Data based truth maintenance

• US 10,395,176 B2
• Filed: 01/29/2016
• Issued: 08/27/2019
• Est. Priority Date: 09/23/2010
• Status: Active Grant

• Current Assignee: Kyndryl Incorporated
• Original Assignee: International Business Machines Corporation
• Inventors: Attaluri, Prabhakar, Iqbal, Mickey, Lawrence, Calvin D., Trevathan, Matthew B.
• Primary Examiner(s): Nilsson, Eric
• Application Number:
  US15/010,498
• Publication Number:
  US 20160147961A1
• Time in Patent Office: 1,306 Days
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

A truth maintenance method and system. The method includes receiving by a computer processor, health event data associated with heath care records for patients. The computer processor associates portions of the health event data with associated patients and related records in a truth maintenance system database. The computer processor derives first health related assumption data and retrieves previous health related assumption data derived from and associated with previous portions of previous health event data. The computer processor executes non monotonic logic with respect to the first health related assumption data and the previous health related assumption data. In response, the computer processor generates and stores updated first updated health related assumption data associated with the first health related assumption data and the previous health related assumption data.

Claims

1. A method comprising:

receiving, by a computer processor of a computing device from a plurality of data sources, first health event data associated with a first plurality of heath care records associated with a plurality of patients, said computer processor controlling a cloud hosted mediation system comprising an inference engine software application, a truth maintenance system database, and non monotonic logic, wherein said non monotonic logic comprises code for enabling a Dempster Shafer theory;

deriving, by said computer processor executing said inference engine software application, first health related assumption data associated with each portion of portions of said first health event data associated with associated patients of said plurality of patients and related records in said truth maintenance system database, wherein said first health related assumption data comprises multiple sets of assumptions associated with said plurality of patients, wherein each set of said multiple sets comprises assumed medical conditions and an associated plausibility percentage value, wherein at least two sets of said multiple sets is associated with each patient of set plurality of patients, wherein a first set of said multiple sets comprises evidence supporting a first fact indicating that a first patient of said plurality of patients has a first medical condition of said assumed medical conditions with a first plausibility percentage value, wherein a second set of said multiple sets comprises evidence supporting a second fact indicating that said first patient has a second medical condition of said assumed medical conditions with a second plausibility percentage value, wherein said first medical condition differs from said second medical condition, and wherein said first plausibility percentage value differs from said second plausibility percentage value;

determining, by said computer processor, based on results of executing the Dempster Shafer theory with respect to said first set and said second set, that said first set comprises a higher belief assignment value than said second set;

generating, by said computer processor based on results of said determining, said deriving and said first executing, an initial diagnosis and treatment recommendation for said first patient, said initial diagnosis and treatment recommendation associated with said first set;

retrieving, by said computer processor from said truth maintenance system database, previous health related assumption data derived from and associated with previous portions of previous health event data retrieved from said plurality of data sources, said previous health related assumption data derived at a time differing from a time of said deriving, said previous health related event data associated with previous health related events occurring at a different time from said first health event data;

additionally executing, by said computer processor executing said non monotonic logic, the Dempster Shafer theory with respect to said first set, said second set, said first patient, and said previous health related assumption data;

modifying, by said computer processor based on results of said additionally executing, said first plausibility percentage value of said first set and said second plausibility percentage value of said second set;

determining, by said computer processor, based on results of said additionally executing and said modifying, that said second set comprises a higher belief assignment value than said first set;

generating, by said computer processor based on said results of said additionally executing and said modifying, an updated diagnosis and treatment recommendation for said first patient; and

generating, by said computer processor executing said non monotonic logic and said inference engine software application, first updated health related assumption data associated with said first health related assumption data and said previous health related assumption data, wherein said previous health related assumption data, said first health related assumption data, and said first updated health related assumption data each comprise assumptions associated with detected medical conditions of said plurality of patients.

2. The method of claim 1, further comprising:

executing, by said computer processor based on said first updated health related assumption data, health related actions associated with said plurality of patients.

