Systems and methods for risk stratification of patient populations

• US 8,311,849 B2
• Filed: 12/10/2010
• Issued: 11/13/2012
• Est. Priority Date: 03/05/2004
• Status: Active Grant

• Current Assignee: Terumo Medical Corporation (Terumo Corporation)
• Original Assignee: Health Outcomes Sciences, LLC
• Inventors: Soto, Gabriel Enrique, Spertus, John Albert
• Primary Examiner(s): Morgan, Robert
• Assistant Examiner(s): Hunter, Sean K
• Application Number:
  US12/965,656
• Publication Number:
  US 20110093288A1
• Time in Patent Office: 704 Days
• Field of Search: 705/2, 705/3
• 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 plurality of health models from different sources, the method comprising:

storing in computer readable memory associated with a health model processing system;

a first health model,

wherein the first health model is from a first source, and

wherein the first health model includes at least;

a first medical prognostic risk stratification model, or

a first medical prognostic outcomes prediction model;

a second health model,

wherein the second health model is from a second source, and

wherein the second health model includes at least;

a second medical prognostic risk stratification model, or

a second medical prognostic outcomes prediction model;

providing one or more data-input interfaces for collecting patient-specific predictors utilized when executing the first health model and the second health model;

providing one or more data-input interfaces for collecting data for one or more patient medical conditions of a first patient utilized when executing the first health model and the second health model;

enabling processing, via a computing device, of the first health model and the second health model using;

collected patient-specific predictors, and

collected one or more patient medical conditions of the first patient; and

providing, via the computing device, an output from the first health model and from the second health model.

2. The method of claim 1, wherein the first health model includes the first medical prognostic outcomes prediction model and the second health model includes the second medical prognostic outcomes prediction model, and wherein:

the first medical prognostic outcomes prediction model is configured to output a first prediction regarding a first outcome, and

the second medical prognostic outcomes prediction model is configured to output a second predication regarding the first outcome.

3. The method of claim 1, wherein the first health model includes the first medical prognostic risk stratification model and the second health model includes the second medical prognostic risk stratification model, and wherein:

the first medical prognostic risk stratification model is configured to output a first risk estimate of a first outcome, and

the second medical prognostic risk stratification model is configured to output a second risk estimate of the first outcome.

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

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

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

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

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

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

6. The method of claim 1, wherein the first health model is in the form of at least one of a:

linear model,

a generalized linear model,

a cumulative multinomial model,

a generalized multinomial model, or

a proportional hazard model.

7. The method of claim 1, the method further comprising providing 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.

8. The method of claim 1, wherein the first health model includes a statistical health model configured to determine a statistical outcome of a:

medical procedure,

medical treatment, and/or

medical condition

with respect to the first patient.

9. The method of claim 8, wherein at least one outcome includes risks associated with genetic factors.

10. The method of claim 8, wherein at least one outcome includes risks associated with biochemical factors.

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

receiving an update to the first statistical health model from the first source; and

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

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

f(x)=β

0+β

1X1+β

2X2+β

3X3+β

nXn.

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

14. The method of claim 1, wherein the first health model includes one or more outcome predictor transforms,

wherein a first of the one or more outcome predictor transforms is an identity, inverse, square root, power, polynomial, exponential, logarithm, or mapping transformation.

15. The method of claim 1, the method further comprising providing a web service via which a patient population database is passed through at least the first health model to project:

disease prevalences.

16. The method of claim 1, the method further comprising providing a web service via which a patient population database is passed through at least the first health model to project:

treatment costs.

17. The method of claim 1, the method further comprising providing a web service via which a patient population database is passed through at least the first health model to project:

resource requirements.

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

providing for display on a remote terminal a user interface via which the first and second health models can be selected from a plurality of other available health models; and

providing a control via which the user can initiate the execution of all of health models selected via the user interface via which the first and second health models can be selected.

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

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

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

causing the first health model of the contracted research agency to be stored in computer readable memory; and

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

20. The method of claim 1, the method further comprising providing reformatted results obtained via the first health model embedded in a format that is customized,

wherein the format customization is based at least in part upon which end user is to receive the results.

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

determining which entity is to receive a first output from the first health model;

determining which entity is to receive a second output from the first health model;

using the determination as to which entity is to receive the first output from the first health model to select a first letterhead;

using the determination as to which entity is to receive the second output from the first health model to select a second letterhead;

transmitting the first output from the first health model to the first entity using the first letterhead; and

transmitting the second output from the first health model to the second entity using the second letterhead.

22. The method of claim 1, the method further comprising providing a first output from the first health model to a first medical entity in an informed consent agreement,

wherein the informed consent agreement is formatted based at least in part on the identity of the first medical entity.

23. The method of claim 1, wherein a first health model, when executed, 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.

