Expert knowledge combination process based medical risk stratifying method and system

• US 20070094048A1
• Filed: 07/31/2006
• Published: 04/26/2007
• Est. Priority Date: 10/25/2005
• Status: Active Grant

• Current Assignee: Caterpillar Incorporated
• Original Assignee: Caterpillar Incorporated
• Inventors: Grichnik, Anthony
• Granted Patent: US 7,584,166 B2
• Time in Patent Office: Days
• US Class Current: 705/2
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/30 for calculating health indices; for individual health risk assessment
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

A method is provided for a medical risk stratification system. The method may include obtaining data records associated with one or more health variables and a plurality of medical risks from a plurality of MRS models based on an expert knowledge combination process and establishing a medical risk process model indicative of interrelationships between the plurality of medical risks and a plurality of health parameters based on the data records. The method may also include obtaining a set of values corresponding to the plurality of health parameters and calculating values of the plurality of medical risks simultaneously based upon the set of values corresponding to the plurality of health parameters and the medical risk process model. Further, the method may include optimizing the plurality of health parameters to minimize the plurality of medical risks simultaneously and presenting the values of the plurality of medical risks.

Claims

1. A method for a medical risk stratification (MRS) system, comprising:

obtaining data records associated with one or more health variables and a plurality of medical risks from a plurality of MRS models based on an expert knowledge combination process;

establishing a medical risk process model indicative of interrelationships between the plurality of medical risks and a plurality of health parameters based on the data records;

obtaining a set of values corresponding to the plurality of health parameters;

calculating values of the plurality of medical risks simultaneously based upon the set of values corresponding to the plurality of health parameters and the medical risk process model;

optimizing the plurality of health parameters to minimize the plurality of medical risks simultaneously; and

presenting the values of the plurality of medical risks.

2. The method according to claim 1, wherein the establishing includes:

selecting the plurality of health parameters from the one or more health variables;

generating a computational model indicative of the interrelationships;

determining desired statistical distributions of the plurality of health parameters of the computational model; and

recalibrating the plurality of health parameters based on the desired statistical distributions.

3. The method according to claim 2, wherein selecting further includes:

pre-processing the data records; and

using a genetic algorithm to select the plurality of health parameters from the one or more health variables based on a mahalanobis distance between a normal data set and an abnormal data set of the data records.

4. The method according to claim 2, wherein generating further includes:

creating a neural network computational model;

training the neural network computational model using the data records; and

validating the neural network computation model using the data records.

5. The method according to claim 2, wherein determining further includes:

determining a candidate set of values of the health parameters with a maximum zeta statistic using a genetic algorithm; and

determining the desired distributions of the health parameters based on the candidate set,

wherein the zeta statistic ζ

is represented by;

$\mathrm{\zeta <br><br>}=\underset{1}{\overset{j}{\sum <br><br>}}<br><br>\text{\hspace{1em}<br><br>}<br><br>\underset{1<br><br>\text{\hspace{1em}<br><br>}}{\overset{i}{\sum <br><br>}}<br><br>\text{\hspace{1em}<br><br>}<br><br><br><br>S_{\mathrm{ij}}<br><br><br><br>\left(\frac{{\mathrm{\sigma <br><br>}}_i}{{\stackrel{\_}{x}}_i}\right)<br><br>\left(\frac{{\stackrel{\_}{x}}_j}{{\mathrm{\sigma <br><br>}}_j}\right),$

provided that x_i represents a mean of an ith input;

x_j represents a mean of a jth output;

σ

_i represents a standard deviation of the ith input;

σ

_j represents a standard deviation of the jth output; and

|S_ij| represents sensitivity of the jth output to the ith input of the computational model.

7. The method according to claim 1, wherein the obtaining data records includes:

selecting a common medical risk among the plurality of MRS models from the plurality of medical risks, and a plurality of model variables of the plurality of MRS models;

obtaining a set of values of the plurality of model variables;

determining a plurality of values of the common medical risk respectively corresponding to the plurality of MRS models, based on the set of values;

determining a unified medical risk based on the plurality of values of the common medical risks; and

creating the data records associated with the one or more health variables by combining plurality of model variables of the plurality of MRS models and the unified medical risk.

8. The method according to claim 7, wherein the determining the unified medical risk includes:

determining the unified medical risk as an Euclidean distance in an Euclidean space having a plurality of dimensions, respectively representing the plurality of medical risks of the plurality of MRS models.

9. The method according to claim 8, wherein:

provided that m is an integer representing the total number of the plurality of MRS models, and (x₁, x₂, x₃, . . . , x_m) represents the plurality of values of the common medical risk from the plurality of MRS models, respectively; and

the Euclidean distance is determined as (x₁²+x₂²+ . . . +x_m²)^1/2.

