer systems, physiological data of the patient from one or more sensors monitoring the patient during CPR, wherein the physiological data is waveform data;
transforming, by one or more computer systems, the physiological data from waveform data to one or more patient compensatory serve index (“CRI”) values thereby transforming the waveform data to a numerical value, wherein transforming the physiological data to the one or more patient CRI values includes:
accessing a data store and acquiring a plurality of reference waveforms from a model, wherein each waveform of the plurality of reference waveforms corresponds to a respective CRI value determined from a ratio of intravascular volume loss at time t and intravascular volume loss at hemodynamic decompensation;
comparing the patient waveform data against the plurality of reference waveforms of the model;
determining a similarity between patient waveform data and the plurality of reference waveforms of the model individually; and
determining the one or more patient CRI values that corresponds to the patient waveform data based at least in part on respective similarities of the patient waveform data to each of the plurality of reference waveforms of the model;
based at least in part on the one or more patient CRI values, estimating, by one or more computer systems, an effectiveness of CPR on the patient, wherein the one or more patient CRI values are compared against a CRI model configured to relate changes in CRI values to the effectiveness of CPR on the patient; and
displaying, by one or more computer systems, the effectiveness of CPR on the patient on a user interface.
2. The method of claim 1 , wherein the one or more patient CRI values are estimated based on physiological data that are at least one of received before, received during, or received after CPR.
3. The method of claim 1 , wherein the one or more patient CRI values comprise a plurality of patient CRI values, and wherein estimating effectiveness of a CPR procedure on the patient further is based at least in part on an average value of CRI over a time period or a standard deviation of at least some of the plurality of patient CRI values, a skewness of at least some of the plurality of patient CRI values, a rate of change of at least two of the plurality of patient CRI values, or a difference between two of the plurality of values of CRI.
4. The method of claim 1 , wherein the effectiveness of CPR on the patient is displayed as a number on a scale from 0 to 100.
5. The method of claim 1 , wherein the plurality of reference waveforms of the model correspond to a state of hemodynamic decompensation or near hemodynamic decompensation, or a series of states progressing towards hemodynamic decompensation.
6. The method of claim 1 , wherein determining the similarity further comprises:
producing, for each respective patient waveform of the patient waveform data, a respective similarity coefficient representing a similarity between a respective patient waveform and each of the plurality of reference waveforms of the model;
normalizing the produced, respective similarity coefficients;
summing each respective value of CRI, corresponding to each of the plurality of reference waveforms of the model, respectively weighted by the normalized respective similarity coefficient; and
determining an estimated CRI value for the patient based on the summed, weighted CRI values.
7. The method of claim 1 , 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.
8. The method of claim 1 , wherein the physiological data comprises data representing blood pressure waveforms, plethysmograph waveforms, or photoplethysmograph (PPG) waveforms.
9. The method of claim 1 , wherein the plurality of reference waveforms are generated by inducing a test subject to enter one or more physiological states, and obtaining physiological data from the test subject while the test subject is in a respective physiological state of the one or more physiological states.
10. The method of claim 9 , further comprising:
inducing a physiological state of reduced circulatory system volume in the test subject.
11. The method of claim 10 , wherein inducing the physiological state comprises subjecting the test subject to lower body negative pressure (“LBNP”).
12. The method of claim 11 , wherein inducing the physiological state comprises subjecting the test subject to dehydration.
13. The method of claim 9 , wherein the one or more physiological states comprises a state of cardiovascular collapse or near-cardiovascular collapse.
14. The method of claim 9 , wherein the one or more physiological states comprises a state of euvolemia.
15. The method of claim 9 , wherein the one or more physiological states comprises a state of hypervolemia.
16. The method of claim 9 , wherein the one or more physiological states comprises a state of dehydration or hypovolemia.
17. The method of claim 9 , further comprising correlating the physiological data of the test subject to the respective physiological state, wherein correlating the physiological data of the test subject with the respective physiological state of the test subject further 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 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 .
18. The method of claim 1 , wherein the effectiveness of CPR on the patient is displayed as a qualitative indicator.
19. The method of claim 1 , further including outputting instructions to control a therapeutic device.
20. A system for non-invasively assessing the health of a patient, comprising:
one or more sensors to obtain physiological data from the patient; and
a computer system in communication with the one or more sensors, the computer system comprising:
one or more processors; and
a non-transitory 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 one or more processors to cause the computer system to:
retrieve physiological data of the patient from one or more sensors monitoring the patient, wherein the physiological data is waveform data;
transform the physiological data from waveform data to one or more patient compensatory reserve index (“CRI”) values thereby transforming the waveform data to a numerical value, wherein transforming the physiological data to the one or more patient CRI values includes:
accessing a data store and acquiring a plurality of reference waveforms from a model, wherein each waveform of the plurality of reference waveforms corresponds to a respective CRI value determined from a ratio of intravascular volume loss at time t and intravascular volume loss at hemodynamic decompensation;
comparing the patient waveform data against the plurality of reference waveforms of the model;
determining a similarity between patient waveform data and the plurality of reference waveforms of the model individually; and
determining the one or more patient CRI values that corresponds to the patient waveform data based at least in part on respective similarities of the patient waveform data to each of the plurality of reference waveforms of the model;
based at least in part on the one or more patient CRI values, estimate the health of the patient, wherein the one or more patient CRI values are compared against a CRI model configured to relate changes in CRI values to the health of the patient; and
display the health of the patient on a user interface.
