System and method for minimizing edits for medical insurance claims processing
View Patent ↗A system and method for consolidating edits that facilitate alteration of information of a medical claim. The method includes accessing an edit list. Words of two or more edits of the edit list to determine similarity therebetween may be compared. A new edit based on the similarity between the edits may be formed. In one embodiment, the similarity may be semantic similarity. The method may further include computing a value indicative of the degree of similarity of the words of the edits. Objects may be utilized in the process of consolidating the edits.
1. A method for consolidating edits, said method comprising:
on one or more computers having at least a processor and memory, accessing an edit list, the edit list comprising a plurality of edits applicable to insurance claims, each of the plurality of edits comprising a directive of an insurance provider to correct or reject an insurance claim under specified circumstances, each edit of the plurality of edits having associated therewith an insurance-provider identifier representing the insurance provider;
on the one or more computers, comparing words of at least two edits of the edit list having a same insurance-provider identifier to determine similarity between the directive contained in each of the at least two edits for a specific insurance provider;
wherein the comparison comprises computing a discrete value indicative of a degree of similarity between the at least two edits of the edit list, the discrete value being based on a number of matched words in the at least two edits;
on the one or more computers, reducing a number of the plurality of edits applicable to insurance claims for the specific insurance provider, the reducing comprising consolidating the at least two edits having the same insurance-provider identifier into a new edit based on a comparison of the discrete value to at least a predetermined threshold; and
on the one or more computers, applying the reduced number of the plurality of edits to one or more insurance claims for the specific insurance provider, the application comprising assessing validity of the one or more insurance claims.
2. The method according to claim 1 , wherein said computing includes determining intersection of the words of the edits.
3. The method according to claim 1 , further comprising forming an object containing content of each edit.
4. The method according to claim 3 , further comprising associating the object with other objects having similar edits.
5. The method according to claim 1 , further comprising generating a token associated with at least one word of the at least two edits.
6. The method according to claim 1 , further comprising utilizing a scale to convert the discrete value to a symbolic description of the similarity of the at least two edits.
7. The method according to claim 6 , wherein said utilizing of the scale includes utilizing a Likert scale to determine the similarity of the at least two edits.
8. The method according to claim 7 , wherein said associating includes associating an alphanumeric value to the at least two edits.
9. The method according to claim 1 , further comprising comparing the words of each edit in the edit list, represented as tokens, to the words of each other edit, represented as tokens, in the edit list.
10. The method according to claim 9 , further comprising:
wherein the reducing comprises consolidating selected ones of the edits in the edit list into more than one new edit; and
generating a list of each new edit formed from said consolidation into the more than one new edit.
11. The method according to claim 1 , further comprising sorting the edits of the edit list based on similarity.
12. The method according to claim 11 , further comprising arranging the edits in descending order based on the similarity between the sorted edits.
13. The method according to claim 11 , further comprising creating a single edit from edits being similar to within a predetermined threshold.
14. The method according to claim 11 , further comprising identifying different words used in edits being dissimilar based on a predetermined threshold.
15. The method according to claim 1 , wherein said comparing words of the at least two edits includes comparing the words for semantic similarity.
16. A computer readable medium having computer-executable instructions stored thereon, the computer-executable instructions, when executed by a processor, causing the processor to:
access an edit list, the edit list comprising a plurality of edits applicable to insurance claims, each of the plurality of edits comprising a directive of an insurance provider to correct or reject an insurance claim under specified circumstances, each edit of the plurality of edits having associated therewith an insurance-provider identifier representing the insurance provider;
compare words of at least two edits of the edit list having a same insurance-provider identifier to determine similarity between the directive contained in each of the at least two edits for a specific insurance provider;
wherein the comparison comprises computation of a discrete value indicative of a degree of similarity between the at least two edits of the edit list, the discrete value being based on a number of matched words in the at least two edits;
reduce a number of the plurality of edits applicable to insurance claims for the specific insurance provider, the reduction comprising consolidating the at least two edits having the same insurance-provider identifier into a new edit based on a comparison of the discrete value to at least a predetermined threshold; and
apply the reduced number of the plurality of edits to one or more insurance claims for the specific insurance provider, the application comprising of validity for the one or more insurance claims.
