Guiding differential diagnosis through information maximization

• US 20060200010A1
• Filed: 03/01/2006
• Published: 09/07/2006
• Est. Priority Date: 03/02/2005
• Status: Active Grant

• Current Assignee: Cerner Innovation, Inc. (Oracle Corporation)
• Original Assignee: Siemens Medical Solutions USA Incorporated (Siemens AG)
• Inventors: Krishnan, Sriram, Rosales, Romer E., Rao, R. Bharat, Mueller, Marianne Larissa
• Granted Patent: US 8,652,039 B2
• Time in Patent Office: Days
• US Class Current: 600/300
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 15/00 ICT specially adapted for medical reports, e.g. generation or transmission thereof
• CPC Class Codes: G16H 20/00 ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

A system and method for diagnosis and treatment decisions based on information maximization is disclosed. Utilizing patient information as well as clinical records from other patients can reduce the uncertainty in both diagnosis and treatment options. The information maximization may consider additional data such as risk, cost, and comfort in making a proper medical decision.

Claims

1. A method of proposing at least one medical decision, the method comprising:

obtaining patient medical data;

obtaining other medical data from existing clinical records;

analyzing the patient medical data and the other medical data with a processor;

identifying the at least one medical decision based on the analysis of the patient medical data and the other medical data; and

determining a probability for each of the at least one medical decision based on the analysis of the patient medical data and the other medical data.

2. The method of claim 1 wherein the step of identifying the at least one medical decision further comprises:

determining a benefit of the at least one medical decision; and

maximizing a function with the benefit, the patient data and the other medical data.

3. The method of claim 1 wherein the at least one medical decision is a question of interest.

4. The method of claim 3 wherein the question of interest is a potential diagnosis of a medical condition.

5. The method of claim 4 wherein the diagnosis of the medical condition is added to the patient medical data.

6. The method of claim 3 wherein the question of interest is a potential method of treatment or selection of a test to be performed.

7. The method of claim 6 wherein at least one result from the method of treatment or the test is added to the patient medical data.

8. The method of claim 7 wherein the probability associated with the at least one medical decision is influenced by the at least one result from the method of treatment or the test.

9. The method of claim 3 wherein an uncertainty is associated with at least one solution to the question of interest, wherein a result from the at least one medical decision can reduce the uncertainty.

10. The method of claim 1 wherein the patient medical data comprises at least one of patient information, demographics, medical history, observations, symptoms, test results, and any combination thereof.

11. The method of claim 10 wherein the at least one medical decision provides at least one of the observations.

12. The method of claim 1 wherein the other medical data from existing clinical records is based on a compilation of medical records of other patients.

13. The method of claim 1 wherein the step of analyzing the patient medical data and the other medical data comprises:

comparing the other medical data with the patient medical data; and

determining which of the at least one medical decision was most effective from the other medical data or is most effective for the patient.

14. The method of claim 1 wherein the step of analyzing the patient medical data and the other medical data comprises utilizing information maximization by maximizing mutual information between unobserved or partially observed variables related to the patient medical state and a question of interest based on the patient medical data and other medical data.

15. The method of claim 1 wherein the step of analyzing the patient medical data and the other medical data comprises maximizing a benefit for a patient, wherein the benefit is predetermined.

16. The method of claim 1 wherein the at least one medical decision comprises a combination of decisions, wherein the combination of decisions comprises a series of decisions.

17. The method of claim 1 wherein the patient data can be modified, further wherein the patient data is automatically updated after the modification of the patient data.

18. The method of claim 1 wherein a benefit is associated with the at least one medical decision, and the benefit influences selection of the at least one medical decision.

19. In a computer readable storage medium having stored therein data representing instructions executable by a programmed processor for determining at least one question of interest, the storage medium comprising instructions for:

providing patient observations including patient medical data;

providing clinical observations based on recorded clinical data;

comparing the patient observations with the clinical observations;

selecting relevant observation data from the clinical observations, wherein the relevant observation data is relevant for analyzing the at least one question of interest; and

determining a solution for the at least one question of interest based on the relevant observation data.

20. The instructions of claim 19 wherein the at least one question of interest is a medical approach.

21. The instructions of claim 20 wherein the medical approach is a diagnosis of a medical condition.

22. The instructions of claim 20 wherein the medical approach is a method of treatment or a test for a medical condition.

23. The instructions of claim 19 wherein the instruction of determining a solution for the at least one question of interest comprises maximizing information for each of at least one observable variable and the question of interest, based on the relevant observation data and the patient observations.

24. A method for determining a test for a medical condition, the method comprising:

choosing the medical condition to be treated;

providing patient observations;

providing existing clinical data;

analyzing with a processor the existing clinical data to find observations based on at least one chosen test to determine the effectiveness of the at least one chosen test; and

determining the effectiveness of each of the at least one chosen test.

25. The method of claim 24 wherein the existing clinical data comprises results from the test performed on other patients.

26. The method of claim 24 wherein the medical condition is breast cancer and the at least one chosen test comprises at least one of film mammography, digital mammography, ultrasound, PET scan, magnetic resonance imaging, and any combination thereof.

27. The method of claim 24 wherein the patient observations comprises at least one of patient information, demographics, medical history, symptoms, test results, and any combination thereof.

28. The method of claim 27 wherein results of each of the at least one chosen tests that are performed on the patient are included in the patient observations.

29. The method of claim 24 wherein the step of choosing the medical condition is performed by the processor by comparing the patient observations with the existing clinical data.