Method and apparatus for identifying matching record candidates

• US 10,510,440 B1
• Filed: 08/04/2014
• Issued: 12/17/2019
• Est. Priority Date: 08/15/2013
• Status: Active Grant

• Current Assignee: Change Healthcare Holdings, LLC (UnitedHealth Group Incorporated)
• Original Assignee: Change Healthcare Holdings, LLC (UnitedHealth Group Incorporated)
• Inventors: Jose, Boban
• Primary Examiner(s): Hein, Devin C
• Application Number:
  US14/450,910
• Time in Patent Office: 1,961 Days
• Field of Search: None
• CPC Class Codes: G16H 10/60 for patient-specific data, e.g. for electronic patient records

Abstract

A method, computing device and computer program product are provided to identify records that are associated with same person, even in instances in which the records are created and stored by different entities. In a method, a plurality of records are received, each having attributes associated with a person. For each record, the method determines a digest by determining a fuzzy representation of one or more of the attributes for the person and then combining representations of the attributes. The method also receives a query relating to a record for the person and determines a digest based upon the attributes of the person. In response to the query, the method identifies one or more records that are associated with respective individuals who are candidates to match the person based upon a comparison of representations of the digests of the records and the person.

Claims

1. A method implemented by a health information infrastructure, the method comprising:

receiving, via a communication interface, a plurality of records, each record having a plurality of demographic attributes associated with an individual, wherein receiving the plurality of records comprises receiving only a portion of a plurality of patient records created by one or more healthcare facilities by receiving, from the one or more healthcare facilities for each of the plurality of patient records created by the one or more healthcare facilities, information defining the demographic attributes associated with the individual, but not receiving information associated with encounters of the individual with a healthcare facility and not receiving documents included in the patient record;

for each record, determining, with processing circuitry, a digest by determining a fuzzy representation of one or more of the plurality of demographic attributes for the respective individual and combining by concatenating into a single string representations of one or more of the plurality of demographic attributes associated with the respective individual including the fuzzy representation of one or more of the plurality of demographic attributes associated with the respective individual;

receiving a query relating to a record for a person and demographic attributes associated with the person;

determining a digest based upon the demographic attributes associated with the person who is a subject of the query, wherein determining the digest comprises determining a fuzzy representation of one or more demographic attributes of the person who is the subject of the query and combining by concatenating into a single string representations of one or more of the demographic attributes of the person who is the subject of the query including the fuzzy representation of one or more demographic attributes of the person who is the subject of the query;

in response to the query, identifying one or more records that are associated with respective individuals who are candidates to match the person based upon a comparison of representations of the digests of the records and a representation of the digest of the person;

for each record that was identified and, as a result, for only a subset of the plurality of records, determining a confidence score by comparing the plurality of demographic attributes associated with the respective individuals to corresponding demographic attributes of the person;

identifying one or more records that are associated with respective individuals who match the person based upon the confidence scores; and

causing at least some of the one or more records that were identified based upon the confidence scores to be associated with respective individuals who are candidates to match the person to be provided via the communication interface.

2. A method according to claim 1 wherein determining a fuzzy representation comprises determining a fuzzy representation of a name by determining a phonetic representation of at least a subset of the name.

3. A method according to claim 1 wherein determining a fuzzy representation comprises determining a fuzzy representation of a date by determining a representation of the date with less specificity than a respective day.

4. A method according to claim 3 wherein determining a representation of the date comprises determining a representation of the date based upon a week, a month, a year or a decade of the respective day.

5. A method according to claim 1 wherein determining a digest comprises determining, for at least some records, a plurality of different digests.

6. A method according to claim 4 wherein the plurality of different digests are based upon a typographical error in a demographic attribute, transposition of first and last names of the respective individual or transposition of a day and month of a date.

7. A method according to claim 1 further comprising hashing the digests of the records and the digest of the person such that the comparison is based upon hashed representations of the digests of the records and a hashed representation of the digest of the person.

8. A method according to claim 1 further comprising communicating with the one or more healthcare facilities via an application programming interface (API) or via a portal application.

