System and method to regularize cancer treatment data for systematic recording

1. A computer-implemented method comprising:

parsing a first data record according to a hierarchy of a set of multi-tier data characteristics, wherein:

a set of data records stored at a central server encode the hierarchy,

the hierarchy characterizes a set of regimens,

the set of regimens relate to treating an oncology condition,

the first data record is received from and managed by a first healthcare provider institution and further encodes a first regimen for treating the particular oncology condition, and

the first regimen is specific to the first healthcare provider institution;

in response to determining that a data characteristic at a tier of the hierarchy is absent from the first data record, flagging the data characteristic as missing;

generating a set of compound scores by applying a set of weights to the multi-tier data characteristics according to the hierarchy to account for the data characteristic flagged as missing, wherein each weight in the set of weights is applied to a corresponding data characteristic of the multi-tier data characteristics;

comparing a first set of compound scores for a first set of data characteristics of the first data record with a second set of compound scores for a second set of data characteristics from the set of data records to indicate a degree of match; and

based on the set of compound scores, determining a prevailing data record as matching the first data record such that when a data record encoding the first regimen is received, the prevailing data record is presented without repeating the generating of the set of compound scores.

2. The computer-implemented method of claim 1 , further comprising:

receiving, from a second healthcare provider institution that is different from the first healthcare provider institution, a second data record encoding a second regimen for treating the oncology condition, the second regimen being specific to the second healthcare provider institution;

parsing the second data record according to the hierarchy of the multi-tier data characteristics; and

in response to determining that the second regimen encoded by the second data record corresponds to the first regimen, presenting the prevailing data record without repeating the comparing of the multi-tier data characteristics.

3. The computer-implemented method of claim 1 , wherein determining the prevailing data record comprises:

in response to determining that a set of compound score for a data record from the set of data records encoding a regimen exceeds the respective sets of compound scores for remaining data records from the set of data records by a threshold value, choosing the data record as the prevailing data record.

4. The computer-implemented method of claim 1 , wherein determining the prevailing data record comprises:

in response to determining that respective sets of compound scores for more than a threshold number of data records from the set of data records are within a margin, re-distributing a new respective weight to each data characteristic of the multi-tier data characteristics in the hierarchy.

5. The computer-implemented method of claim 1 , wherein comparing a first set of compound scores for a first set of data characteristics of the first data record with a second set of compound scores for a second set of data characteristics from the set of data records stored at the central server comprises:

comparing data characteristics of administering a cocktail of multiple drugs as encoded by the first data record with data characteristics from the data records that include the multiple drugs.

6. The computer-implemented method of claim 1 , wherein comparing a first set of compound scores for a first set of data characteristics of the first data record with a second set of compound scores for a second set of data characteristics from the set of data records stored at the central server comprises:

comparing data characteristics of multiple administrations involving a cocktail of multiple drugs as encoded by the first data record with data characteristics from the data records that include the multiple drugs.

7. The computer-implemented method of claim 1 , wherein comparing a first set of compound scores for a first set of data characteristics of the first data record with a second set of compound scores for a second set of data characteristics from the set of data records stored at the central server comprises:

comparing data characteristics of administering a brand name drug as encoded by the first data record with data characteristics from the data records that include the brand name drug based on a matching standard that is higher than that of a generic drug.

8. The computer-implemented method of claim 1 , further comprising:

accessing a data object representing a first tier of information encoding a cocktail combination of drugs for treating the oncology condition, a second tier of information encoding cycles for each drug from the cocktail combination of the first tier for treating the oncology condition, and a third tier of information encoding administration details of administering each drug from the cocktail combination of the first tier during cycles from the second tier.

9. The computer-implemented method of claim 8 , wherein the set of compound score is generated by combining contributions from the multi-tier data characteristics at all three tiers.

10. The computer-implemented method of claim 9 ,

wherein the data object encodes the multi-tier data characteristics on an ladder of importance, and

wherein combining contributions from the multi-tier data characteristics at all three tiers comprises:

applying a respective weight to each tier of the multi-tier data characteristics by allocating more weight at levels that are higher in the hierarchy, and less weight to the data characteristics flagged as potentially missing.

