Determining erroneous codes in medical reports

A non-transitory computer readable medium having stored instruction which, when executed by a processor, cause the processor to:

• obtain a medical report comprising a plurality of codes, each code representing a comment comprising clinical information;
• generate a respective vector representation for each of the plurality of codes in the medical report, wherein values of a vector representation for a code of the plurality of codes are generated based on relation of the code in a set of reference medical reports to other codes in the set of reference medical reports, wherein relative values of a pair of vector representations are correlated with a co-occurrence of corresponding codes in the set of reference medical reports,
• wherein the respective vector representation is generated by converting the code into a plurality of position values that each represent a position in a dimension of a hyper dimensional vector space, each position value determined to reflect a frequency that the code co-occurs with a respective one of the other codes in the set of reference medical reports and assigned to a vector component of the respective vector representation;
• identify at least one of the generated vector representations as an outlying vector representation relative to other vector representations for the plurality of codes in the medical report, wherein said identifying comprises determining that the at least one generated vector representations is separated by more than a threshold separation from the other vector representations based on the position values in the hyper dimensional vector space;
• and
• determine, based on the identification of the at least one generated vector representation as being an outlier and the position values in the hyper dimensional space, that the code represented by the at least one generated vector is an erroneous code in the medical report.

A system for determining an erroneous code in a medical report;

• the system comprising:
• a memory comprising a set of instructions;
• a processor configured to communicate with the memory and to execute the set of instructions, wherein the set of instructions, when executed by the processor, cause the processor to:
• obtain a medical report comprising a plurality of codes, each code representing a comment comprising clinical information;
• generate a respective vector representation for each of the plurality of codes in the medical report, wherein values of a vector representation for a code of the plurality of codes are generated based on relation of the code in a set of reference medical reports to other codes in the set of reference medical reports, wherein relative values of any pair of vector representations are correlated with a co-occurrence of corresponding codes of the pair of vector representations in the set of reference medical reports,
• wherein the respective vector representation is generated by converting the code into a plurality of position values that each represent a position in a dimension of a hyper dimensional vector space, each position value determined to reflect a frequency that the code co-occurs with a respective one of the other codes in the set of reference medical reports and assigned to a vector component of the respective vector representation;
• identify at least one of the generated vector representations as an outlying vector representation relative to other vector representations for the plurality of codes in the medical report, wherein said identifying comprises determining that the at least one generated vector representations is separated by more than a threshold separation from the other vector representations based on the position values in the hyper dimensional vector space;
• and
• determine, based on the identification of the at least one generated vector representation as being an outlier and the position values in the hyper dimensional space, that the code represented by the at least one generated vector is an erroneous code in the medical report.