Code Point Resolution Using Natural Language Processing and Metathesaurus

Abstract

A system and related method exchange medical information with a medical management system. The method comprises receiving, using a processor of a code point resolver, from the medical management system, medical text via a network interface. A code point is a single standardized medical terminology code (SMTC) that corresponds to a medical concept contained within the medical text. The method further applies rule-based logic to process the medical text to form a localized mapping of a text portion of the medical text to a plurality of candidate SMTCs (CSMTCs) that are related to at least one metathesaurus concept entity (MCE) in a metathesaurus, and to determines the code point from the CSMTCs. The method transmits, via the network interface, to the medical management system, the code point.

1 . A method for exchanging medical information with a medical management system, comprising:
 receiving, using a processor of a code point resolver, from the medical management system, medical text via a network interface, wherein a code point is a single standardized medical terminology code (SMTC) that corresponds to a medical concept contained within the medical text;   applying rule-based logic to process the medical text to form a localized mapping of a text portion of the medical text to a plurality of candidate SMTCs (CSMTCs) that are related to at least one metathesaurus concept entity (MCE) in a metathesaurus and to determine the code point from the CSMTCs, wherein applying rule-based logic comprises:
 determining a fitness score with a fitness scorer of the rule-based logic for each of the CSMTCs using weightings that are based on a medical application intent; and 
 determining the code point by selecting a best-fit SMTC having a highest fitness score of the CSMTCs; and 
   transmitting, via the network interface, to the medical management system, the code point.   
     
     
         2 . The method of  claim 1 , wherein the medical text represents a medical application. 
     
     
         3 . The method of  claim 1 , further comprising:
 parsing, with a natural language processor (NLP) of the rule-based logic, the medical text into one or more concepts that are each associated with one or more of the CSMTCs.   
     
     
         4 . The method of  claim 3 , further comprising:
 using the NLP to parse the medical text into medical text portions based on a mechanism selected from the group consisting of punctuation, keywords, and parts of language.   
     
     
         5 . (canceled) 
     
     
         6 . The method of  claim 1 , wherein determining the fitness score comprises utilizing an additional element that is separate from the medical text and is selected from the group consisting of clinical notes and structured data. 
     
     
         7 . The method of  claim 1 , wherein the SMTCs are based on one or more MCEs. 
     
     
         8 . The method of  claim 1 , further comprising filtering, using a relevance determiner of the rule-based logic, the CSMTCs based on a type of medical application. 
     
     
         9 . The method of  claim 1 , wherein the determining of the fitness score comprises using weightings that are further based on at least one of a hypernym and hyponym relationship, a source reliability measure, or codes determined by an industry acceptance rating. 
     
     
         10 . The method of  claim 1 , wherein the weighting for the medical application intent is greater for a procedure than for a non-procedure. 
     
     
         11 . The method of  claim 9 , wherein the weighting for the hypernym and hyponym relationship is greater for the hypernym than for the hyponym. 
     
     
         12 . The method of  claim 9 , wherein the weightings are proportional to a source reliability measure. 
     
     
         13 . The method of  claim 1 , wherein the SMTC is based on an interchange coding system selected from the group consisting of SNOMED, LOINC, and RxNorm. 
     
     
         14 . The method of  claim 1 , further comprising:
 receiving medical input data in addition to the medical text that comprises a first clinical note, a second clinical note different from the first clinical note, and at least one structured data element; and   merging, using the rule-based logic, medical input records from two elements selected from the group consisting of the first clinical note, the second clinical note, and the structured data element, based on dates of the medical input records having compatible codes.   
     
     
         15 . A code point resolver, comprising:
 a memory; and   a processor that is configured to:   receive from the medical management system, medical text via a network interface, wherein a code point is a single standardized medical terminology code (SMTC) that corresponds to a medical concept contained within the medical text;   apply rule-based logic to process the medical text to form a localized mapping of a text portion of the medical text to a plurality of candidate SMTCs (CSMTCs) that are related to at least one metathesaurus concept entity (MCE) in a metathesaurus and to determine the code point from the CSMTCs, wherein applying rule-based logic comprises:
 determining a fitness score with a fitness scorer of the rule-based logic for each of the CSMTCs using weightings that are based on a medical application intent; and 
 determining the code point by selecting a best-fit SMTC having a highest fitness score of the CSMTCs; and 
   transmit, via the network interface, to the medical management system, the code point.   
     
     
         16 . The code point resolver of  claim 15 , wherein applying the rule-based logic further comprises:
 parsing, with a natural language processor (NLP) of the rule-based logic, the medical text into one or more concepts that are each associated with one or more of the CSMTCs.   
     
     
         17 . The code point resolver of  claim 16 , wherein applying the rule-based logic further comprises:
 using the NLP to parse the medical text into medical text portions based on a mechanism selected from the group consisting of punctuation, keywords, and parts of language.   
     
     
         18 . (canceled) 
     
     
         19 . A computer program product for a code point resolver, the computer program product comprising:
 one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions comprising program instructions to:   receive, using a processor of a code point resolver, from the medical management system, medical text via a network interface, wherein a code point is a single standardized medical terminology code (SMTC) that corresponds to a medical concept contained within the medical text;   apply rule-based logic to process the medical text to form a localized mapping of a text portion of the medical text to a plurality of candidate SMTCs (CSMTCs) that are related to at least one metathesaurus concept entity (MCE) in a metathesaurus and to determine the code point from the CSMTCs, wherein applying rule-based logic comprises:
 determining a fitness score with a fitness scorer of the rule-based logic for each of the CSMTCs using weightings that are based on a medical application intent; and 
 determining the code point by selecting a best-fit SMTC having a highest fitness score of the CSMTCs; and 
   transmit, via the network interface, to the medical management system, the code point.   
     
     
         20 . The computer program product of  claim 19 , wherein determining the fitness score further comprises using weightings that are further based on at least one of a hypernym and hyponym relationship, a source reliability measure, or codes determined by an industry acceptance rating. 
     
     
         21 . The code point resolver of  claim 15 , wherein determining the fitness score further comprises using weightings that are further based on at least one of a hypernym and hyponym relationship, a source reliability measure, or codes determined by an industry acceptance rating. 
     
     
         22 . The method of  claim 1 , wherein the weightings are applied as a sequence of rules of the rule-based logic to the CSMTCs, wherein the sequence comprises:
 applying a relevance determiner to the CSMTCs to generate a first filtered set of CSMTCs;   determining if the first filtered set of CSMTCs comprises more than one CSMTC;   in response to the first filtered set of CSMTCs comprising more than one CSMTC, applying a weighting to the first filtered set of CSMTCs based on the hypernym and hyponym relationships to generate a second filtered set of CSMTCs;   determining if the second filtered set of CSMTCs comprises more than one CSMTC; and   in response to the second filtered set of CSMTCs comprising more than one CSMTC, applying a weighting to the second filtered set of CSMTCs based on the source reliability measure to generate a third filtered set of CSMTCs.