DATA MINING SYSTEM FOR NONINVASIVE INTRACRANIAL PRESSURE ASSESSMENT

• US 20100049082A1
• Filed: 04/05/2007
• Published: 02/25/2010
• Est. Priority Date: 04/05/2006
• Status: Active Grant

• Current Assignee: Regents of the University of California (University of California)
• Original Assignee: Regents of the University of California (University of California)
• Inventors: Martin, Neil A., Hu, Xiao, Nenov, Valeriy I.
• Granted Patent: US 8,821,408 B2
• Time in Patent Office: Days
• US Class Current: 600/561
• CPC Class Codes: A61B 5/02028 Determining haemodynamic parameters not otherwise provided for, e.g. cardiac contractility or left ventricular ejection fraction
• CPC Class Codes: A61B 5/026 Measuring blood flow A61B3/1233, A61B3/1241 take precedence
• CPC Class Codes: A61B 5/031 Intracranial pressure

Abstract

Systems and methods are described for noninvasively assessing an intracranial pressure of a patient. Some embodiments include providing a simulation model with a measured arterial blood pressure of the patient. Some embodiments further include providing the simulation model with a measured cerebral blood flow velocity of the patient. The simulation model correlates arterial blood pressure values, cerebral blood flow velocity values, and intracranial pressure values. Some embodiments further includes determining an intracranial pressure of the patient based on the simulation model. Some embodiments further includes creating an output data set indicative of the determined intracranial pressure.

Claims

1. A system, for determining an estimated intracranial pressure (ICP) of a first patient, comprising:

a processing module that;

receives a first input based on a first plurality of measurements of a first physiological parameter of the first patient, the first physiological parameter correlating with ICP;

receives a second input based on a second plurality of measurements of a second physiological parameter of the first patient, the second physiological parameter correlating with ICP;

processes the first and second inputs based on an ICP model; and

outputs data indicative of the estimated ICP of the first patient;

wherein the ICP model is chosen from a plurality of potential ICP models, each of the potential ICP models having an associated mapping function that maps values of said first and second physiological parameters to at least one dissimilarity value, each of said at least one dissimilarity value representing a dissimilarity between an estimated ICP value or function and an observed ICP value or function.

2. The system of claim 1, wherein a hemodynamic feature vector comprises said values of, or derived values from, said first and second physiological parameters.

3. The system of claim 1, wherein said ICP model is chosen based on dissimilarity values obtained by:

inputting data indicative of the first patient'"'"'s first plurality of measurements and indicative of the first patient'"'"'s second plurality of measurements into the mapping functions of each of the potential ICP models;

based on the inputted data, outputting a corresponding dissimilarity value for each of the potential ICP models; and

choosing an optimal dissimilarity value from among the corresponding dissimilarity values, based on at least one criterion.

4. The system of claim 3, wherein each of the corresponding dissimilarity values comprises a scalar value.

5. The system of claim 3, wherein a hemodynamic feature vector comprises derived values from said first patient'"'"'s said first plurality of measurements and second plurality of measurements.

6. The system of claim 3, wherein the at least one criterion comprises determining a minimum dissimilarity value from among the corresponding dissimilarity values.

7. The system of claim 3, wherein the at least one criterion comprises determining the maximum-score dissimilarity value from among the corresponding dissimilarity values.

8. The system of claim 3, wherein the dissimilarity value comprises an expression of a cross correlation coefficient between estimated and observed ICP values or vectors.

9. The system of claim 3, wherein the dissimilarity value comprises an expression of a pulsatile component of at least one of said first plurality of measurements and said second plurality of measurements.

10. The system of claim 3, wherein the dissimilarity value comprises an expression of a slow wave component of at least one of said first plurality of measurements and said second plurality of measurements.

11. The system of claim 1, further comprising an output module that is configured to receive the output produced by the processing module.

12. The system of claim 11, wherein said output module comprises an electronic display.

13. The system of claim 11, wherein said output module comprises a printed display.

14. The system of claim 11, wherein the output module comprises an audible display.

15. The system of claim 1, wherein the processing module comprises computer-executable instructions.

16. The system of claim 1, further comprising a storage module that stores data indicative of at least one of said first plurality of measurements and said second plurality of measurements.

17. The system of claim 1, wherein said output comprises data configured to be stored on a computer-readable medium.

18. The system of claim 1, wherein at least one of said first and second physiological parameters comprises a pCO₂.

19. The system of claim 1, wherein at least one of said first and second physiological parameters comprises arterial pO₂.

20. The system of claim 1, wherein at least one of said first and second physiological parameters comprises an arterial blood pressure.

21. The system of claim 1, wherein at least one of said first and second physiological parameters is a cerebral blood flow velocity.

22. The system of claim 1, wherein at least one of said first and second physiological parameters comprises an echocardiographic measurement.

23. The system of claim 1, wherein said observed ICP value or function is obtained from a patient other than said first patient.

24. A system, for determining an estimated value or function of a first physiological parameter of a first patient, comprising:

a processing module that;

receives a first input based on a first plurality of measurements of a second physiological parameter of the first patient, the second physiological parameter correlating with the first physiological parameter;

receives a second input based on a second plurality of measurements of a third physiological parameter of the first patient, the third physiological parameter correlating with the first physiological parameter;

processes the first and second inputs based on a physiological-parameter model; and

outputs data indicative of the estimated first physiological parameter of the first patient;

wherein the physiological-parameter model is chosen from a plurality of potential physiological-parameter models, each of the potential physiological-parameter models having an associated mapping function that maps values of said second and third physiological parameters to at least one dissimilarity value, each of said at least one dissimilarity value representing a dissimilarity between an estimated first-physiological-parameter value or function and an observed first-physiological-parameter value or function.

