Methods and apparatus for providing decision support

• US 7,643,969 B2
• Filed: 03/04/2005
• Issued: 01/05/2010
• Est. Priority Date: 03/04/2005
• 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): Rodriguez; Paul L
• Assistant Examiner(s): Craig; Dwin M
• Application Number:
  US11/072,209
• Publication Number:
  US 20060200549A1
• Time in Patent Office: 1,768 Days
• Field of Search: 703/2, 703/11, 345/595, 706/60
• US Class Current: 703/2
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

A method for providing decision support includes using a programmed computer to input a regression model specification, and to repeat the input a plurality of times to obtain and store a plurality of regression model specifications. The method further includes using the programmed computer to analyze selected regression model specifications to determine at least one of common variables and functions of common variables, to thereby determine a reduced-redundancy request for input of variables, when a plurality of the stored regression model specifications are selected for use.

Claims

1. A machine-readable medium or media having instructions recorded thereon that when executed by a processor:

(a) input a regression model specification related to providing predictions regarding the outcome for a patient of a medical treatment;

(b) repeat (a) a plurality of times to obtain and store a plurality of the regression model specifications;

(c) when a plurality of the stored regression model specifications are selected for use, analyze the selected regression model specifications to determine at least one of common variables and functions of common variables, to thereby determine a reduced-redundancy request for input of variables;

(d) output a user interface for display, the user interface including a plurality of fields to receive patient parameters corresponding to the reduced redundancy request for input of variables;

output for display a set of stored regression model specifications;

accept a selection of the displayed regression model specifications for use;

output for display a reduced-redundancy user interface that requests a user to provide input of variables for the selected regression model specifications;

accept input values for the variables requested; and

use the accepted input values to determine and provide for display results of the selected stored regression model specifications.

2. A machine readable medium in accordance with claim 1 wherein the instructions when executed store accepted variable values in a database with an indication of person or object to which they apply, to retrieve the stored variable values from the database when a different regression model specification is selected for use for the same person or object, and to provide, as default values, the stored variable values for the same person or object for the different regression specification that is selected.

3. A machine readable medium in accordance with claim 1 wherein the instructions when executed enable the printing of the results using customizable content stored in a memory or database, and wherein the results comprise a visual representation of a statistical range.

4. A machine readable medium in accordance with claim 1 wherein to obtain coefficients associated with the selected regression model specifications, the instructions when executed instruct the processor to retrieve variable values from a database and perform a regression using the retrieved variable values.

5. A machine readable medium in accordance with claim 1 wherein the instructions when executed instruct the processor to display a visual selection of mathematical variable transforms for at least some variables and to accept a selection of the mathematical variable transforms and store the selection in a memory.

6. A machine readable medium in accordance with claim 1, wherein the results of the selected stored regression model specifications include a medical outcome prediction, a confidence level, and a symptom probability.

7. A method for providing decision support, the method comprising using a programmed computer to:

(a) input a regression model specification related to providing predictions regarding the outcome for a patient of a medical treatment;

(b) repeat (a) a plurality of times to obtain and store in computer readable memory a plurality of the regression model specifications;

(c) when a plurality of the stored regression model specifications are selected for use, analyze the selected regression model specifications to determine at least one of common variables and/or functions of common variables, to thereby determine a reduced-redundancy request for input of variables; and

(d) output for display a user interface including one or more fields to receive respective patient parameters corresponding to the reduced redundancy request for input of variables;

display a set of stored regression model specifications;

accept a selection of the displayed regression model specifications for use;

display a reduced-redundancy user interface that requests a user to provide input of variables for the selection of regression model specifications;

accept input values for the variables requested; and

use the accepted input values to determine and display results of the selected stored regression model specifications.

8. A method in accordance with claim 7 further comprising using the computer to store accepted variable values in a database with an indication of person or object to which they apply, to retrieve the stored variable values from the database when a different regression model specification is selected for use for the same person or object, and to provide, as default values, the stored variable values for the same person or object for the different regression specification that is selected.

9. A method in accordance with claim 7 further comprising using the computer to display results of the selected regression model specifications, and to print the results using customizable content stored in a memory or database, and wherein the results comprise a visual representation of a statistical range.

10. A method in accordance with claim 7 wherein the displayed results comprise a visual representation of a statistical range.