21. The system of claim 20 , wherein the one or more patient CRI values are estimated based on physiological data that are at least one of received before, received during, or received after CPR.
22. The system of claim 20 , wherein the one or more patient CRI values comprise a plurality of patient CRI values, and wherein estimating effectiveness of a CPR procedure on the patient further is based at least in part on an average value of CRI over a time period or a standard deviation of at least some of the plurality of patient CRI values, a skewness of at least some of the plurality of patient CRI values, a rate of change of at least two of the plurality of patient CRI values, or a difference between two of the plurality of values of CRI.
23. The system of claim 20 , further including displaying the effectiveness of CPR on the patient as a number on a scale from 0 to 100.
24. The system of claim 20 , wherein the plurality of reference waveforms of the model correspond to a state of hemodynamic decompensation or near hemodynamic decompensation, or a series of states progressing towards hemodynamic decompensation.
25. The system of claim 20 , wherein determining the similarity between patient waveform data and the plurality of reference waveforms of the model further comprises:
producing, for each respective patient waveform of the patient waveform data, a respective similarity coefficient representing the similarity between a respective patient waveform and each of the plurality of reference waveforms of the model;
normalizing the produced, respective similarity coefficients;
summing each respective value of CRI, corresponding to each of the plurality of reference waveforms of the model, respectively weighted by the normalized respective similarity coefficient; and
determining an estimated CRI value for the patient based on the summed, weighted CRI values.
26. The system of claim 20 , wherein at least one of the one or more sensors is selected from the group comprising 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.
27. The system of claim 20 , wherein the physiological data comprises data representing blood pressure waveforms, plethysmograph waveforms, or photoplethysmograph (PPG) waveforms.
28. The method of claim 20 , wherein the effectiveness of CPR on the patient is displayed as a qualitative indicator.
29. The method of claim 20 , further including outputting instructions to control a therapeutic device.
30. A system for non-invasively determining the effectiveness of cardiopulmonary resuscitation (CPR) on a patient, comprising:
one or more sensors to obtain physiological data from the patient; and
a computer system in communication with the one or more sensors, the computer system comprising:
one or more processors; and
a non-transitory 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 one or more processors to cause the computer system to:
retrieve physiological data of the patient from one or more sensors monitoring the patient during CPR, wherein the physiological data is waveform data;
transform the physiological data from waveform data to one or more patient compensatory reserve index (“CRI”) values thereby transforming the waveform data to a numerical value, wherein transforming the physiological data to the one or more patient CRI values includes:
accessing a data store and acquiring a plurality of reference waveforms from a model, wherein each waveform of the plurality of reference waveforms corresponds to a respective CRI value determined from a ratio of intravascular volume loss at time t and intravascular volume loss at hemodynamic decompensation;
comparing the patient waveform data against the plurality of reference waveforms of the model;
determining a similarity between patient waveform data and the plurality of reference waveforms of the model individually; and
determining the one or more patient CRI values that corresponds to the patient waveform data based at least in part on respective similarities of the patient waveform data to each of the plurality of reference waveforms of the model;
based at least in part on the one or more patient CRI values, estimate an effectiveness of CPR on the patient, wherein the one or more patient CRI values are compared against a CRI model configured to relate changes in CRI values to the effectiveness of CPR on the patient; and
display the effectiveness of CPR on the patient on a user interface.
31. The system of claim 30 , wherein the one or more patient CRI values comprise a plurality of patient CRI values, and wherein estimating effectiveness of a CPR procedure on the patient further is based at least in part on an average value of CRI over a time period or a standard deviation of at least some of the plurality of patient CRI values, a skewness of at least some of the plurality of patient CRI values, a rate of change of at least two of the plurality of patient CRI values, or a difference between two of the plurality of values of CRI.
32. The system of claim 30 , wherein determining the similarity between patient waveform data and the plurality of reference waveforms of the model further comprises:
producing, for each respective patient waveform of the patient waveform data, a respective similarity coefficient representing the similarity between a respective patient waveform and each of the plurality of reference waveforms of the model;
normalizing the produced, respective similarity coefficients;
summing each respective value of CRI, corresponding to each of the plurality of reference waveforms of the model, respectively weighted by the normalized respective similarity coefficient; and
determining an estimated CRI value for the patient based on the summed, weighted CRI values.
33. The system of claim 30 , wherein at least one of the one or more sensors is selected from the group comprising 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.
34. The system of claim 30 , wherein the physiological data comprises data representing blood pressure waveforms, plethysmograph waveforms, or photoplethysmograph (PPG) waveforms.
35. The method of claim 1 , further including outputting a recommended treatment option based on the one or more patient CRI values.