9. A computing device of a health information infrastructure, the computing device comprising a processing circuitry configured to:

receive a plurality of records, each record having a plurality of demographic attributes associated with an individual, wherein the plurality of records are received by receiving only a portion of a plurality of patient records created by one or more healthcare facilities by receiving, from the one or more healthcare facilities for each of the plurality of patient records created by the one or more healthcare facilities, information defining the demographic attributes associated with the individual, but not receiving information associated with encounters of the individual with a healthcare facility and not receiving documents included in the patient record;

for each record, determine a digest by determining a fuzzy representation of one or more of the plurality of demographic attributes for the respective individual and combining by concatenating into a single string representations of one or more of the plurality of demographic attributes associated with the respective individual including the fuzzy representation of one or more of the plurality of demographic attributes associated with the respective individual;

receive a query relating to a record for a person and demographic attributes associated with the person;

determine a digest based upon the demographic attributes associated with the person who is a subject of the query, wherein the digest is determined by determining a fuzzy representation of one or more demographic attributes of the person who is the subject of the query and combining by concatenating into a single string representations of one or more of the demographic attributes of the person who is the subject of the query including the fuzzy representation of one or more demographic attributes of the person who is the subject of the query;

in response to the query, identify one or more records that are associated with respective individuals who are candidates to match the person based upon a comparison of representations of the digests of the records and a representation of the digest of the person;

for each record that was identified and, as a result, for only a subset of the plurality of records, determine a confidence score by comparing the plurality of demographic attributes associated with the respective individuals to corresponding demographic attributes of the person;

identify one or more records that are associated with respective individuals who match the person based upon the confidence scores; and

cause at least some of the one or more records that were identified based upon the confidence scores to be associated with respective individuals who are candidates to match the person to be provided via a communication interface.

10. A computing device according to claim 9 wherein the processing circuitry is configured to determine a fuzzy representation by determining a fuzzy representation of a name by determining a phonetic representation of at least a subset of the name.

11. A computing device according to claim 9 wherein the processing circuitry is configured to determine a fuzzy representation by determining a fuzzy representation of a date by determining a representation of the date with less specificity than a respective day.

12. A computing device according to claim 9 wherein the processing circuitry is configured to determine a digest by determining, for at least some records, a plurality of different digests.

13. A computing device according to claim 12 wherein the plurality of different digests are based upon a typographical error in a demographic attribute, transposition of first and last names of the respective individual or transposition of a day and month of a date.

14. A computing device according to claim 9 wherein the processing circuitry is further configured to hash the digests of the records and the digest of the person such that the comparison is based upon hashed representations of the digests of the records and a hashed representation of the digest of the person.

15. A computer program product of a health information infrastructure, the computer program product comprising a non-transitory computer readable storage medium having program code portions stored thereon, the program code portions configured, upon execution, to:

receive a plurality of records, each record having a plurality of demographic attributes associated with an individual, wherein the plurality of records are received by receiving only a portion of a plurality of patient records created by one or more healthcare facilities by receiving, from the one or more healthcare facilities for each of the plurality of patient records created by the one or more healthcare facilities, information defining the demographic attributes associated with the individual, but not receiving information associated with encounters of the individual with a healthcare facility and not receiving documents included in the patient record;

for each record, determine a digest by determining a fuzzy representation of one or more of the plurality of demographic attributes for the respective individual and combining by concatenating into a single string representations of one or more of the plurality of demographic attributes associated with the respective individual including the fuzzy representation of one or more of the plurality of demographic attributes associated with the respective individual;

receive a query relating to a record for a person and demographic attributes associated with the person;

determine a digest based upon the demographic attributes associated with the person who is a subject of the query, wherein the digest is determined by determining a fuzzy representation of one or more demographic attributes of the person who is the subject of the query and combining by concatenating into a single string representations of one or more of the demographic attributes of the person who is the subject of the query including the fuzzy representation of one or more demographic attributes of the person who is the subject of the query;

in response to the query, identify one or more records that are associated with respective individuals who are candidates to match the person based upon a comparison of representations of the digests of the records and a representation of the digest of the person;

for each record that was identified and, as a result, for only a subset of the plurality of records, determine a confidence score by comparing the plurality of demographic attributes associated with the respective individuals to corresponding demographic attributes of the person;

identify one or more records that are associated with respective individuals who match the person based upon the confidence scores; and

cause at least some of the one or more records that were identified based upon the confidence scores to be associated with respective individuals who are candidates to match the person to be provided via a communication interface.

16. A computer program product according to claim 15 wherein the program code portions configured to determine a fuzzy representation comprise program code portions configured to:

determine a fuzzy representation of a name by determining a phonetic representation of at least a subset of the name; and

determine a fuzzy representation of a date by determining a representation of the date with less specificity than a respective day.

17. A computer program product according to claim 15 wherein the program code portions configured to determine a digest comprise program code portions configured to determine, for at least some records, a plurality of different digests.

18. A computer program product according to claim 15 wherein the program code portions are further configured to hash the digests of the records and the digest of the person such that the comparison is based upon hashed representations of the digests of the records and a hashed representation of the digest of the person.