System and method to regularize cancer treatment data for systematic recording
Implementations provide a method to consolidate data records of regimens for treating oncology conditions. The method includes: accessing data records each encoding multi-tier data characteristics of a regimen for treating a particular oncology condition; receiving a first data record encoding a first regimen specific to a first healthcare provider institution; parsing the first data record according to a hierarchy of the encoded multi-tier data characteristics; distributing a respective weight to each of the encoded data characteristics to account for the potentially missing data characteristic; comparing data characteristics of the first data record with data characteristics from the data records by applying the respective weight to each data characteristic at a particular tier of the hierarchy such that a respective compound score is generated for each data record; and based on the compound scores for all data records, determining a prevailing data record of regimen as matching the first data record.
1. A method comprising:
parsing, based on a data structure hierarchy, a first data record that represents a first regimen for a disease, wherein the data structure hierarchy indicates a hierarchy for data records in a database, wherein the first data record has been encoded into a set of multi-tier characteristics, wherein each level of the set of multi-tier characteristics represents a respective trait of a treatment to a disease for a de-identified patient,
based on parsing the first data record and in response to determining that the first regimen is mapped in the database, providing a second regimen of a prevailing data record in the database as a match for the first regimen, and
based on parsing the first data record and in response to determining that the first regimen is not mapped in the database, obtaining a score indicative of a degree of match between the first regimen and the second regimen.
2. The method of claim 1 , further comprising:
benchmarking the first regimen based on an efficacy of the second regimen.
3. The method of claim 1 , further comprising:
recording treatment data during a course of the first regimen; and
comparing the treatment data during the course of the first regimen with the prevailing data record.
4. The method of claim 3 , further comprising:
based on comparing the treatment data with the prevailing data record, refining a set of weights to the set of multi-tier data characteristics.
5. The method of claim 1 , wherein obtaining the score comprises applying a set of weights to the set of multi-tier data characteristics of the data structure hierarchy, wherein each weight in the set of weights is applied to a corresponding data characteristic of the set of multi-tier data characteristics.
6. The method of claim 5 , further comprising:
identifying, based on applying the set of weights to the set of multi-tier data characteristics, the prevailing data record in the database.
7. The method of claim 5 , further comprising:
in response to determining that a data characteristic of the data structure hierarchy is absent from the first data record, flagging the data characteristic as missing.
8. The method of claim 1 , wherein the score indicative of a degree of match is based on comparing a first score and a second score, wherein the first score is based on the set of multi-tier data characteristics encoded from the first data record, and the second score is based on a second set of multi-tier data characteristics encoded from the prevailing data record.
9. A computer system comprising one or more processors, wherein the one or more processors are configured to perform operations of:
parsing, based on a data structure hierarchy, a first data record that represents a first regimen for a disease, wherein the data structure hierarchy indicates a hierarchy for data records in a database, wherein the first data record has been encoded into a set of multi-tier characteristics, wherein each level of the set of multi-tier characteristics represents a respective trait of a treatment to a disease for a de-identified patient,
based on parsing the first data record and in response to determining that the first regimen is mapped in the database, providing a second regimen of a prevailing data record in the database as a match for the first regimen, and
based on parsing the first data record and in response to determining that the first regimen is not mapped in the database, obtaining a score indicative of a degree of match between the first regimen and the second regimen.
10. The computer system of claim 9 , further comprising:
benchmarking the first regimen based on an efficacy of the second regimen.
11. The computer system of claim 9 , further comprising:
recording treatment data during a course of the first regimen; and
comparing the treatment data during the course of the first regimen with the prevailing data record.
12. The computer system of claim 11 , further comprising:
based on comparing the treatment data with the prevailing data record, refining a set of weights to the set of multi-tier data characteristics.
13. The computer system of claim 9 , wherein obtaining the score comprises applying a set of weights to the set of multi-tier data characteristics, wherein each weight in the set of weights is applied to a corresponding data characteristic of the set of multi-tier data characteristics.
14. The computer system of claim 13 , further comprising:
identifying, based on applying the set of weights to the set of multi-tier data characteristics, the prevailing data record in the database.
15. The computer system of claim 13 , further comprising:
in response to determining that a data characteristic of the data structure hierarchy is absent from the first data record, flagging the data characteristic as missing.
16. The computer system of claim 9 , wherein the score indicative of a degree of match is based on comparing a first score and a second score, wherein the first score is based on the set of multi-tier data characteristics encoded from the first data record, and the second score is based on a second set of multi-tier data characteristics encoded from the prevailing data record.
17. A non-transitory computer-readable medium, comprising software instructions, that when executed by a computer, cause the computer to execute operations comprising:
parsing, based on a data structure hierarchy, a first data record that represents a first regimen for a disease, wherein the data structure hierarchy indicates a hierarchy for data records in a database, wherein the first data record has been encoded into a set of multi-tier characteristics, wherein each level of the set of multi-tier characteristics represents a respective trait of a treatment to a disease for a de-identified patient,
based on parsing the first data record and in response to determining that the first regimen is mapped in the database, providing a second regimen of a prevailing data record in the database as a match for the first regimen, and
based on parsing the first data record and in response to determining that the first regimen is not mapped in the database, obtaining a score indicative of a degree of match between the first regimen and the second regimen.
18. The non-transitory computer-readable medium of claim 17 , wherein the operations further comprise:
benchmarking the first regimen based on an efficacy of the second regimen.
19. The non-transitory computer-readable medium of claim 17 , wherein the operations further comprise:
recording treatment data during a course of the first regimen; and
comparing the treatment data during the course of the first regimen with the prevailing data record.
20. The non-transitory computer-readable medium of claim 19 , wherein the operations further comprise:
based on comparing the treatment data with the prevailing data record, refining a set of weights to the set of multi-tier data characteristics.