Classification code parser

1. A method of operating a classification code parser comprising:

reading a classification code having a description;

reading a required keyword, and a total number of keywords associated with the classification code;

reading text of a note;

tokenizing the text of the note with a central processing unit to create a note token stream, the note token stream having a note token and a position of the note token within the note token stream;

creating a keyword map including the required keyword associated with the position based on the required keyword matching the note token, and the keyword map including a total number of matched keywords;

determining a match ratio from the total number of the matched keywords and the total number of the keywords;

determining a proximity factor based on a shortest span of tokens within the note token stream containing all the matched keywords; and

determining a strength of a match between the classification code and the note based on the match ratio being multiplied by the proximity factor with the central processing unit.

2. The method of claim 1 wherein reading the classification code includes reading an ICD-O-3 code.

3. The method of claim 1 wherein reading the classification code includes reading the classification code having a behavior code;

further comprising determining a behavior factor according to the following equation:

if the behavior code is “3”; or

if the behavior code is “2” and the description contains “non-invasive”;

then the behavior factor is 1.5;

otherwise, the behavior factor is 1.0; and

wherein determining the strength includes multiplying the match ratio, the proximity factor, and the behavior factor.

4. The method of claim 3 further comprising calculating a length bonus according to the following equation:

length bonus=0.01*Σ b k

where b k is a largest value between (c−6) and 0, where c is a number of characters in one of the matched keywords, where Σ indicates that b k for each of the matched keywords should be summed; and

wherein determining the strength is calculated according to the following equation:

x=m*b*p,

if x> 0 then strength= x +lb,

else strength= x,

where m is the match ratio, where b is the behavior factor, where p is the proximity factor, and where lb is the length bonus.

5. The method of claim 1 wherein determining the match ratio includes determining the match ratio according to the following equation:

match ratio= k 2 /m,

where k is the total number of the matched keywords and where m is the total number of the keywords.

6. The method of claim 1 wherein determining the proximity factor includes determining the proximity factor according to the following equation:

proximity factor=1/(1+ e/ 50),

where e is a largest value between (s−m) and 0, where s is the shortest span of tokens within the note token stream containing all the matched keywords, and where m is a total number of the keywords in the classification code.

7. The method of claim 1 further comprising:

reading a secondary keyword and an ignored token;

determining a primary keyword as any of the keywords that are not the required keyword, the secondary keyword, or the ignored token; and

determining whether the primary keyword matches a second note token within the note token stream.

8. The method of claim 1 wherein tokenizing the text further includes:

reading a special token; and

converting the text to lowercase unless the text matches the special token.

9. The method of claim 1 wherein tokenizing the text further includes:

reading a description synonym; and

replacing the note token with the descriptive synonym based on the note token matching the descriptive synonym.

10. The method of claim 1 wherein tokenizing the text further includes:

splitting the note into a sentence;

identifying a negative term; and

deleting a portion of the sentence from the negative term to an end of the sentence.

11. A non-transitory computer readable medium in useful association with a processor having instructions configured to:

read a classification code having a description;

read a required keyword, and a total number of keywords associated with the classification code;

read text of a note;

tokenize the text of the note with a central processing unit to create a note token stream, the note token stream having a note token and a position of the note token within the note token stream;

create a keyword map including the required keyword associated with the position based on the required keyword matching the note token, and the keyword map including a total number of matched keywords;

determine a match ratio from the total number of the matched keywords and the total number of the keywords;

determine a proximity factor based on a shortest span of tokens within the note token stream containing all the matched keywords; and

determine a strength of a match between the classification code and the note based on the match ratio being multiplied by the proximity factor with the central processing unit.

12. The computer readable medium of claim 11 wherein the instructions configured to read the classification code includes instructions configured to read an ICD-O-3 code.

13. The computer readable medium of claim 11 wherein the instructions configured to read the classification code includes instructions configured to read the classification code having a behavior code;

further comprising instructions configured to determine a behavior factor according to the following equation:

if the behavior code is “3”; or

if the behavior code is “2” and the description contains “non-invasive”;

then the behavior factor is 1.5;

otherwise, the behavior factor is 1.0; and

wherein the instructions configured to determine the strength includes instructions configured to multiply the match ratio, the proximity factor, and the behavior factor.

14. The computer readable medium of claim 13 further comprising instructions configured to calculate a length bonus according to the following equation:

length bonus=0.01*Σ b k

where b k is a largest value between (c−6) and 0, where c is the number of characters in one of the matched keywords, where Σ indicates that b k for each of the matched keywords should be summed; and

wherein the instructions configured to determine the strength include instructions configured to calculate the strength according to the following equation:

x=m*b*p,

if x> 0 then strength= x +lb,

else strength= x,

where m is the match ratio, where b is the behavior factor, where p is the proximity factor, and where lb is the length bonus.

15. The computer readable medium of claim 11 wherein the instructions configured to determine the match ratio includes instructions configured to determine the match ratio according to the following equation:

match ratio= k 2 /m,

where k is the total number of the matched keywords and where m is the total number of the keywords.

16. The computer readable medium of claim 11 wherein the instructions configured to determine the proximity factor includes instructions configured to determine the proximity factor according to the following equation:

proximity factor=1/(1+ e/ 50),

where e is a largest value between (s−m) and 0, where s is the shortest span of tokens within the note token stream containing all the matched keywords, and where m is the total number of the keywords in the classification code.

17. The computer readable medium of claim 11 further comprising instructions configured to:

read a secondary keyword and an ignored token;

determine a primary keyword as any of the keywords that are not the required keyword, the secondary keyword, or the ignored token; and

determine whether the primary keyword matches a second note token within the note token stream.

18. The computer readable medium of claim 11 wherein the instructions configured to tokenize the text further includes instructions configured to:

read a special token; and

convert the text to lowercase unless the text matches the special token.

19. The computer readable medium of claim 11 wherein the instructions configured to tokenize the text further includes instructions configured to:

read a description synonym; and

replace the note token with the descriptive synonym based on the note token matching the descriptive synonym.

20. The computer readable medium of claim 11 wherein the instructions configured to tokenize the text further includes instructions configured to:

split the note into a sentence;

identify a negative term; and

delete a portion of the sentence from the negative term to an end of the sentence.