Method and system for grouping medical claims

• US 10,535,430 B1
• Filed: 07/25/2014
• Issued: 01/14/2020
• Est. Priority Date: 07/25/2014
• Status: Active Grant

• Current Assignee: Merative US LP
• Original Assignee: International Business Machines Corporation
• Inventors: Fischer, Anne Elizabeth, Dunn, Dennis, Pickens, Gary, Moldwin, Elisse Jane, Bouman, Peter Mark, Sirbu, George
• Primary Examiner(s): Holcomb, Mark
• Application Number:
  US14/341,253
• Time in Patent Office: 1,999 Days
• Field of Search: 705 2- 4
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 40/20 for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms

Abstract

A method and system for grouping medical claims data, including outpatient medical claims, into medical events for further analysis is disclosed. Historical outpatient medical claims data is first aggregated by one or more categorization schemes, and then grouped by patient and date. Once the outpatient medical claims data is aggregated and grouped, the methods disclosed build outpatient events by further grouping together disparate medical claims data records that represent a single encounter with an outpatient healthcare system. The outpatient events may be used for analyzing aspects of outpatient care.

Claims

1. A method for grouping medical claims data from a plurality of data sources comprising:

receiving from the plurality of data sources, at a processor, a plurality of medical claims data records each comprising a plurality of data fields;

sorting, at the processor, the plurality of medical claims data records by at least one grouping scheme, wherein the at least one grouping scheme examines at least one data field in each of the plurality of medical claims data records;

building, at the processor, at least one dateblock from the plurality of medical claims data records, wherein building the at least one dateblock comprises;

examining a patient data field and a date data field in each of the plurality of medical claims data records and grouping the medical claims data records together by a first patient and a first date; and

sorting, by the first date, the medical claims data records grouped by the first patient into the at least one dateblock;

prioritizing, at the processor, within the at least one dateblock, the medical claims data records according to the at least one grouping scheme to identify a first priority medical claims data record, wherein a procedure associated with the first priority medical claims data record comprises an anchor procedure for a first medical event;

assigning, by the processor, a match level to each medical claims data record in the set of remaining medical claims data records grouped by the first patient, wherein the match level is selected from a plurality of match levels based on a plurality of matching factors;

matching, by the processor, each medical claims data record in the set of the remaining medical claims data records to a set of the remaining medical claims data records that match the anchor procedure for the first medical event when the assigned match level is above a threshold probability level indicating that the medical claims data records are related to the anchor procedure for the medical event, wherein the probability level is derived from the strength of at least one observed relationship between medical claims data in a set of historical medical claims data;

building, at the processor, within the at least one dateblock, the first medical event, wherein the first medical event comprises the first priority medical claims data record and the set of the remaining medical claims data records that match the anchor procedure for the first medical event; and

applying, by the processor, the first medical event to a healthcare system analysis.

2. The method of claim 1, wherein the plurality of medical claims data records comprise outpatient medical claims data records.

3. The method of claim 1, further comprising building, by the processor, a first output data record, wherein the first output data record comprises summary information about a set of medical claims data related to the first medical event.

4. The method of claim 1, further comprising building, by the processor, a first cross-reference data record, wherein the first cross-reference data record includes a list of medical claims data records included in the first medical event.

5. The method of claim 1, wherein the at least one grouping scheme comprises grouping by procedure type.

6. The method of claim 1, wherein the at least one grouping scheme comprises grouping by a disease category.

7. The method of claim 1, wherein the at least one grouping scheme comprises grouping by a revenue category.

8. The method of claim 1, wherein the at least one grouping scheme comprises grouping by provider type.

9. The method of claim 1, wherein building dateblocks comprises:

determining, by the processor, if the medical claims data records grouped by the first patient comprise at least one of;

a one-day date;

a consecutive two-day date group, or a consecutive three-day date group; and

building, by the processor, at least one of;

a one-day dateblock;

a two-day dateblock;

or a three-day dateblock based on the determination.

10. The method of claim 1, wherein at least one of the plurality of matching factors comprises determining if the anchor procedure is a facility-based anchor procedure.

