Methods, systems and computer program products for associating records in healthcare databases with individuals

• US 20060080312A1
• Filed: 10/12/2004
• Published: 04/13/2006
• Est. Priority Date: 10/12/2004
• Status: Active Grant

• Current Assignee: Kyndryl Incorporated
• Original Assignee: International Business Machines Corporation
• Inventors: Friedlander, Robert R., Khan, Anwer M.
• Granted Patent: US 8,892,571 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/3334 Selection or weighting of terms from queries, including natural language queries
• CPC Class Codes: G06Q 10/00 Administration; Management
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records
• CPC Class Codes: G16H 40/67 for remote operation
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

Methods, systems and computer program products for associating healthcare records in healthcare databases with an individual are provided. One or more attribute types are located in first and second records. The one or more attribute types being associated with the individual. A weighted score is determined for the located at least one attribute type based on a comparison of the located at least one attribute type in the first record and the located at least one attribute type in the second record. The weighted score indicates a likelihood that the located at least one attribute type in the first and second records are both associated with the individual. A confidence is provided and is associated with the first and second records based on the weighted score. The confidence score indicates a likelihood that both the first and second records are associated with the individual.

Claims

1. A method of associating healthcare records in healthcare databases with an individual, comprising:

locating at least one attribute type in first and second records, the at least one attribute type being associated with the individual;

determining a weighted score for the located at least one attribute type based on a comparison of the located at least one attribute type in the first record and the located at least one attribute type in the second record, the weighted score indicating a likelihood that the located at least one attribute type in the first and second records are associated with the individual; and

providing a confidence score associated with the first and second records based on the weighted score, the confidence score indicating a likelihood that the first and second records are associated with the individual.

2. The method of claim 1, wherein providing the confidence score comprises applying logic to the weighted score.

3. The method of Claim 1, wherein the first and second records are located in first and second databases, respectively.

4. The method of claim 3, wherein the first and second databases are the same database.

5. The method of claim 1, wherein locating the at least one attribute type comprises:

obtaining the at least one attribute type associated with the individual from the first record in a first database on a local server; and

locating the obtained at least one attribute type in the second record in a second database on a remote server.

6. The method of claim 1, wherein the at least one attribute type comprises a first name, last name, a social security number, a gender, a birth date, an address, a telephone number, a birth place, a blood type, an age, a height, a weight, eye color, hair color, race and/or a gene signature.

7. The method of claim 1, further comprising:

assigning the individual an identifier so as to allow future identification of the individual; and

associating the identifier with the first and second records if the confidence score meets a predetermined threshold.

8. The method of claim 1, further comprising combining information in the first and second records into a third complete record if the confidence score meets a predetermined threshold.

9. The method of claim 1:

wherein locating at least one attribute type comprises locating a first attribute type associated with the individual in the first and second records and locating a second attribute type associated with the individual in the first and second records;

wherein determining a weighted score comprises determining a first weighted score based on a comparison of the located first attribute type in the first record and the located first attribute type in the second record and determining a second weighted score based on a comparison of the located second attribute type in the first record and the located second attribute type in the second record; and

wherein providing the confidence score comprises applying logic to the first and second weighted scores to provide the confidence score associated with the first and second records based on the first and second weighted scores.

10. The method of claim 1, carried out by a computer program product embodied in a computer readable medium.

11. A method of associating healthcare records in healthcare databases with an individual comprising providing a confidence score associated with first and second records based on a comparison of at least one attribute type located in the first record and the second record, the confidence score indicating a likelihood that both the first and second records are associated with the individual.

12. The method of claim 11, carried out by a computer program product embodied in a computer readable medium.

13. A system for associating healthcare records in healthcare databases with an individual, comprising:

a location circuit configured to locate at least one attribute type in first and second records, the at least one attribute type being associated with the individual;

a statistical module configured to compare the located at least one attribute type in the first record and the located at least one attribute type in the second record and determine a weighted score based on the comparison indicating a likelihood that the located at least one attribute type in the first and second records are both associated with the individual; and

an identification circuit configured to provide a confidence score associated with the first and second records based on the weighted score, the confidence score indicating a likelihood that both the first and second records are associated with the individual.

14. The system of claim 13, wherein the identification circuit is further configured to apply logic to the weighted scores to provide the confidence score.

15. The system of claim 13, wherein the first and second records are located in first and second databases, respectively.

16. The system of claim 15, wherein the first and second databases are the same database.

17. The system of claim 13, wherein the location circuit is further configured to:

obtain the at least one attribute type associated with the individual from the first record in a first database on a local server; and

locate the obtained at least one attribute type in the second record in a second database on a remote server.

18. The system of claim 13, wherein the at least one attribute type comprises a first name, a last name, a social security number, a gender, a birth date, an address, a telephone number, a birth place, a blood type, an age, a height, a weight, eye color, hair color, race and/or a gene signature.

19. The system of claim 13, wherein the identification circuit is further configured to:

assign the individual an identifier so as to allow future identification of the individual; and

associate the identifier with the first and second records if the confidence score meets a predetermined threshold.

20. The system of claim 13, wherein the identification circuit is further configured to combine information in the first and second records into a third complete record if the confidence score meets a predetermined threshold.