Systems and methods for risk stratification of patient populations

• US 7,853,456 B2
• Filed: 03/04/2005
• Issued: 12/14/2010
• Est. Priority Date: 03/05/2004
• Status: Active Grant

• Current Assignee: Terumo Medical Corporation (Terumo Corporation)
• Original Assignee: Health Outcomes Sciences, LLC
• Inventors: Spertus, John Albert, Soto, Gabriel Enrique
• Primary Examiner(s): Morgan; Robert W
• Assistant Examiner(s): HUNTER, SEAN KRISTOPHER
• Application Number:
  US11/072,053
• Publication Number:
  US 20050203773A1
• Time in Patent Office: 2,111 Days
• Field of Search: 705/2, 705/3, 705/4
• US Class Current: 705/2
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06Q 40/08 Insurance
• CPC Class Codes: G16H 10/20 for electronic clinical trials or questionnaires
• CPC Class Codes: G16H 15/00 ICT specially adapted for medical reports, e.g. generation or transmission thereof
• CPC Class Codes: G16H 40/67 for remote operation
• CPC Class Codes: G16H 50/30 for calculating health indices; for individual health risk assessment
• CPC Class Codes: G16H 50/50 for simulation or modelling of medical disorders
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

A statistical processing system includes a server operably configured with program instructions implementing a plurality of statistical models to at least one of (a) predict a health outcome based on questionnaire responses, (b) assist a patient'"'"'s choice of therapeutic modality based on questionnaire responses, and (c) assess a health risk or status based on questionnaire responses. Also provided is a research agency communicating with the server and contracted to provide the statistical models using a visual interface communicated by the server. The server is configured to analyze requests received from users relating to a plurality of said statistical models to reduce redundancy in requests for patient data.

Claims

1. A method of utilizing a statistical health model, the method comprising:

storing in computer readable memory associated with a statistical health model translation system a first plurality of statistical health models from respective sources in a plurality of different sources,

wherein at least one statistical health model in the first plurality of statistical health models from the respective sources is a medical prognostic risk stratification model and/or a medical prognostic outcomes prediction model in the form of at least one of a;

linear model,

a generalized linear model,

a cumulative multinomial model,

a generalized multinomial model,

a proportional hazard model;

providing via the statistical health model translation system one or more user interfaces including a plurality of fields that enable one or more users to specify for the at least one statistical health model;

an outcome predicted by the at least one statistical health model;

one or more outcome predictors;

a mathematical relationship between;

the outcome predicted by the at least one statistical health model, and

the one or more outcome predictors;

providing via the statistical health model translation system one or more user interfaces that enable one or more users to select models from the first plurality of statistical health models for execution;

receiving a user selection of one or more of the first plurality of statistical health models;

automatically generating data-input interfaces for collecting patient-specific predictors utilized when executing the selected one or more of the first plurality of statistical health models based at least in part on the one or more outcome predictors;

processing, via a computing device, the one or more outcome predictors and information regarding a patient received via the automatically generated data-input interfaces, where the information received via the automatically generated data-input interfaces includes one or more patient medical conditions, using the selected one or more of the first plurality of statistical health models; and

providing, via the computing device, an output from the selected one or more of the first plurality of statistical health models.

2. The method of claim 1, the method further comprising providing via the statistical health model translation system a user interface including a plurality of fields configured to:

receive one or more predictor coefficients; and

receive one or more predictor coefficient covariances for calculating confidence intervals.

3. The method of claim 1, wherein the first plurality of statistical health models includes a statistical health model configured to determine a statistical outcome of a medical procedure, medical treatment or intervention, and/or medical condition with respect to the patient.

4. The method of claim 3, wherein at least one outcome includes risks associated with genetic factors or biochemical factors.

5. The method of claim 1, the method further comprising:

receiving an update to a first statistical health model of the first plurality of statistical health models from the source entity; and

storing the update in computer readable memory associated with a statistical health model translation system.

6. The method of claim 1, wherein the first plurality of statistical health models includes a statistical health model of the form:

f(x)=β

0+β

1X1+β

2X2+β

3X3+β

nXn.

7. The method of claim 1, wherein the first plurality of statistical health models includes a statistical health model that is non-linear.

8. The method of claim 1, wherein the first plurality of statistical health models includes one or more outome predictor transforms, wherein a first of the one or more outome predictor transforms is an identity, inverse, square root, power, polynomial, exponential, logarithm, or mapping transformation.

9. The method of claim 1, the method further comprising converting at least one of the one or more statistical health model predictors into a predictor vector.

10. The method of claim 1, the method further comprising providing a web service via which a patient population database is passed through at least a first selected plurality of the first plurality of statistical health models to project disease prevalences, treatment costs, and/or resource requirements.