3. The method of claim 2, wherein said health related actions comprise treatment options for said plurality of patients.

4. The method of claim 3, wherein said health related actions comprises implementing a pay by usage cloud metering model associated with said plurality of patients.

5. The method of claim 2, further comprising:

transmitting, by said computer processor to a plurality of health care providers, data describing said health related actions associated with said plurality of patients.

6. The method of claim 1, wherein said previous health related assumption data, said first health related assumption data, and said first updated health related assumption data each comprise assumptions associated with said plurality of patients.

7. The method of claim 1, wherein said generating first updated health related assumption data comprises retracting portions of said first health related assumption data and said previous health related assumption data.

8. The method of claim 7, further comprising:

retrieving, by said computer processor, historical patient data and treatment options data;

after said retracting, associating by said computer processor, said first updated health related assumption data with said historical patient data and said treatment options data;

generating, by said computer processor, health related recommendations associated with said plurality of patients; and

presenting, by said computer processor via a dashboard view on a display device, said health related recommendations.

9. The method of claim 8, wherein said health related recommendations comprise treatment options for said plurality of patients.

10. The method of claim 1, further comprising:

providing at least one support service for at least one of creating, integrating, hosting, maintaining, and deploying computer-readable code in said computing system, wherein the code in combination with the computing system is capable of performing the method of claim 1.

11. A computer program product, comprising a non-transitory computer readable memory device storing a computer readable program code, said computer readable program code comprising an algorithm that when executed by a computer processor implements a method within a computing device, said method comprising:

receiving, by said computer processor from a plurality of data sources, first health event data associated with a first plurality of heath care records associated with a plurality of patients, said computer processor controlling a cloud hosted mediation system comprising an inference engine software application, a truth maintenance system database, and non monotonic logic, wherein said non monotonic logic comprises code for enabling a Dempster Shafer theory;

deriving, by said computer processor executing said inference engine software application, first health related assumption data associated with each portion of portions of said first health event data associated with associated patients of said plurality of patients and related records in said truth maintenance system database, wherein said first health related assumption data comprises multiple sets of assumptions associated with said plurality of patients, wherein each set of said multiple sets comprises assumed medical conditions and an associated plausibility percentage value, wherein at least two sets of said multiple sets is associated with each patient of set plurality of patients, wherein a first set of said multiple sets comprises evidence supporting a first fact indicating that a first patient of said plurality of patients has a first medical condition of said assumed medical conditions with a first plausibility percentage value, wherein a second set of said multiple sets comprises evidence supporting a second fact indicating that said first patient has a second medical condition of said assumed medical conditions with a second plausibility percentage value, wherein said first medical condition differs from said second medical condition, and wherein said first plausibility percentage value differs from said second plausibility percentage value;

determining, by said computer processor, based on results of executing the Dempster Shafer theory with respect to said first set and said second set, that said first set comprises a higher belief assignment value than said second set;

generating, by said computer processor based on results of said determining, said deriving and said first executing, an initial diagnosis and treatment recommendation for said first patient, said initial diagnosis and treatment recommendation associated with said first set;

retrieving, by said computer processor from said truth maintenance system database, previous health related assumption data derived from and associated with previous portions of previous health event data retrieved from said plurality of data sources, said previous health related assumption data derived at a time differing from a time of said deriving, said previous health related event data associated with previous health related events occurring at a different time from said first health event data;

additionally executing, by said computer processor executing said non monotonic logic, the Dempster Shafer theory with respect to said first set, said second set, said first patient, and said previous health related assumption data;

modifying, by said computer processor based on results of said additionally executing, said first plausibility percentage value of said first set and said second plausibility percentage value of said second set;

determining, by said computer processor, based on results of said additionally executing and said modifying, that said second set comprises a higher belief assignment value than said first set;

generating, by said computer processor based on said results of said additionally executing and said modifying, an updated diagnosis and treatment recommendation for said first patient; and

generating, by said computer processor executing said non monotonic logic and said inference engine software application, first updated health related assumption data associated with said first health related assumption data and said previous health related assumption data, wherein said previous health related assumption data, said first health related assumption data, and said first updated health related assumption data each comprise assumptions associated with detected medical conditions of said plurality of patients.