11. A method in accordance with claim 7 wherein to obtain coefficients associated with the selected regression model specifications, the instructions are further configured to instruct the processor to retrieve variables from a database and perform a regression using the retrieved variable values.

12. A method in accordance with claim 7 further comprising using the computer to display a visual selection of mathematical variable transforms for at least some variables and to accept a selection of the mathematical variable transforms and store the selection in a memory.

13. A method in accordance with claim 7, wherein the results of the selected stored regression model specifications include a medical outcome prediction, a confidence level, and a symptom probability.

14. A method for providing medical decision support with respect to medical treatments, the method comprising using a programmed computer to:

providing a user interface for inputting a plurality of regression model specifications related to medical treatment and outcome;

providing a user interface via which the user can select all or a subset of the plurality of the regression model specifications;

identifying common variables and/or functions of common variables with respect to the selected regression model specifications, to thereby determine a reduced-redundancy request for input of variables;

outputting for display a reduced-redundancy user interface that requests a user to provide input of variables for the selected regression model specifications;

receiving input values for the variables requested;

causing at least in part the regression model specifications selected by the user to be run using the received input values to obtain results;

causing at least in part the results of the regression model specifications to be output for display to the user; and

identifying one or more common variables in at least two regression model specifications; and

determining a reduced-redundancy request for input of variables based on the identification of the one or more common variables.

15. The method as defined in claim 14, wherein the results of the user-selected regression model specifications and parameters used to execute those models are stored for subsequent retrieval.

16. The method as defined in claim 14, the method further comprising using the results of the user-selected regression model specifications to create an informed consent document and/or patient educational material including a discussion of procedural risks and benefits.

17. The method as defined in claim 14, the method further comprising providing for display on a user display device a visual selection of parametric regression model forms.

18. The method as defined in claim 14, wherein models corresponding to the plurality of regression model specifications include a linear model and/or a nonlinear model.

19. The method as defined in claim 14, wherein at least one regression model is defined in terms of at least a coefficient vector for calculating confidence intervals.

20. The method as defined in claim 14, wherein at least one regression model is defined in terms of a coefficient vector and a covariance matrix for calculating confidence intervals.

21. The method as defined in claim 14, wherein the user selects the plurality of the regression model specifications via a visually presented menu of regression model specifications.

22. The method as defined in claim 14, wherein the plurality of regression model specifications are related to patient clinical variables associated with predicting outcomes related to cardiovascular medicine.

23. The method as defined in claim 14, wherein the plurality of regression model specifications are related to patient clinical variables associated with predicting health related outcomes.

24. The method as defined in claim 14, wherein at least one of the plurality of the regression model specifications is associated with at least one of the following parameters:

blood pressure, diabetes, ejection fraction, or age.

25. A method for providing medical decision support with respect to medical treatments, the method comprising using a programmed computer to:

providing a user interface for inputting a plurality of regression model specifications related to medical treatment and outcome;

providing an interface via which a third-party request can select one or more of the plurality of the regression model specifications;

causing at least in part the regression model specifications selected by the request to be run;

causing at least in part results of the regression model specifications to be returned to the third-party;

identifying one or more common variables in at least two regression model specifications; and

determining a reduced-redundancy request for submission of variables based on the identification of the one or more common variables.

26. The method as defined in claim 25, wherein models corresponding to the plurality of regression model specifications include a linear model and/or a nonlinear model.

27. The method as defined in claim 25, wherein at least one model is defined in terms of at least a coefficient vector for calculating confidence intervals.

28. The method as defined in claim 25, wherein at least one model is defined in terms of a coefficient vector and a covariance matrix for calculating confidence intervals.

29. A machine-readable medium or media having instructions recorded thereon that when executed by a processor:

(a) input a regression model specification related to providing predictions regarding the outcome for a patient of a medical treatment;

(b) repeat (a) a plurality of times to obtain and store a plurality of the regression model specifications;

(c) when a plurality of the stored regression model specifications are selected for use, analyze the selected regression model specifications to determine at least one of common variables and functions of common variables, to thereby determine a reduced-redundancy request for input of variables;

(d) output a user interface for display, the user interface including a plurality of fields to receive patient parameters corresponding to the reduced redundancy request for input of variables;

output for display a set of stored regression model specifications;

accept a selection of the displayed regression model specifications for use;

determine whether a first parameter for a first regression model can be derived from one or more parameters of other regression models via one or more calculations, and if so, inhibiting a redundant request with respect to the first parameter.