11. The method of claim 1, wherein the one or more user interfaces that enable one or more users to select models from the first plurality of statistical health models for execution further comprises a control via which the user can initiate the execution of all of the selected models.

12. The method of claim 1, the method further comprising:

contracting with a research agency to provide a first statistical health model to the statistical health model translation system;

contracting with a hospital to provide the hospital with access to the first statistical health model;

storing in computer readable the first statistical health model of the contracted research agency; and

electronically providing the contracted hospital with access to the first statistical health model.

13. The method of claim 1, the method further comprising providing access to a first statistical health model of the first plurality of statistical health models to a hospital.

14. The method of claim 1, the method further comprising providing reformatted results obtained via the statistical health model embedded in a format that is customized, wherein the customization is based at least in part upon which end user is to receive the results.

15. The method of claim 1, the method further comprising transmitting over a network a first output from the statistical health model to a first medical entity using a first letterhead and second output from the statistical health model to a second medical entity using a second letterhead.

16. The method of claim 1, the method further comprising providing a first output from a first statistical health model of the first plurality of statistical health models to a first medical entity in a format as an informed consent agreement, wherein the informed consent agreement is formatted based at least in part on the identity of the first medical entity.

17. The method of claim 1, wherein a first statistical health model of the first plurality of statistical health models is configured to perform at least one of the following:

predict a health outcome based on questionnaire responses,

assist a patient'"'"'s choice of therapeutic modality based on questionnaire responses,

assess a health risk or status based on questionnaire responses.

18. The method of claim 1, the method further comprising providing structured lists of parameters and default values to a remote system.

19. The method of claim 1, the method further comprising obtaining values of coefficients for a first statistical health model of the first plurality of statistical health models.

20. The method of claim 1, the method further comprising receiving default values of model parameters.

21. The method of claim 1, the method further comprising transmitting to a remote client a response including HTML, WML, or XML formatting, including lists of the model parameters and default values.

22. The method of claim 1, the method further comprising transmitting to the remote system information concerning selected courses of action with respect to treating a medical condition and corresponding resulting outcomes.

23. The method of claim 1, the method further comprising receiving from the remote system patient risk assessments using health query responses and health parameter data.

24. The method of claim 1, the method further comprising providing for display a user interface configured to receive information regarding the patient and the patient medical condition(s).

25. The method of claim 1, the method further comprising providing a programmatic interface to receive information regarding the patient and one or more patient medical conditions.

26. The method of claim 1, the method further comprising providing via the statistical health model translation system one or more user interfaces that enable one or more users to specify via a plurality of defined fields:

one or more limits and/or lists of possible input values for the one or more outcome predictors; and

one or more transforms for the one or more statistical health model predictors.

27. The method of claim 1, the method further comprising providing, via the computing device, an output from a first statistical health model of the first plurality of statistical health models for display and/or returning an output from the first statistical health model of the first plurality of statistical health models via a programmatic interface.

69. The method of claim 1, wherein the plurality of sources includes a plurality of servers associated with one or more research agencies and wherein the first plurality of statistical health models are received electronically.

70. The method of claim 1, wherein the selected one or more of the first plurality of statistical health models includes a plurality of selected models, the method further comprising:

providing for display the results of the execution of the plurality of selected models, wherein the results of the execution of the plurality of selected models are displayed at the same time via a first output user interface;

descriptively identifying the plurality of selected models via the first output user interface; and

identifying the specified outcome that the plurality of selected models are predicting.

71. The method of claim 1, wherein the selected one or more of the first plurality of statistical health models includes a model that is linear in transformed variables.

28. A tangible computer-readable medium having computer-executable instructions stored thereon that, if executed by a computing device, cause the computing device to perform a method comprising:

storing in computer readable memory associated with a statistical health model translation system a first plurality of statistical health models from respective sources in a plurality of different sources,

wherein at least one statistical health model in the first plurality of statistical health models from the respective sources is a medical prognostic risk stratification model and/or a medical prognostic outcomes prediction model in the form of at least one of a;

linear model,

a generalized linear model,

a cumulative multinomial model,

a generalized multinomial model,

a proportional hazard model;

providing via the statistical health model translation system one or more user interfaces including a plurality of fields that enable one or more users to specify for the at least one statistical health model;

an outcome predicted by the at least one statistical health model;

one or more outcome predictors;

a mathematical relationship between;

the outcome predicted by the at least one statistical health model, and

the one or more outcome predictors;

providing via the statistical health model translation system one or more user interfaces that enable one or more users to select models from the first plurality of statistical health models for execution;

receiving a user selection of one or more of the first plurality of statistical health models;

automatically generating data-input interfaces for collecting patient-specific predictors utilized when executing the selected one or more of the first plurality of statistical health models based at least in part on the one or more outcome predictors;

processing, via a computing device, the one or more outcome predictors and information regarding a patient received via the automatically generated data-input interfaces, where the information received via the automatically generated data-input interfaces includes one or more patient medical conditions, using the selected one or more of the first plurality of statistical health models; and

providing, via the computing device, an output from the selected one or more of the first plurality of statistical health models.