17. The computer readable medium according to claim 16 , wherein the computer-executable instructions, when executed by the processor, further cause the processor to form an object containing content of each edit.
18. The computer readable medium according to claim 17 , wherein the computer-executable instructions, when executed by the processor, further cause the processor to associate the object with other objects having similar edits.
19. The computer readable medium according to claim 16 , wherein the computer-executable instructions, when executed by the processor, further cause the processor to generate a token associated with at least one word of the at least two edits.
20. The computer readable medium according to claim 16 , wherein the computer-executable instructions, when executed by the processor, further cause the processor to utilize a scale to symbolically describe the similarity of the at least two edits.
21. The computer readable medium according to claim 16 , wherein the computer-executable instructions, when executed by the processor, further cause the processor to compare each edit to each other edit in the edit list.
22. The computer readable medium according to claim 21 , further comprising:
wherein the reduction comprises consolidation of selected ones of the edits in the edit list into more than one new edit; and
wherein the computer-executable instructions, when executed by the processor, further cause the processor to generate a list of each new edit formed from said consolidation into the more than one new edit.
23. The computer readable medium according to claim 16 , wherein the computer-executable instructions, when executed by the processor, further cause the processor to sort the edits of the edit list based on similarity.
24. The computer readable medium according to claim 23 , wherein the computer-executable instructions, when executed by the processor, further cause the processor to create a single edit from edits being similar to within a predetermined threshold.
25. The computer readable medium according to claim 23 , wherein the computer-executable instructions, when executed by the processor, further cause the processor to identify different words used in edits being dissimilar based on a predetermined threshold.
26. The computer readable medium according to claim 16 , wherein the new edit is formed based on semantic similarity between the at least two edits.
27. A system for consolidating edits that facilitate alteration of information of an insurance claim, said system comprising:
a processor operable to execute software having instructions to:
access an edit list, the edit list comprising a plurality of edits applicable to insurance claims, each of the plurality of edits comprising a directive of an insurance provider to correct or reject an insurance claim under specified circumstances, each edit of the plurality of edits having associated therewith an insurance-provider identifier representing the insurance provider;
compare words of at least two edits of the edit list having a same insurance-provider identifier to determine similarity between the directive contained in each of the at least two edits for a specific insurance provider;
wherein the comparison comprises computation of a discrete value indicative of a degree of similarity between the at least two edits of the edit list, the discrete value being based on a number of matched words in the at least two edits;
reduce a number of the plurality of edits applicable to insurance claims for the specific insurance provider, the reduction comprising consolidating the at least two edits having the same insurance-provider identifier into a new edit based on a comparison of the discrete value to at least a predetermined threshold; and
apply the reduced number of the plurality of edits to one or more insurance claims for the specific insurance provider, the application comprising assessment of validity for the one or more insurance claims.
28. The system according to claim 27 , wherein the instructions to compute a discreet value indicative of the degree of similarity between the at least two edits further include instructions to determine intersection of the words of the at least two edits.
29. The system according to claim 27 , wherein the software further includes instructions to form an object containing content of each edit.
30. The system according to claim 29 , wherein the software further includes instructions to associate the object with other objects having similar edits.
31. The system according to claim 29 , wherein the software further includes instructions to sort the edits based on degree of similarity.
32. The system according to claim 31 , wherein the software further includes instructions to sort the edits in decreasing order of similarity.
33. The system according to claim 31 , wherein the software further includes instructions to form a single edit from multiple edits being similar to within a predetermined threshold of similarity.
34. The system according to claim 31 , wherein the software further includes instructions to identify different words used in edits being dissimilar based on a predetermined threshold.
35. The system according to claim 27 , wherein the software further includes instructions to generate a token associated with the words of the edit.
36. The system according to claim 27 , wherein the software further includes instructions to:
utilize a scale to convert the discrete value to a symbolic description of the similarity of the at least two edits.
37. The system according to claim 27 , wherein the software further includes instructions to compare each edit to each other edit in the edit list.
38. The system according to claim 37 , further comprising:
wherein the reducing comprises consolidating selected ones of the edits in the edit list into more than one new edit; and
wherein the software further includes instructions to generate a list of each new edit formed from said consolidation into the more than one new edit.
39. The system according to claim 27 , wherein the software further includes instructions to form the new edit based on semantic similarity of the at least two edits.