30. A machine-readable medium or media having instructions recorded thereon that when executed by a processor:

(a) input a regression model specification related to providing predictions regarding the outcome for a patient of a medical treatment;

(b) repeat (a) a plurality of times to obtain and store a plurality of the regression model specifications;

(c) when a plurality of the stored regression model specifications are selected for use, analyze the selected regression model specifications to determine at least one of common variables and functions of common variables, to thereby determine a reduced-redundancy request for input of variables;

(d) output a user interface for display, the user interface including a plurality of fields to receive patient parameters corresponding to the reduced redundancy request for input of variables;

output for display a set of stored regression model specifications;

accept a selection of the displayed regression model specifications for use; and

determine whether a first parameter for a first regression model can be obtained from one or more parameters of other regression models, and if so, inhibiting a redundant request with respect to the first parameter.

31. A machine-readable medium or media having instructions recorded thereon that when executed by a processor:

(a) input a regression model specification related to providing predictions regarding the outcome for a patient of a medical treatment;

(b) repeat (a) a plurality of times to obtain and store a plurality of the regression model specifications;

(c) when a plurality of the stored regression model specifications are selected for use, analyze the selected regression model specifications to determine at least one of common variables and functions of common variables, to thereby determine a reduced-redundancy request for input of variables;

(d) output a user interface for display, the user interface including a plurality of fields to receive patient parameters corresponding to the reduced redundancy request for input of variables;

output for display a set of stored regression model specifications; and

accept a selection of the displayed regression model specifications for use;

provide for display a parametric regression model form including fields configured to receive a medical outcome type request and a parameter transformation association with a parameter, wherein the parameter is age.

32. A method for providing decision support, the method comprising using a programmed computer to:

(a) input a regression model specification related to providing predictions regarding the outcome for a patient of a medical treatment;

(b) repeat (a) a plurality of times to obtain and store in computer readable memory a plurality of the regression model specifications;

(c) when a plurality of the stored regression model specifications are selected for use, analyze the selected regression model specifications to determine at least one of common variables and/or functions of common variables, to thereby determine a reduced-redundancy request for input of variables; and

(d) output for display a user interface including one or more fields to receive respective patient parameters corresponding to the reduced redundancy request for input of variables; and

determine whether a first parameter for a first regression model can be derived from one or more parameters of other regression models via one or more calculations, and if so, inhibiting a redundant request with respect to the first parameter.

33. A method for providing decision support, the method comprising using a programmed computer to:

(a) input a regression model specification related to providing predictions regarding the outcome for a patient of a medical treatment;

(b) repeat (a) a plurality of times to obtain and store in computer readable memory a plurality of the regression model specifications;

(c) when a plurality of the stored regression model specifications are selected for use, analyze the selected regression model specifications to determine at least one of common variables and/or functions of common variables, to thereby determine a reduced-redundancy request for input of variables; and

(d) output for display a user interface including one or more fields to receive respective patient parameters corresponding to the reduced redundancy request for input of variables; and

determine whether a first parameter for a first regression model can be obtained from one or more parameters of other regression models, and if so, inhibiting a redundant request with respect to the first parameter.

34. A method for providing decision support, the method comprising using a programmed computer to:

(a) input a regression model specification related to providing predictions regarding the outcome for a patient of a medical treatment;

(b) repeat (a) a plurality of times to obtain and store in computer readable memory a plurality of the regression model specifications;

(c) when a plurality of the stored regression model specifications are selected for use, analyze the selected regression model specifications to determine at least one of common variables and/or functions of common variables, to thereby determine a reduced-redundancy request for input of variables; and

(d) output for display a user interface including one or more fields to receive respective patient parameters corresponding to the reduced redundancy request for input of variables; and

provide for display a parametric regression model form including fields configured to receive a medical outcome type request and a parameter transformation association with a parameter, wherein the parameter is age.