29. The tangible computer-readable medium of claim 28, the method further comprising providing via the statistical health model translation system a user interface including a plurality of fields configured to:

receive one or more predictor coefficients; and

receive one or more predictor coefficient covariances for calculating confidence intervals.

30. The tangible computer-readable medium of claim 28, wherein the first plurality of statistical health models includes the statistical health model is configured to determine a statistical outcome of a medical procedure, medical treatment or intervention, and/or medical condition with respect to the patient.

31. The tangible computer-readable medium of claim 30, wherein at least one outcome includes risks associated with genetic factors or biochemical factors.

32. The tangible computer-readable medium of claim 28, the method further comprising:

receiving an update to a first statistical model of the first plurality of statistical health models from the source entity; and

storing the update in computer readable memory associated with a statistical health model translation system.

33. The tangible computer-readable medium of claim 28, wherein the first plurality of statistical health models includes a statistical health model of the form:

f(x)=β

0+β

1X1+β

2X2+β

3X3+β

bXn.

34. The tangible computer-readable medium of claim 28, wherein the first plurality of statistical health models includes a statistical health model that is non-linear.

35. The tangible computer-readable medium of claim 28, wherein the first plurality of statistical health models includes one or more outome predictor transforms, wherein a first of the one or more outome predictor transforms is an identity, inverse, square root, power, polynomial, exponential, logarithm, or mapping transformation.

36. The tangible computer-readable medium of claim 28, the method further comprising converting the one or more statistical health model predictors into a predictor vector.

37. The tangible computer-readable medium of claim 28, the method further comprising providing a web service via which a patient population database is passed through the statistical health model to project disease prevalences, treatment costs, and/or resource requirements.

38. The tangible computer-readable medium of claim 28, wherein the one or more user interfaces that enable one or more users to select models from the first plurality of statistical health models for execution further comprises a control via which the user can initiate the execution of all of the selected models.

39. The tangible computer-readable medium of claim 28, the method further comprising:

contracting with a research agency to provide a first statistical health model to the statistical health model translation system;

contracting with a hospital to provide the hospital with access to the first statistical health model;

storing in computer readable the first statistical health model of the contracted research agency; and

electronically providing the contracted hospital with access to the first statistical health model.

40. The tangible computer-readable medium of claim 28, the method further comprising providing access to a first statistical health model of the first plurality of statistical health models to a hospital.

41. The tangible computer-readable medium of claim 28, the method further comprising providing reformatted results obtained via the statistical health model embedded in a format that is customized, wherein the customization is based at least in part upon which end user is to receive the results.

42. The tangible computer-readable medium of claim 28, the method further comprising transmitting over a network a first output from the statistical health model to a first medical entity using a first letterhead and second output from the statistical health model to a second medical entity using a second letterhead.

43. The tangible computer-readable medium of claim 28, the method further comprising providing a first output from a first statistical health model of the first plurality of statistical health models to a first medical entity in a format as an informed consent agreement, wherein the informed consent agreement is formatted based at least in part on the identity of the first medical entity.

44. The tangible computer-readable medium of claim 28, wherein a first statistical health model of the first plurality of statistical health models is configured to perform at least one of the following:

predict a health outcome based on questionnaire responses,

assist a patient'"'"'s choice of therapeutic modality based on questionnaire responses,

assess a health risk or status based on questionnaire responses.

45. The tangible computer-readable medium of claim 28, the method further comprising providing structured lists of parameters and default values to a remote system.

46. The tangible computer-readable medium of claim 28, the method further comprising obtaining values of coefficients for a first statistical health model of the first plurality of statistical health models.

47. The tangible computer-readable medium of claim 28, the method further comprising receiving default values of model parameters.

48. The tangible computer-readable medium of claim 28, the method further comprising transmitting to a remote client a response including HTML, WML, or XML formatting, including lists of the model parameters and default values.

49. The tangible computer-readable medium of claim 28, the method further comprising transmitting to the remote system information concerning selected courses of action with respect to treating a medical condition and corresponding resulting outcomes.

50. The tangible computer-readable medium of claim 28, the method further comprising receiving from the remote system patient risk assessments using health query responses and health parameter data.