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

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

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

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

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

29. A computerized system, the system comprising:

a computing device;

computer readable media with program code stored thereon, that when executed by the computing device, performs operations comprising;

storing in computer readable memory;

a first health model,

wherein the first health model is from a first source, and

wherein the first health model includes at least;

a first medical prognostic risk stratification model, or

a first medical prognostic outcomes prediction model;

a second health model,

wherein the second health model is from a second source, and

wherein the second health model includes at least;

a second medical prognostic risk stratification model, or

a second medical prognostic outcomes prediction model;

providing one or more data-input interfaces for collecting patient-specific predictors utilized when executing the first health model and the second health model;

providing one or more data-input interfaces for collecting data for one or more patient medical conditions of a first patient utilized when executing the first health model and the second health model;

enabling processing of the first health model and the second health model using;

collected patient-specific predictors, and

collected one or more patient medical conditions of the first patient; and

providing an output from the first health model and from the second health model.

30. The system of claim 29, wherein the first health model includes the first medical prognostic outcomes prediction model and the second health model includes the second medical prognostic outcomes prediction model, and wherein:

the first medical prognostic outcomes prediction model is configured to output a first prediction regarding a first outcome, and

the second medical prognostic outcomes prediction model is configured to output a second predication regarding the first outcome.

31. The system of claim 29, wherein the first health model includes the first medical prognostic risk stratification model and the second health model includes the second medical prognostic risk stratification model, and wherein:

the first medical prognostic risk stratification model is configured to output a first risk estimate of a first outcome, and

the second medical prognostic risk stratification model is configured to output a second risk estimate of the first outcome.

32. The system of claim 29, the operations further comprising:

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

33. The system of claim 29, the operations further comprising:

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

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

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

34. The system of claim 29, the operations further comprising:

providing 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.

35. The system of claim 29, wherein the first health model 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 first patient.

36. The system of claim 29, wherein the first health model 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 first patient,

wherein at least one outcome includes risks associated with genetic factors.

37. The system of claim 29, wherein the first health model 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 first patient,

wherein at least one outcome includes risks associated with biochemical factors.

38. The system of claim 29, the operations further comprising:

electronically receiving an update to the first statistical health model from the first source; and

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

39. The system of claim 29, wherein the first health model includes a statistical health model that is non-linear.

40. The system of claim 29, wherein the first health model includes one or more outcome predictor transforms, wherein a first of the one or more outcome predictor transforms is an identity, inverse, square root, power, polynomial, exponential, logarithm, or mapping transformation.

41. The system of claim 29, the operations further comprising:

providing a web service via which a patient population database is passed through at least the first health model to project;

disease prevalences,

treatment costs, and/or

resource requirements.

42. The system of claim 29, the operations further comprising:

providing for display on a remote terminal a user interface via which the first and second health models can be selected from a plurality of other available health models; and

providing a control via which the user can initiate the execution of all of health models selected via the user interface via which the first and second health models can be selected.

43. The system of claim 29, the operations further comprising:

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

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

causing the first health model of the contracted research agency to be stored in computer readable memory; and

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

44. The system of claim 29, the operations further comprising:

providing reformatted results obtained via the first health model embedded in a format that is customized,

wherein the format customization is based at least in part upon which end user is to receive the results.

45. The system of claim 29, the operations further comprising:

determining which entity is to receive a first output from the first health model;

determining which entity is to receive a second output from the first health model;

using the determination as to which entity is to receive the first output from the first health model to select a first letterhead;

using the determination as to which entity is to receive the second output from the first health model to select a second letterhead;

transmitting the first output from the first health model to the first entity using the first letterhead; and

transmitting the second output from the first health model to the second entity using the second letterhead.

46. The system of claim 29, the operations further comprising:

providing a first output from the first health model to a first medical entity in an informed consent agreement,

wherein the informed consent agreement is formatted based at least in part on the identity of the first medical entity.

47. The system of claim 29, the operations further comprising:

transmitting to a remote client a document including XML formatting, including lists of model parameters and default values.

48. The system of claim 29, the operations further comprising:

transmitting to a remote system information concerning one or more courses of action with respect to treating a medical condition and corresponding resulting outcomes.

49. Computer readable media with program code stored thereon, that when executed by a computing device, performs operations comprising:

storing in computer readable memory;

a first health model,

wherein the first health model is from a first source, and

wherein the first health model includes at least;

a first medical prognostic risk stratification model, or

a first medical prognostic outcomes prediction model;

a second health model,

wherein the second health model is from a second source, and

wherein the second health model includes at least;

a second medical prognostic risk stratification model, or

a second medical prognostic outcomes prediction model;

providing one or more data-input interfaces for collecting patient-specific predictors utilized when executing the first health model and the second health model;

providing one or more data-input interfaces for collecting data for one or more patient medical conditions of a first patient utilized when executing the first health model and the second health model;

enabling processing of the first health model and the second health model using;

collected patient-specific predictors, and

collected one or more patient medical conditions of the first patient; and

providing an output from the first health model and from the second health model.