Patient data mining for quality adherence

• US 8,214,224 B2
• Filed: 11/04/2002
• Issued: 07/03/2012
• Est. Priority Date: 11/02/2001
• Status: Active Grant

• Current Assignee: Cerner Health Services Incorporated (Oracle Corporation)
• Original Assignee: Siemens Corp. (Siemens AG), Siemens Medical Solutions USA Incorporated (Siemens AG)
• Inventors: Rao, R. Bharat, Sandilya, Sathyakama, Scherpbier, Harm J., Warrick, Thomas R.
• Primary Examiner(s): RANGREJ, SHEETAL
• Application Number:
  US10/287,074
• Publication Number:
  US 20030125985A1
• Time in Patent Office: 3,529 Days
• Field of Search: 705 2- 3
• US Class Current: 705/2
• 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

The present invention provides systems and methods for automatically ensuring adherence to clinical guidelines during the course of patient treatments. A data source contains patient records, including records for patients being treated; a guidelines knowledge base contains clinical guidelines; and a quality adherence engine is configured to monitor adherence with the clinical guidelines for patients being treated. At least some of the patient records may include information obtained from mining unstructured patient data. The system includes an output component for outputting quality adherence information. The outputted quality adherence information may include reminders, including reminders to take clinical actions in accordance with the clinical guidelines. The outputted quality adherence information may also include warnings that the clinical guidelines have not been observed.

Claims

1. A system for automatically ensuring adherence to clinical guidelines, comprising:

a data source containing at least one patient record, including a first record for a patient being treated, the first patient record including structured information mined from unstructured patient data by a processor, the unstructured patient data including free text, the structured information for the patient being treated comprising values for variables related to clinical actions for the patient being treated, each of the values inferred from pieces extracted, by mining, from the unstructured patient data for the patient being treated, the pieces for each variable assigned respective first probabilities of indicating respective possible values, different pieces indicating different possible values of the respective variable, a plurality of the first probabilities referring to a same one of the variables combined into a unified probability for the value for the same one of the variables, at least one of the first probabilities being less than 100%, the value for the same one of the variables determined from the unified probability, the pieces and possible values for each of the variables being for the patient being treated, at least one of the pieces extracted from the free text;

a guideline knowledge base containing a clinical guideline; and

a quality adherence engine for monitoring adherence with the clinical guideline as a function of the information mined from unstructured patient data in the first record for the patient being treated.

2. The system of claim 1, further including an output component for outputting quality adherence information.

3. The system of claim 2, wherein the outputted quality adherence information includes reminders.

4. The system of claim 3, wherein the reminders include reminders to take a clinical action in accordance with the clinical guidelines.

5. The system of claim 2, wherein the outputted quality adherence information includes warnings that the clinical guideline has not been observed.

6. The system of claim 2, wherein the outputted quality adherence information includes warning that the clinical guideline has not been observed based on a probability exceeding a threshold.

7. The system of claim 2 wherein the outputted quality adherence information includes a report.

8. The system of claim 2 wherein the outputted quality adherence information includes schedule information.

9. The system of claim 1, wherein the at least one patient record comprises a plurality of patient records, the patient records contained in the data source include information regarding the clinical actions taken during patient treatments.

10. The system of claim 9, wherein the quality adherence engine monitors adherence to the clinical guideline at least in part by comparing the clinical action with the clinical guideline.

11. The system of claim 10, wherein the clinical guideline relate to recommended clinical action.

12. The system of claim 11, wherein the quality adherence engine monitors adherence to the clinical guideline at least in part by determining a subsequent recommended clinical action.

13. The system of claim 12, wherein the quality adherence engine monitors adherence to the clinical guideline at least in part by outputting a reminder for the subsequent recommended clinical action.

14. The system of claim 1 wherein the quality adherence engine is operable to identify a relevant guideline for the patient being treated.

15. The system of claim 1 wherein the quality adherence engine is operable to assign a probability to each of a plurality of clinical actions.

16. The system of claim 1 wherein the clinical guideline comprises health care person performed actions and the adherence comprises evaluation of compliance by the health care person.

17. A method for automatically ensuring adherence to clinical guidelines during the course of patient treatments, the method comprising the steps of:

obtaining a patient record for a patient being treated, the patient record containing at least some structured information from a mined unstructured data source, the structured information comprising values for variables related to clinical actions for the patient being treated, the values for the variables inferred from pieces extracted, by processor mining, from the unstructured patient data source, the pieces for each variable assigned respective first probabilities for different possible values for the respective variable, a plurality of the first probabilities referring to a same one of the variables of the patient being treated combined into a unified probability for the value for the same one of the variables, at least one of the first probabilities being less than 100%, the value determined from the unified probability, the pieces and possible values being for the patient being treated, at least one of the pieces extracted from free text;

retrieving a clinical guideline from a guideline knowledge base; and

monitoring adherence to the clinical guideline for the patient being treated as a function of the information from the mined unstructured data source.

18. The method of claim 17, further including the step of outputting quality adherence information.

19. The method of claim 18, wherein the outputted quality adherence information includes a reminder.

20. The method of claim 19, wherein the reminder is to take a clinical action in accordance with the clinical guideline.

21. The method of claim 18, wherein the outputted quality adherence information includes a warning that the clinical guideline has not been observed.

22. The method of claim 18, wherein the outputted quality adherence information includes a warning that the clinical guideline has not been observed based on a probability exceeding a threshold.

23. The method of claim 18, wherein the obtained patient record includes the clinical action taken during a patient treatment.

24. The method of claim 23, wherein monitoring adherence to the clinical guideline includes comparing the clinical action with the clinical guideline.

25. The method of claim 24, wherein the clinical guideline relates to a recommended clinical action.

26. The method of claim 24, wherein monitoring adherence to the clinical guideline further includes determining a subsequent recommended clinical action.

27. The method of claim 26, wherein monitoring adherence to the clinical guideline further includes outputting a reminder for the subsequent recommended clinical action.

29. The method of claim 18 wherein outputting comprises outputting a report.

30. The method of claim 18 wherein outputting comprises outputting schedule information.

31. The method of claim 17 wherein retrieving comprises identifying a relevant guideline for the patient being treated.

32. The method of claim 17 wherein monitoring comprises assigning a second probability to each of a plurality of clinical actions.

28. A program storage device readable by a machine, tangibly embodying a program of instructions executable on the machine to perform method steps for automatically ensuring adherence to clinical guidelines, the method steps comprising:

obtaining patient records for patients being treated, at least some of the patient records containing information from mined unstructured data sources, the information for a first patient being treated comprising values for variables related to clinical actions, each of the values being from pieces extracted, by mining, from the unstructured patient data, each of the pieces for a same variable assigned first probabilities, a plurality of the first probabilities referring to the same one of the variables combined into a unified probability for the value for the same one of the variables, at least one of the first probabilities being less than 100%, the value determined from the unified probability, the pieces and values being for the patient being treated, at least one of the pieces extracted from free text of the unstructured data source;

retrieving clinical guidelines from a guidelines knowledge base; and

monitoring adherence to the clinical guidelines for the patients being treated as a function of the information from a mined unstructured data source.