12. The computer program product of claim 11, wherein said method further comprises:

executing, by said computer processor based on said first updated health related assumption data, health related actions associated with said plurality of patients.

13. The computer program product of claim 12, wherein said health related actions comprise treatment options for said plurality of patients.

14. The computer program product of claim 13, wherein said health related actions comprises implementing a pay by usage cloud metering model associated with said plurality of patients.

15. The computer program product of claim 12, wherein said method further comprises:

transmitting, by said computer processor to a plurality of health care providers, data describing said health related actions associated with said plurality of patients.

16. The computer program product of claim 11, wherein said previous health related assumption data, said first health related assumption data, and said first updated health related assumption data each comprise assumptions associated with said plurality of patients.

17. The computer program product of claim 11, wherein said generating first updated health related assumption data comprises retracting portions of said first health related assumption data and said previous health related assumption data.

18. The computer program product of claim 17, wherein said method further comprises:

retrieving, by said computer processor, historical patient data and treatment options data;

after said retracting, associating by said computer processor, said first updated health related assumption data with said historical patient data and said treatment options data;

generating, by said computer processor, health related recommendations associated with said plurality of patients; and

presenting, by said computer processor via a dashboard view on a display device, said health related recommendations.

19. A computing system comprising a computer processor coupled to a computer-readable memory unit, said memory unit comprising instructions that when executed by the computer processor implements a method comprising:

receiving, by said computer processor from a plurality of data sources, first health event data associated with a first plurality of heath care records associated with a plurality of patients, said computer processor controlling a cloud hosted mediation system comprising an inference engine software application, a truth maintenance system database, and non monotonic logic, wherein said non monotonic logic comprises code for enabling a Dempster Shafer theory;

deriving, by said computer processor executing said inference engine software application, first health related assumption data associated with each portion of portions of said first health event data associated with associated patients of said plurality of patients and related records in said truth maintenance system database, wherein said first health related assumption data comprises multiple sets of assumptions associated with said plurality of patients, wherein each set of said multiple sets comprises assumed medical conditions and an associated plausibility percentage value, wherein at least two sets of said multiple sets is associated with each patient of set plurality of patients, wherein a first set of said multiple sets comprises evidence supporting a first fact indicating that a first patient of said plurality of patients has a first medical condition of said assumed medical conditions with a first plausibility percentage value, wherein a second set of said multiple sets comprises evidence supporting a second fact indicating that said first patient has a second medical condition of said assumed medical conditions with a second plausibility percentage value, wherein said first medical condition differs from said second medical condition, and wherein said first plausibility percentage value differs from said second plausibility percentage value;

determining, by said computer processor, based on results of executing the Dempster Shafer theory with respect to said first set and said second set, that said first set comprises a higher belief assignment value than said second set;

generating, by said computer processor based on results of said determining, said deriving and said first executing, an initial diagnosis and treatment recommendation for said first patient, said initial diagnosis and treatment recommendation associated with said first set;

retrieving, by said computer processor from said truth maintenance system database, previous health related assumption data derived from and associated with previous portions of previous health event data retrieved from said plurality of data sources, said previous health related assumption data derived at a time differing from a time of said deriving, said previous health related event data associated with previous health related events occurring at a different time from said first health event data;

additionally executing, by said computer processor executing said non monotonic logic, the Dempster Shafer theory with respect to said first set, said second set, said first patient, and said previous health related assumption data;

modifying, by said computer processor based on results of said additionally executing, said first plausibility percentage value of said first set and said second plausibility percentage value of said second set;

determining, by said computer processor, based on results of said additionally executing and said modifying, that said second set comprises a higher belief assignment value than said first set;

generating, by said computer processor based on said results of said additionally executing and said modifying, an updated diagnosis and treatment recommendation for said first patient; and

generating, by said computer processor executing said non monotonic logic and said inference engine software application, first updated health related assumption data associated with said first health related assumption data and said previous health related assumption data, wherein said previous health related assumption data, said first health related assumption data, and said first updated health related assumption data each comprise assumptions associated with detected medical conditions of said plurality of patients.