System and method for analyzing de-identified health care data
View Patent ↗A system and method for creating a unique alias associated with an individual identified in a health care database such that health care data, and particularly pharmaceutical-related data, can be efficiently gathered and analyzed. The system has a first store for storing at least one record where each record includes a plurality of identification fields which when concatenated uniquely identify an individual, and at least one health care field corresponding to health care data associated with the individual. The system also has a second data store, and a processor. The processor selects a record of the first data store, then selects a subset of the plurality of identification fields within the selected record, and concatenates the selected subset of identification fields. Then the processor stores the concatenated identification fields in a record in the second store with at least one health care field from the selected record of the first data store.
1. A system for analyzing de-personalized health care data, comprising:
(a) a plurality of health care databases, the plurality of health care databases each including at least one record, each record including a de-personalized yet unique patient identifier associated with a patient, whereby the de-personalized patient identifier is a common value identifying a specific patient across a plurality of health care databases that are associated with distinct database systems of different organizations;
(b) one or more processors in communication with a first of the health care databases, and one or more storage devices storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
(i) receiving a new record from at least one of the plurality of healthcare databases, the new record comprising a plurality of identification fields uniquely identifying a patient associated with the new record;
(ii) concatenating, into a combined textual representation, text from each of the accessed plurality of identification fields included in the new record,
(iii) generating at least one de-personalized yet unique patient identifier associated with the patient by encrypting the concatenated text of the combined textual representation; and
(iv) storing, in a first of the health care databases, at least a portion of the received new record in association with the least one de-personalized yet unique patient identifier.
2. A method for de-identifying health care data comprising:
receiving a new record from at least one of a plurality of health care databases, the new record comprising a plurality of identification fields uniquely identifying a patient associated with the new record;
concatenating, into a combined textual representation, text from each of the plurality of identification fields included in the new record,
generating at least one de-personalized yet unique patient identifier associated with the patient by encrypting the concatenated text of the combined textual representation, the at least one de-personalized yet unique patient identifier representing a common value identifying the patient across a plurality of health care databases that are associated with distinct database systems of different organizations; and
storing, in a first of the health care databases, at least a portion of the received new record in association with the least one de-personalized yet unique patient identifier.
3. A non-transitory computer-readable medium encoded with instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
receiving a new record from at least one of a plurality of health care databases, the new record comprising a plurality of identification fields uniquely identifying a patient associated with the new record;
concatenating, into a combined textual representation, text from each of the plurality of identification fields included in the new record,
generating at least one de-personalized yet unique patient identifier associated with the patient by encrypting the concatenated text of the combined textual representation, the at least one de-personalized yet unique patient identifier representing a common value identifying the patient across a plurality of health care databases that are associated with distinct database systems of different organizations; and
storing, in a first of the health care databases, at least a portion of the received new record in association with the least one de-personalized yet unique patient identifier.
4. The system of claim 1 , wherein the plurality of identification fields included in the new record comprise one or more of a patient's name, address, social security, contact number, date of birth, or gender.
5. The system of claim 1 , wherein the one or more processors execute instructions that cause the one or more processors to perform operations comprising:
identifying one or more records stored in the first of the health care databases that include the at least one de-personalized yet unique patient identifiers; and
generating a report based on data included in the identified one or more records.
6. The system of claim 1 , wherein the new record comprises one or more healthcare fields that include at least one of pharmaceutical claims data, medical claims data, or hospital claims data.
7. The system of claim 1 , wherein the operations further comprise:
removing, from the portion of the new record that is stored in associated with the at least one de-personalized yet unique patient identifier, information other than the at least one de-personalized yet unique patient identifier that identifies the patient.
8. The system of claim 1 , wherein:
the plurality of identification fields comprises a patient last name field and a patient birthdate field; and
concatenating the text from each of the plurality of identification fields included in the new record comprises concatenating, into the combined textual representation, a first text segment corresponding to a value stored in the patient name field and a second text segment corresponding to a value stored in the patient birthdate field.
9. The method of claim 2 , wherein the plurality of identification fields included in the new record comprise one or more of a patient's name, address, social security, contact number, date of birth, or gender.
10. The method of claim 2 , comprising:
identifying one or more records stored in the first of the health care databases that include the at least one de-personalized yet unique patient identifiers; and
generating a report based on data included in the identified one or more records.
11. The method of claim 2 , wherein the new record comprises one or more healthcare fields that include at least one of pharmaceutical claims data, medical claims data, or hospital claims data.
12. The computer-readable medium of claim 3 , wherein the plurality of identification fields included in the new record comprise one or more of a patient's name, address, social security, contact number, date of birth, or gender.
13. The computer-readable medium of claim 3 , wherein the operations comprise:
identifying one or more records stored in the first of the health care databases that include the at least one de-personalized yet unique patient identifiers; and
generating a report based on data included in the identified one or more records.
14. The computer-readable medium of claim 3 , wherein the new record comprises one or more healthcare fields that include at least one of pharmaceutical claims data, medical claims data, or hospital claims data.