24. The method of claim 1, wherein building the at least one dateblock further comprises:

estimating an accuracy of the probability level by comparing an observed relationship between medical claims data in a set of historical medical claims data.

25. The method of claim 24, wherein the matching of each medical claims data record in the set of the remaining medical claims data records is limited based on the estimate of the accuracy.

11. A system for grouping disparate outpatient medical claims data, the system comprising:

a database comprising outpatient medical claims data from multiple claims data sources; and

a server coupled to the database;

wherein, the server is further configured to;

receive a plurality of outpatient medical claims data records from the database, each of the plurality of outpatient medical claims data records comprising a plurality of data fields;

sort the plurality of outpatient medical claims data records by at least one grouping scheme, wherein the at least one grouping scheme examines at least one data field in each of the plurality of outpatient medical claims data records;

build at least one dateblock from the plurality of outpatient medical claims data records, wherein building the at least one dateblock comprises;

examining a patient data field and a date data field in each of the plurality of outpatient medical claims data records and grouping the outpatient medical claims data records together by a first patient and a first date; and

sorting, by the first date, the outpatient medical claims data records grouped by the first patient into the at least one dateblock;

prioritize, within the at least one dateblock, the outpatient medical claims data records according to the at least one grouping scheme to identify a first priority outpatient medical claims data record, wherein a procedure associated with the first priority outpatient medical claims data record comprises an anchor procedure for a first outpatient event;

calculate a probability level for each of the remaining medical claims data records grouped by the first patient, wherein the probability level indicates the relation of the medical claims data records to the anchor procedure for the medical event;

assign a match level to each of the remaining medical claims data records grouped by the first patient, wherein the match level is selected from a plurality of match levels based on a rule associated with a plurality of matching factors;

match each medical claims data record in the set of the remaining medical claims data records to a set of the remaining medical claims data records that match the anchor procedure for the first medical event when the probability level of each assigned match is above a match threshold, wherein the match of each of the medical claims data records is limited based on an estimated accuracy of the probability level determined by comparing at least one observed relationship between medical claims data in a set of historical medical claims data;

build, within the at least one dateblock, the first outpatient event, wherein the first outpatient event comprises the first priority outpatient medical claims data record and the set of the remaining outpatient medical claims data records that match the anchor procedure for the first outpatient event; and

apply the first outpatient event to an outpatient system analysis.

12. The system of claim 11, wherein the server is further configured to:

build a first output data record, wherein the first output data record comprises summary information about a set of outpatient medical claims data related to the first outpatient event;

build a first cross-reference data record, wherein the first cross-reference data record includes a list of outpatient medical claims data records included in the first outpatient event;

incorporate at least one of the first output data record and the first cross-reference data record into an outpatient medical claims analysis.

13. The system of claim 12, further comprising:

an access device coupled to the server; and

wherein the server is further configured to;

receive, from the access device, a request for the first output data record and the first cross-reference data record;

forward, to the access device, the first output data record and the first cross-reference data record.

14. The system of claim 11, wherein the at least one grouping scheme comprises grouping by procedure type.

15. The system of claim 11, wherein the at least one grouping scheme comprises grouping by a disease category.

16. The system of claim 11, wherein the at least one grouping scheme comprises grouping by a revenue category.

17. The system of claim 11, wherein building dateblocks further comprises:

determining if the outpatient medical claims data records grouped by the first patient comprise at least one of;

a one-day date;

a consecutive two-day date group, or a consecutive three-day date group; and

building at least one of;

a one-day dateblock;

a two-day dateblock;

or a three-day dateblock based on the determination.

18. A non-transitory computer-readable medium comprising computer-readable instructions for performing the steps of:

receiving from a plurality of data sources, at a processor, a plurality of outpatient medical claims data records;

grouping, by the processor, the plurality of outpatient medical claims data records according to a procedure grouping scheme to identify a procedure type for each of the plurality of outpatient medical claims data records;

aggregating, by the processor, the plurality of outpatient medical claims data records by date to create a plurality of dateblocks, wherein each of the plurality of dateblocks comprises a subset of the plurality of outpatient medical claims data records;

prioritizing, by the processor, in each of the plurality of dateblocks, the respective subset of the plurality of outpatient medical claims data records;

