Quality metric extraction and editing for medical data

• US 8,670,997 B2
• Filed: 02/08/2007
• Issued: 03/11/2014
• Est. Priority Date: 02/09/2006
• Status: Active Grant

• Current Assignee: Cerner Innovation, Inc. (Oracle Corporation)
• Original Assignee: Siemens Medical Solutions USA Incorporated (Siemens AG)
• Inventors: Krishnan, Sriram, Landi, William A., Steck, Harald, Rosales, Romer E., Niculescu, Radu Stefan, Rahmanian, Farbod, Rao, R. Bharat
• Primary Examiner(s): NGUYEN, HIEP VAN
• Application Number:
  US11/672,639
• Publication Number:
  US 20070192143A1
• Time in Patent Office: 2,588 Days
• Field of Search: 705/3
• US Class Current: 705/3
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 30/04 Billing or invoicing
• 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

Abstract

Medical related quality of care information is extracted and edited for reporting. Patient records are mined. The mining may include mining unstructured data to create structured information. Measures are derived automatically from the structured information. A user may then edit the measures, data points used to derive the measures, or other quality metric based on expert review. The editing may allow for a better quality report. Tools may be provided to configure reports, allowing generation of new or different reports.

Claims

1. A system for editing medical related quality metric information, the system comprising:

a user input device;

at least one memory operable to store at least one medical patient record; and

a processor configured to;

extract at least a first quality metric from the at least one medical patient record, the first quality metric being a value indicating a quality of care related to a guideline or requirement and the first quality metric calculated from patient treatment information in the at least one medical patient record, the patient treatment information comprising a fact, inferred conclusion, or report value for a patient based on the at least one medical patient record;

receive a change request relative to the first quality metric from the user input device, the change request being for editing the patient treatment information in the at least one medical patient record used to determine the first quality metric;

change the fact, inferred conclusion, or report value to a different fact, different conclusion, or different report value in the at least one medical patient record for the editing; and

output the first quality metric modified as a function of the different fact, different conclusion, or different report value.

2. The system of claim 1 wherein the processor is configured to output the first quality metric in a quality of care report before receiving the change request, and is configured to output an updated quality of care report with the modified first quality metric.

3. The system of claim 1 wherein the processor is configured to output data, from the at least one medical patient record, supporting the first quality metric.

4. The system of claim 1 wherein the processor is configured to record a user identification associated with the change request.

5. The system of claim 1 wherein the processor is configured to store an annotation received from the user input device, the annotation being for the change request.

6. The system of claim 1 wherein the processor is configured to modify a second quality metric as a function of the change request for the first quality metric.

7. The system of claim 1 wherein the processor is configured to implement a learning function for the first quality metric as a function of the change request.

8. The system of claim 1 wherein the processor is configured to generate a report as a function of selections from the user input device, the first quality metric output in the report.

9. The system of claim 1 wherein the at least one memory is configured to store at least part of the at least one medical patient record as unstructured data, and wherein the processor is configured to extract from, at least in part, the unstructured data, the extraction being probabilistic.

10. The system of claim 1 wherein the at least one memory is operable to store medical patient records for a plurality of patients, and wherein the processor is configured to select a sub-set of the plurality of patients associated with a condition, configured to extract a plurality of quality metrics for each patient of the sub-set, the plurality of quality metrics including the first quality metric, and configured to generate a report as a function of the plurality of quality metrics.

11. The system of claim 1 further comprising:

a display operable to display the quality metric, patient identification, a medical patient record data supporting the quality metric, and a plurality of buttons associated with processor functions;

wherein the user input device is operable to select the buttons.

12. In a non-transitory computer readable storage medium having stored therein data representing instructions executable by a programmed processor for editing medical related quality metric information, the storage medium comprising instructions for:

mining a patient record for patient treatment information related to a plurality of report values, the report values being metrics indicating quality of care related to a guideline or requirement;

deriving the report values from the patient treatment information;

displaying the report values for a patient at a given time;

receiving edit information from a user, the edit information being for editing at least one of a plurality of supporting data values, a relationship between the supporting data values, or both for the at least one of the report values;

changing the at least one of the data values, the relationship, or both based on the edit information, the data values and relationship between the supporting data values representing a state of the patient as indicated by the patient record such that the changing reflects a different state of the patient at the given time; and

generating a report as a function of the changed at least one of the data values, the changed relationship, or both and the report values.