35. A method for providing medical decision support with respect to medical treatments, the method comprising using a programmed computer to:

provide a user interface for presentation on a display via which a user can select from a plurality of regression model specifications related to providing predictions regarding the outcome of a medical treatment;

provide a user interface for presentation on the display via which the user can initiate the running of the selected regression model specifications to be run using data related to a first patient;

cause at least in part results of the regression model specifications to be returned to the user as human readable output, the output including predictions regarding the outcome of the medical treatment with respect to the first patient; and

wherein the results of the regression model specifications to the user are in the form of patient educational material including a discussion of procedural risks and benefits.

36. The method as defined in claim 35, the method further comprising:

identifying one or more common variables in at least two regression model specifications; and

determining a reduced-redundancy request for submission of variables based on the identification of the one or more common variables.

37. The method as defined in claim 35, wherein models corresponding to the plurality of regression model specifications include a linear model and/or a nonlinear model.

38. The method as defined in claim 35, wherein at least one regression model is defined in terms of at least a coefficient vector for calculating confidence intervals.

39. The method as defined in claim 35, wherein the returned predications relate to stroke risk using different types of medical procedures.

40. The method as defined in claim 35, wherein the returned predications relate to risk using different types of medical procedures for a first patient ailment.

41. The method as defined in claim 35, wherein the returned predications enable the first patient to assess risks associated with different treatments.

42. The method as defined in claim 35, wherein the results of the regression model specifications are returned to the user as an informed consent document for the first patient.

43. A method for providing medical decision support with respect to medical treatments, the method comprising using a programmed computer to:

provide a user interface for presentation on a display via which a user can select from a plurality of regression model specifications related to providing predictions regarding the outcome of a medical treatment;

provide a user interface for presentation on the display via which the user can initiate the running of the selected regression model specifications to be run using data related to a first patient;

cause at least in part results of the regression model specifications to be returned to the user as human readable output, the output including predictions regarding the outcome of the medical treatment with respect to the first patient; and

wherein the returned predications provide a predication related to treating the first patient using angioplasty and a prediction related to treating the first patient using bypass surgery.

44. A method for providing medical decision support with respect to medical treatments, the method comprising using a programmed computer to:

provide a user interface for presentation on a display via which a user can select from a plurality of regression model specifications related to providing predictions regarding the outcome of a medical treatment;

provide a user interface for presentation on the display via which the user can initiate the running of the selected regression model specifications to be run using data related to a first patient;

cause at least in part results of the regression model specifications to be returned to the user as human readable output, the output including predictions regarding the outcome of the medical treatment with respect to the first patient

wherein the results of the regression model specifications are returned to the user as an informed consent document for the first patient;

wherein the returned predications enable the first patient to assess risks associated with different treatments; and

wherein the informed consent document is generated to include terms under which patient treatment is provided, a disclaimer, and a signature line for the first patient and/or another person authorized to provide consent for the first patient treatment.

45. A method for providing medical decision support with respect to medical treatments, the method comprising using a programmed computer to:

provide a user interface for presentation on a display via which a user can select from a plurality of regression model specifications related to providing predictions regarding the outcome of a medical treatment;

provide a user interface for presentation on the display via which the user can initiate the running of the selected regression model specifications to be run using data related to a first patient;

cause at least in part results of the regression model specifications to be returned to the user as human readable output, the output including predictions regarding the outcome of the medical treatment with respect to the first patient; and

provide one or more portal content modules, including a workgroup directory and/or a discussion thread.

46. A method for enabling a user to specify a regression model used to provide medical decision support with respect to a medical treatment, the method comprising using a programmed computer to:

provide a user interface via which a user can specify a regression model type;

provide a user interface via which a user can specify;

an outcome type,

a parameter type,

a medical parameter name;

a limit on a parameter range, the limit relating to a patient characteristic;

obtain model coefficients;

enable a user to run the regression model; and

wherein the model coefficients include an intercept term, a mean square error term, and/or a number of degrees of freedom term.

47. The method as defined in claim 46, wherein the model type is selectable by the user from a group including at least linear, multinominal, and proportional hazard.

48. The method as defined in claim 46, wherein the medical parameter name is selectable via a menu including a plurality of medical parameter names, including at least one related to blood pressure, diabetes, and/or fractures.

49. The method as defined in claim 46, wherein the medical parameter type is selectable from the group including binary, enumerated, integer, and decimal.

50. The method as defined in claim 46, wherein the parameter range limit relates to gender and/or age.