Patient data mining for diagnosis and projections of patient states

• US 7,181,375 B2
• Filed: 11/04/2002
• Issued: 02/20/2007
• Est. Priority Date: 11/02/2001
• Status: Active Grant

• Current Assignee: Cerner Health Services Incorporated (Oracle Corporation)
• Original Assignee: Siemens Corporate Research Incorporated (Siemens AG), Siemens Medical Solutions USA Incorporated (Siemens AG)
• Inventors: Sandilya, Sathyakama, Niculescu, Radu Stefan, Rao, R. Bharat, Goel, Arun Kumar
• Primary Examiner(s): PALADINI, ALBERT WILLIAM
• Application Number:
  US10/287,053
• Publication Number:
  US 20030126101A1
• Time in Patent Office: 1,569 Days
• Field of Search: 703/11, 703/2, 705/3, 128/920, 600/300
• US Class Current: 703/2
• CPC Class Codes: G06F 16/30 of unstructured textual data document management systems G06F16/93
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G16H 10/20 for electronic clinical trials or questionnaires
• 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 40/20 for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
• CPC Class Codes: G16H 40/63 for local operation
• 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: 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
• CPC Class Codes: G16H 70/60 relating to pathologies
• CPC Class Codes: Y10S 128/92 Computer assisted medical diagnostics

Abstract

A method and system for determining patient states is provided. The method includes the steps of data mining a patient record using a domain knowledge base relating to a disease of interest; inputting the mined data into a model of the disease of interest; and determining a state of the patient based on the model. The system includes a data miner for mining information from a patient record using a domain knowledge base relating to a disease of interest; and a processor for creating a patient model of the disease of interest, processing the mined data in the model to determine a current state of the patient and future states for different courses of treatment, and recommending a therapy based on the determined future state.

Claims

1. A method for determining patient states, the method comprising:

data mining a patient record using a domain knowledge base relating to a disease of interest, the data mining including mining unstructured data of the patient record;

inputting the mined data into a model of the disease of interest; and

determining a state of the patient based on the model.

2. The method as in claim 1, wherein the state is assigned a probability.

3. The method as in claim 1, further comprising determining a sequence of states of the patient.

4. The method as in claim 3, wherein the sequence is assigned a probability.

5. The method as in claim 1, further comprising determining a future state of the patient.

6. The method as in claim 5, wherein the future state is assigned a probability.

7. The method as in claim 1, further comprising creating the model of the disease of interest by mining population-based data using the domain knowledge of the disease of interest.

8. The method as in claim 1, further comprising determining a variable of the patient state.

9. The method as in claim 8, wherein the variable is assigned a probability.

40. The method of claim 1 further comprising:

inferring a factoid from a plurality of data output by the data mining;

wherein inputting comprises inputting the factoid.

10. A system for determining patient states, the system comprising:

a data miner for mining information from a patient record using a domain knowledge base relating to a disease of interest, the data mining including mining unstructured data of the patient record; and

a processor for creating a patient model of the disease of interest and processing the mined data in the model to determine a state of the patient.

11. The system as in claim 10, wherein the processor assigns a probability to the patient state.

12. The system as in claim 10, wherein the processor determines a sequence of states of the patient.

13. The system as in claim 12, wherein the processor assigns a probability to the sequence.

14. The system as in claim 10, wherein the processor determines a future state of the patient.

15. The system as in claim 14, wherein the processor assigns a probability to the future state.

16. The system as in claim 10, wherein the data miner mines population-based data using the domain knowledge of the disease of interest and the processor creates the model of the disease of interest from the population-based mined data.

17. The system as in claim 14, wherein the processor assigns an outcome to the future state by finding a patient similar to the patient.

18. The system as in claim 14, wherein the processor determines a plurality of similar patients, and assigns probabilities to future states by averaging outcomes of the similar patients.

19. The system as in claim 18, wherein the processor assigns weights to the outcomes of plurality of similar patients.

20. The system as in claim 10, wherein the processor determines a variable related to the patient state.

21. The system as in claim 20, wherein the variable is assigned a probability.

22. The system as in claim 14, wherein the processor determines a plurality of outcomes by simulating a plurality of treatments based on the mined data of the patient.

23. The system as in claim 22, wherein the processor assigns probabilities to the outcomes and suggests a therapy.

24. A program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine to perform a method for determining patient states, the method comprising:

data mining unstructured data of a patient record using a domain knowledge base relating to a disease of interest;

inputting the mined data into a model of the disease of interest; and

determining a state of the patient based on the model.

25. A method for determining patient states, the method comprising:

data mining a patient record using a domain knowledge base relating to a disease of interest;

inputting the mined data into a model of the disease of interest;

determining a state of the patient based on the model; and

assigning a probability of existence of the state.

26. The method as in claim 25 further comprising determining a sequence of states of the patient, wherein the probability is assigned to the sequence.

27. The method as in claim 25 further comprising determining a future state of the patient, wherein another probability is assigned to the future state.

28. The method as in claim 25 further comprising determining a variable of the patient state, wherein the variable is assigned another probability.

41. The method of claim 25 wherein determining the state and assigning the probability comprise determining a posteriori probability as a function observations from the mined data.

29. A system for determining patient states, the system comprising:

a data miner for mining information from a patient record using a domain knowledge base relating to a disease of interest; and

a processor for creating a patient model of the disease of interest, processing the mined data in the model to determine a state of the patient and assigning a probability of existence of the state.

30. The system as in claim 29 wherein the processor is operable to determine a sequence of states of the patient and operable to assign another probability to the sequence.

31. The system as in claim 29 wherein the processor is operable to determine a future state of the patient and operable to assign another probability to the future state.

32. The system as in claim 29 wherein the processor is operable to determine a variable related to the patient state and operable to assign another probability to the variable.

33. The system as in claim 29 wherein the processor is operable to determine a plurality of outcomes by simulating a plurality of treatments based on the mined data of the patient and is operable to assign probabilities to the outcomes.

34. A method for determining patient states, the method comprising:

data mining a patient record using a domain knowledge base relating to a disease of interest;

inputting the mined data into a model of the disease of interest; and

determining a future state of the patient based on the model;

wherein the mining comprises mining unstructured data, a probability of existence is assigned to the future state or combinations thereof.

35. The method of claim 34 wherein the mining comprises mining unstructured data.

36. The method of claim 34 wherein the probability is assigned to the future state.

37. A system for determining patent states, the system comprising:

a data miner for mining information from a patient record using a domain knowledge base relating to a disease of interest; and

a processor for creating a patient model of the disease of interest and processing the mined data in the model to determine a state of the patient;

wherein the mining comprises mining unstructured data, a probability of existence is assigned to the future state or combinations thereof.

38. The system of claim 37 wherein the mining comprises mining unstructured data.

39. The system of claim 37 wherein the probability is assigned to the future state.