51. The tangible computer-readable medium of claim 28, the method further comprising providing for display a user interface configured to receive information regarding the patient and the patient medical condition(s).

52. The tangible computer-readable medium of claim 28, the method further comprising providing a programmatic interface to receive information regarding the patient and one or more patient medical conditions.

53. The tangible computer-readable medium of claim 28, the method further comprising providing via the statistical health model translation system one or more user interfaces that enable one or more users to specify via a plurality of defined fields:

one or more limits and/or lists of possible input values for the one or more outcome predictors; and

one or more transforms for the one or more statistical health model predictors.

54. The tangible computer-readable medium of claim 28, the method further comprising providing, via the computing device, an output from a first statistical health model of the first plurality of statistical health models for display and/or returning an output from the first statistical health model of the first plurality of statistical health models via a programmatic interface.

55. A system, comprising:

a computing device;

tangible computer-readable medium having computer-executable instructions stored thereon that, if executed by a computing device, cause the computing device to perform a method comprising;

storing in computer readable memory associated with a statistical health model translation system a first plurality of statistical health models from respective sources in a plurality of different sources,

wherein at least one statistical health model in the first plurality of statistical health models from the respective sources is a medical prognostic risk stratification model and/or a medical prognostic outcomes prediction model in the form of at least one of a;

linear model,

a generalized linear model,

a cumulative multinomial model,

a generalized multinomial model,

a proportional hazard model;

providing via the statistical health model translation system one or more user interfaces including a plurality of fields that enable one or more users to specify for the at least one statistical health model;

an outcome predicted by the at least one statistical health model;

one or more outcome predictors;

a mathematical relationship between;

the outcome predicted by the at least one statistical health model, and

the one or more outcome predictors;

providing via the statistical health model translation system one or more user interfaces that enable one or more users to select models from the first plurality of statistical health models for execution;

receiving a user selection of one or more of the first plurality of statistical health models;

automatically generating data-input interfaces for collecting patient-specific predictors utilized when executing the selected one or more of the first plurality of statistical health models based at least in part on the one or more outcome predictors;

processing, via a computing device, the one or more outcome predictors and information regarding a patient received via the automatically generated data-input interfaces, where the information received via the automatically generated data-input interfaces includes one or more patient medical conditions using the selected one or more of the first plurality of statistical health models; and

providing, via the computing device, an output from the selected one or more of the first plurality of statistical health models.

56. The system of claim 55, the method further comprising providing via the statistical health model translation system a user interface including a plurality of fields configured to:

receive one or more predictor coefficients; and

receive one or more predictor coefficient covariances for calculating confidence intervals.

57. The system of claim 55, wherein the first plurality of statistical health models includes a statistical health model is configured to determine a statistical outcome of a medical procedure, medical treatment or intervention, and/or medical condition with respect to the patient.

58. The method of claim 57, wherein at least one outcome includes risks associated with genetic factors or biochemical factors.

59. The system of claim 55, the method further comprising:

receiving an update to a first statistical health model of the first plurality of statistical health models from the source entity; and

storing the update in computer readable memory associated with a statistical health model translation system.

60. The system of claim 55, wherein the first plurality of statistical health models includes a statistical health model is of the form:

f(x)=β

0+β

1X1+β

2X2+β

3X3+β

nXn.

61. The system of claim 55, wherein the first plurality of statistical health models includes a statistical health model that is non-linear.

62. The system of claim 55, wherein the first plurality of statistical health models includes one or more outome predictor transforms, wherein a first of the one or more outome predictor transforms is an identity, inverse, square root, power, polynomial, exponential, logarithm, or mapping transformation.

63. The system of claim 55, the method further comprising converting at least one of the one or more statistical health model predictors into a predictor vector.

64. The system of claim 55, the method further comprising providing a web service via which a patient population database is passed through at least a first selected plurality of the first plurality of statistical health models to project disease prevalences, treatment costs, and/or resource requirements.

65. The system of claim 55, wherein the one or more user interfaces that enable one or more users to select models from the first plurality of statistical health models for execution further comprises a control via which the user can initiate the execution of all of the selected models.

66. The system of claim 55, the method further comprising:

contracting with a research agency to provide a first statistical health model to the statistical health model translation system;

contracting with a hospital to provide the hospital with access to the first statistical health model;

storing in computer readable the first statistical health model of the contracted research agency; and

electronically providing the contracted hospital with access to the first statistical health model.

67. The system of claim 55, the method further comprising providing access to a first statistical health model of the first plurality of statistical health models to a hospital.

68. The system of claim 55, the method further comprising providing reformatted results obtained via the statistical health model embedded in a format that is customized, wherein the customization is based at least in part upon which end user is to receive the results.