11. A computer system comprising one or more processors configured to perform operations of:

parsing a first data record according to a hierarchy of a set of multi-tier data characteristics, wherein:

a set of data records stored at a central server encode the hierarchy,

the hierarchy characterizes a set of regimens,

the set of regimens relate to treating an oncology condition,

the first data record is received from and managed by a first healthcare provider institution and further encodes a first regimen for treating the oncology condition, and

the first regimen is specific to the first healthcare provider institution;

in response to determining that a data characteristic at a tier of the hierarchy is absent from the first data record, flagging the data characteristic as missing;

generating a set of compound scores by applying a set of weights to the multi-tier data characteristics according to the hierarchy to account for the data characteristic flagged as missing, wherein each weight in the set of weights is applied to a corresponding data characteristic of the multi-tier data characteristics;

comparing a first set of compound scores for a first set of data characteristics of the first data record with a second set of compound scores for a second set of data characteristics from the set of data records to indicate a degree of match; and

based on the set of compound scores, determining a prevailing data record as matching the first data record such that when a data record encoding the first regimen is received, the prevailing data record is presented without repeating the generating of the set of compound scores.

12. The computer system of claim 11 , wherein the operations further comprise:

receiving, from a second healthcare provider institution that is different from the first healthcare provider institution, a second data record encoding a second regimen for treating the oncology condition, the second regimen being specific to the second healthcare provider institution;

parsing the second data record according to the hierarchy of the multi-tier data characteristics; and

in response to determining that the second regimen encoded by the second data record corresponds to the first regimen, presenting the prevailing data record without repeating the comparing of the multi-tier data characteristics.

13. The computer system of claim 11 , wherein determining the prevailing data record comprises:

in response to determining that a set of compound score for a data record from the set of data records encoding a regimen exceeds the respective sets of compound scores for remaining data records from the set of data records by a threshold value, choosing the data record as the prevailing data record.

14. The computer system of claim 11 , wherein determining the prevailing data record comprises:

in response to determining that respective sets of compound scores for more than a threshold number of data records from the set of data records are within a margin, re-distributing a new respective weight to each data characteristic of the multi-tier data characteristics in the hierarchy.

15. The computer system of claim 11 , wherein comparing a first set of compound scores for a first set of data characteristics of the first data record with a second set of compound scores for a second set of data characteristics from the set of data records stored at the central server comprises:

comparing data characteristics of administering a cocktail of multiple drugs as encoded by the first data record with data characteristics from the data records that include the multiple drugs.

16. The computer system of claim 11 , wherein comparing a first set of compound scores for a first set of data characteristics of the first data record with a second set of compound scores for a second set of data characteristics from the set of data records stored at the central server comprises:

comparing data characteristics of multiple administrations involving a cocktail of multiple drugs as encoded by the first data record with data characteristics from the data records that include the multiple drugs.

17. The computer system of claim 11 , wherein comparing a first set of compound scores for a first set of data characteristics of the first data record with a second set of compound scores for a second set of data characteristics from the set of data records stored at the central server comprises:

comparing data characteristics of administering a brand name drug as encoded by the first data record with data characteristics from the data records that include the brand name drug based on a matching standard that is higher than that of a generic drug.

18. The computer system of claim 11 , wherein accessing data records each encoding a multi-tier data characteristics of a regimen for treating a particular oncology condition comprises:

accessing a data object representing a first tier of information encoding a cocktail combination of drugs for treating the oncology condition, a second tier of information encoding cycles for each drug from the cocktail combination of the first tier for treating the oncology condition, and a third tier of information encoding administration details of administering each drug from the cocktail combination of the first tier during cycles from the second tier.

19. The computer system of claim 18 , wherein the set of compound score is generated by combining contributions from the multi-tier data characteristics at all three tiers.

20. The computer system of claim 19 ,

wherein the data object encodes the multi-tier data characteristics on an ladder of importance, and

wherein combining contributions from the multi-tier data characteristics at all three tiers comprises:

applying a respective weight to each tier of the multi-tier data characteristics by allocating more weight at levels that are higher in the hierarchy, and less weight to the data characteristics flagged as potentially missing.