25. The system of claim 24, wherein the first physiological parameter comprises intracranial pressure (ICP).

26. The system of claim 25, wherein the second physiological parameter comprises cerebral blood flow velocity (CBFV) and the third physiological parameter comprises an arterial blood pressure (ABP).

27. The system of claim 24, wherein the first physiological parameter comprises cerebral blood flow velocity (CBFV).

28. The system of claim 27, wherein the second physiological parameter comprises intracranial pressure (ICP) and the third physiological parameter comprises an arterial blood pressure (ABP).

29. A method, of determining an estimated intracranial pressure (ICP) of a first patient, comprising:

inputting into an ICP model a first plurality of measurements, of a first physiological parameter of the first patient, the first physiological parameter correlating with ICP;

inputting into the ICP model a second plurality of measurements, of a second physiological parameter of the first patient, the second physiological parameter correlating with ICP; and

outputting from the ICP model the estimated ICP of the patient,

wherein the ICP model is chosen from a plurality of potential ICP models, each of the potential ICP models having an associated mapping function that maps values of said first and second physiological parameters to at least one dissimilarity value, each of said at least one dissimilarity value representing a dissimilarity between an estimated ICP value or function and an observed ICP value or function.

30. The method of claim 29, wherein said first plurality of measurements is obtained over time and said second plurality of measurements is obtained over time.

31. The method of claim 29, wherein a hemodynamic feature vector comprises said values of, or derived values from, said first and second physiological parameters.

32. The method of claim 29, wherein said ICP model is chosen based on dissimilarity values obtained by:

inputting the first patient'"'"'s first plurality of measurements and second plurality of measurements into the mapping functions of each of the potential ICP models;

outputting a corresponding dissimilarity value for each of the potential ICP models; and

choosing an optimal dissimilarity value from among the corresponding dissimilarity values, based on at least one criterion.

33. The method of claim 32, wherein a hemodynamic feature vector comprises derived values from said first patient'"'"'s said first plurality of measurements and second plurality of measurements.

34. The method of claim 32, wherein each of the corresponding dissimilarity values comprises a scalar value.

35. The method of claim 32, wherein the at least one criterion comprises determining a minimum dissimilarity value from among the corresponding dissimilarity values.

36. The method of claim 32, wherein the at least one criterion comprises determining a maximum-score dissimilarity value from among the corresponding dissimilarity values.

37. The method of claim 32, wherein the dissimilarity value comprises an expression of a cross correlation coefficient between estimated and observed ICP values or vectors.

38. The method of claim 32, wherein the dissimilarity value comprises an expression of a pulsatile component of at least one of said first plurality of measurements and said second plurality of measurements.

39. The method of claim 32, wherein the dissimilarity value comprises an expression of a slow wave component of at least one of said first plurality of measurements and said second plurality of measurements.

40. The method of claim 29, wherein at least one of said first and second physiological parameters comprises a pCO₂.

41. The method of claim 29, wherein at least one of said first and second physiological parameters comprises an arterial pO₂.

42. The method of claim 29, wherein at least one of said first and second physiological parameters comprises an arterial blood pressure.

43. The method of claim 29, wherein at least one of said first and second physiological parameters is a cerebral blood flow velocity.

44. The method of claim 29, wherein at least one of said first and second physiological parameters comprises an echocardiographic measurement.

45. The method of claim 29, wherein said observed ICP value or function is obtained from a patient other than said first patient.

46. The method of claim 29, wherein a signal comprises at least one of said first plurality of measurements and said second plurality of measurements.

47. The method of claim 46, wherein said signal comprises an electrical signal.

48. A method, of determining an estimated value or function of a first physiological parameter of a first patient, comprising:

inputting into a physiological-parameter model a first plurality of measurements, of a second physiological parameter of the first patient, the second physiological parameter correlating with the first physiological parameter;

inputting into the physiological-parameter model a second plurality of measurements, of a third physiological parameter of the first patient, the third physiological parameter correlating with the first physiological parameter; and

outputting from the physiological-parameter model the estimated value or function of a first physiological parameter of the patient,

wherein the physiological-parameter model is chosen from a plurality of potential physiological-parameter models, each of the potential physiological-parameter models having an associated mapping function that maps values of said second and third physiological parameters to at least one dissimilarity value, each of said at least one dissimilarity value representing a dissimilarity between an estimated first-physiological-parameter value or function and an observed first-physiological-parameter value or function.

49. The method of claim 48, wherein the first physiological parameter comprises intracranial pressure (ICP).

50. The method of claim 49, wherein the second physiological parameter comprises cerebral blood flow velocity (CBFV) and the third physiological parameter comprises an arterial blood pressure (ABP).

51. The method of claim 48, wherein the first physiological parameter comprises cerebral blood flow velocity (CBFV).

52. The method of claim 51, wherein the second physiological parameter comprises intracranial pressure (ICP) and the third physiological parameter comprises an arterial blood pressure (ABP).