13. The instructions of claim 12 wherein mining comprises mining for data points, and wherein deriving comprises determining each of the report values from a plurality of the data points.

14. The instructions of claim 12 wherein displaying comprises displaying the report values and data, from the patient record, supporting the report value.

15. The instructions of claim 12 further comprising:

storing a user identification associated with the user edit information.

16. The instructions of claim 12 further comprising:

storing an annotation for the user edit information.

17. The instructions of claim 12 wherein the user edit information is of a first report value;

further comprising;

modifying a second report value in response to the user edit information of the first report value.

18. The instructions of claim 12 further comprising:

storing a plurality of user edits;

machine-learning from the user edits; and

updating a function for the deriving as a function of the learning.

19. The instructions of claim 12 wherein mining comprises mining at least some of the information from unstructured data, wherein deriving comprises probabilistically deriving the report values, and wherein displaying comprises displaying probabilities associated with the report values.

20. The instructions of claim 12 wherein mining comprises mining a plurality of patient records for a plurality of patients, including the patient record;

further comprising;

selecting a sub-set of the plurality of patients, the sub-set comprising patients associated with a condition relevant to the report;

wherein deriving comprises deriving for each of the patients; and

wherein generating comprises generating the report summarizing quality of care for the patients associated with the condition.

21. The instructions of claim 12 wherein displaying comprises displaying a plurality of buttons associated with report related functions, and wherein receiving comprises receiving user selection of one of the buttons;

further comprising;

performing the report related function associated with the one of the buttons.

22. A method for editing medical related quality metric information, the method comprising:

extracting, by a processor, facts about a patient from a patient record, the facts representing characteristics of the patient at a given time and reflected in the patient record;

displaying, on a display device, the facts;

receiving, by the processor, an edit to a first one of the facts, the edit being a change of the first one of the facts from a first value to be a different value, the first value and the different value representing one of the characteristics of the patient at the same given time;

changing, by the processor, the first one of the facts in the patient record based on the edit; and

generating, by the processor, a report for at least one quality value calculated from the facts, the generating being as a function of the facts, including the edited first fact.

23. The method of claim 22 further comprising:

displaying evidence from the patient record supporting the first fact.

24. The method of claim 22 wherein extracting comprises extracting from structured and unstructured data of the patient record.

25. The method of claim 22 wherein extracting comprises probabilistically determining the first fact from data of the patient record associated with the first fact.

26. The method of claim 22 wherein displaying comprises displaying an input associated with the first fact, and wherein receiving the edit comprises receiving an entry in the input.

27. The method of claim 22 wherein generating the report comprises generating the report as a function of a user configuration of the report.

28. In a non-transitory computer readable storage medium having stored therein data representing instructions executable by a programmed processor for editing medical related quality metric information, the storage medium comprising instructions for:

providing a report template;

receiving user indication of a plurality of different quality metrics to be included in one report, the different quality metrics indicating quality of care related to a guideline or requirement;

selecting qualifying patients separately from the receiving of the user indication of the plurality of different quality metrics to be included in the one report;

mining a patient record for information associated with the user-indicated quality metrics to be included in the report, the mining extracting the information from the patient record relevant to the different quality metrics received as the user indication; and

generating the report with quality metric values derived from the mined information.

29. The instructions of claim 28 further comprising:

receiving a user edit of a first one of the quality metric values;

wherein generating comprises generating the report with an edited quality metric value.

30. The instructions of claim 28 wherein providing the report template comprises providing a plurality of templates associated with different quality metrics, wherein receiving user indication comprises receiving user selection of a sub-set of the plurality of templates, and wherein generating comprises generating the report as a function of the sub-set of templates.

31. The instructions of claim 28 further comprising:

receiving a user selected parameter value;

wherein mining comprises mining as a function of the user selected parameter value.

32. The instructions of claim 28 wherein mining comprises mining from structured and unstructured information;

and

further comprising;

deriving the quality metric values as a function of probabilities associated with the information.