10. A computer system, comprising:

a database containing data records associating a plurality of medical risks and a plurality of health parameters; and

a processor configured to;

obtain data records associated with one or more health variables and a plurality of medical risks from a plurality of MRS models based on an expert knowledge combination process;

establish a medical risk process model indicative of interrelationships between the plurality of medical risks and a plurality of health parameters based on the data records;

obtain a set of values corresponding to the plurality of health parameters;

calculate values of the plurality of medical risks simultaneously based upon the set of values corresponding to the plurality of health parameters and the medical risk process model;

optimize the plurality of health parameters to minimize the plurality of medical risks simultaneously; and

present the values of the plurality of medical risks.

11. The computer system according to claim 10, wherein, to establish the medical risk process model, the processor is further configured to:

select the plurality of health parameters from the one or more health variables;

generate a computational model indicative of the interrelationships;

determine desired statistical distributions of the plurality of health parameters of the computational model; and

recalibrate the plurality of health parameters based on the desired statistical distributions.

12. The computer system according to claim 10, wherein, to obtain the data records, the processor is further configured to:

select a common medical risk among the plurality of MRS models from the plurality of medical risks, and a plurality of model variables of the plurality of MRS models;

obtain a set of values of the plurality of model variables;

determine a plurality of values of the common medical risk respectively corresponding to the plurality of MRS models, based on the set of values;

determine a unified medical risk based on the plurality of values of the common medical risks; and

create the data records associated with the one or more health variables by combining plurality of model variables of the plurality of MRS models and the unified medical risk.

13. The computer system according to claim 12, wherein, to determine the unified medical risk, the processor is further configured to:

determine the unified medical risk as an Euclidean distance in an Euclidean space having a plurality of dimensions, respectively representing the plurality of medical risks of the plurality of MRS models.

14. The computer system according to claim 13, wherein:

provided that m is an integer representing the total number of the plurality of MRS models, and (x₁, x₂, x₃, . . . x_m) represents the plurality of values of the common medical risk from the plurality of MRS models, respectively; and

the Euclidean distance is determined as (x₁²+x₂²+ . . . +x_m²)^1/2

15. The computer system according to claim 10, further includes:

one or more input devices configured to obtain the set of values corresponding to the plurality of health parameters indicative of factual and desired health information about an individual user or a population.

16. The computer system according to claim 10, further includes:

a display device configured to;

display the set of values of the plurality of health parameters in a first display area;

display statistic data corresponding to the plurality of heath parameters in a second display area; and

display the interrelationships between the plurality of health parameters and the plurality of medical risks in a third display area.

17. A computer-readable medium for use on a computer system configured to perform a medical risk stratification procedure, the computer-readable medium having computer-executable instructions for performing a method comprising:

obtaining data records associated with one or more health variables and a plurality of medical risks from a plurality of MRS models based on an expert knowledge combination process;

establishing a medical risk process model indicative of interrelationships between the plurality of medical risks and a plurality of health parameters based on the data records;

obtaining a set of values corresponding to the plurality of health parameters;

calculating values of the plurality of medical risks simultaneously based upon the set of values corresponding to the plurality of health parameters and the medical risk process model;

optimizing the plurality of health parameters to minimize the plurality of medical risks simultaneously; and

presenting the values of the plurality of medical risks.

18. The computer-readable medium according to claim 17, wherein the establishing includes:

selecting the plurality of health parameters from the one or more health variables;

generating a computational model indicative of the interrelationships;

determining desired statistical distributions of the plurality of health parameters of the computational model; and

recalibrating the plurality of health parameters based on the desired statistical distributions.

19. The computer-readable medium according to claim 18, wherein determining further includes:

determining a candidate set of values of the health parameters with a maximum zeta statistic using a genetic algorithm; and

determining the desired distributions of the health parameters based on the candidate set,

wherein the zeta statistic ζ

is represented by;

$\mathrm{\zeta <br><br>}=\underset{1}{\overset{j}{\sum <br><br>}}<br><br>\text{\hspace{1em}<br><br>}<br><br>\underset{1<br><br>\text{\hspace{1em}<br><br>}}{\overset{i}{\sum <br><br>}}<br><br>\text{\hspace{1em}<br><br>}<br><br><br><br>S_{\mathrm{ij}}<br><br><br><br>\left(\frac{{\mathrm{\sigma <br><br>}}_i}{{\stackrel{\_}{x}}_i}\right)<br><br>\left(\frac{{\stackrel{\_}{x}}_j}{{\mathrm{\sigma <br><br>}}_j}\right),$

provided that x_i represents a mean of an ith input;

x_j represents a mean of a jth output;

σ

_i represents a standard deviation of the ith input;

σ

_j represents a standard deviation of the jth output; and

|S_ij| represents sensitivity of the jth output to the ith input of the computational model.

20. The computer-readable medium according to claim 19, wherein the obtaining data records includes:

selecting a common medical risk among the plurality of MRS models from the plurality of medical risks, and a plurality of model variables of the plurality of MRS models;

obtaining a set of values of the plurality of model variables;

determining a plurality of values of the common medical risk respectively corresponding to the plurality of MRS models, based on the set of values;

determining a unified medical risk based on the plurality of values of the common medical risks; and

creating the data records associated with the one or more health variables by combining plurality of model variables of the plurality of MRS models and the unified medical risk.