determining, by the processor, in each of the plurality of dateblocks, for a first outpatient medical claims data record having a facility component associated therewith, in the respective subset of the plurality of outpatient medical claims data records, whether the procedure type for the first outpatient medical claims data record falls within a set of procedure types that include both a facility component and a professional component for more than a predetermined frequency based on an analysis of historical grouped medical claims data records, wherein the predetermined frequency is based on an analysis of historical grouped medical claims data records;

linking, by the processor, in each of the plurality of dateblocks, the first outpatient medical claims data record having a facility component associated therewith to a second outpatient medical claims data record having a professional component associated therewith in the respective subset of the plurality of outpatient medical claims data records, based on the determination;

identifying, by the processor, at least one anchor procedure in each of the plurality of dateblocks, the at least one anchor procedure representing at least one of the outpatient medical claims data records in the respective subset of the plurality of outpatient medical claims data records;

applying, by the processor, matching logic to the remaining outpatient medical claims data records in the respective subset of the plurality of outpatient medical claims data records to match at least one remaining outpatient medical claims data records in the respective subset of the plurality of outpatient medical claims data records with the anchor procedure outpatient medical claims data record;

building, by the processor, at least one outpatient event comprising the anchor procedure outpatient medical claims data record and the at least one remaining outpatient medical claims data records in the respective subset of the plurality of outpatient medical claims data records; and

applying, by the processor, at least one outpatient event to an outpatient system analysis.

19. The computer-readable medium of claim 18, further comprising determining, by the processor, in each of the plurality of dateblocks, for the first outpatient medical claims data record having a facility component associated therewith, in the respective subset of the plurality of outpatient medical claims data records, whether the procedure type for the first outpatient medical claims data record falls within a set of procedure types that include both a facility component and a professional component more than 50% of the time based on an analysis of historical grouped medical claims data records.

20. A method for grouping medical claims data from a plurality of data sources comprising:

receiving from the plurality of data sources, at a processor, a plurality of medical claims data records each comprising a plurality of data fields;

building, at the processor, at least one dateblock from the plurality of medical claims data records, wherein building the at least one dateblock comprises;

examining a patient data field and a date data field in each of the plurality of medical claims data records and grouping the medical claims data records together by a first patient and a first date;

sorting, by the first date, the medical claims data records grouped by the first patient into the at least one dateblock;

determining, by the processor, in the at least one dateblock, for a first outpatient medical claims data record, whether a procedure type for the first outpatient medical claims data record falls within a set of procedure types that include both a facility component and a professional component for more than a predetermined frequency based on an analysis of historical grouped medical claims data records, wherein the predetermined frequency is based on an analysis of historical grouped medical claims data records;

linking, by the processor, in the at least one dateblock, the first outpatient medical claims data record having a facility component associated therewith to a second outpatient medical claims data record having a professional component associated therewith, based on the determination;

identifying, by the processor, at least one anchor procedure in the at least one dateblock, the at least one anchor procedure representing at least one of the outpatient medical claims data records in the medical claims data records grouped by the first patient;

applying, by the processor, matching logic to the remaining outpatient medical claims data records in the medical claims data records grouped by the first patient to match at least one remaining outpatient medical claims data records in the medical claims data records grouped by the first patient with the anchor procedure outpatient medical claims data record;

building, by the processor, at least one outpatient event comprising the anchor procedure outpatient medical claims data record and the at least one remaining outpatient medical claims data records in the medical claims data records grouped by the first patient; and

applying, by the processor, the at least one outpatient event to an outpatient system analysis.

21. The method of claim 20, further comprising sorting, at the processor, the plurality of medical claims data records by at least one grouping scheme, wherein the at least one grouping scheme examines at least one data field in each of the plurality of medical claims data records.

22. The method of claim 20, further comprising determining, by the processor, in the at least one dateblock, for a first outpatient medical claims data record having a facility component associated therewith, whether the procedure type for the first outpatient medical claims data record falls within a set of procedure types that include both a facility component and a professional component more than 50% of the time based on an analysis of historical grouped medical claims data records.

23. The method of claim 20, wherein the step of determining further comprises examining, by the processor, a revenue category associated with the procedure type for the first outpatient medical claims data record.