Method and system to align two coding standards

A method of aligning codes between two coding standards, comprising:

• collecting established mappings between pairs of codes of two coding standards among coding standards, from an internet and from existing machine-readable publications, using text analysis techniques;
• accessing the two coding standards including descriptions accompanying each code of the pairs of codes, and finding a syntactical similarity of the pairs of codes of the two coding standards using the descriptions to provide syntactical mappings, using text similarity measures;
• accessing existing cases annotated with both of the two coding standards, and finding any case-based mappings between pairs of codes of the two coding standards from the existing cases that are annotated with both coding standards, based on individual cases annotated with both coding standards and/or based on a cohort of cases annotated with both coding standards having a defined characteristic of population of cases, each population case being annotated with one of the two coding standards;
• aggregating the mappings;
• and
• accepting input of codes from one of the two coding standards and using the aggregated mappings to extract a suitable mapping from the input codes to a code of another coding standard, from among extracted mapping candidates indicatable as most promising mapping candidates.

A non-transitory computer-readable storage medium storing a computer program which when executed on a computing device carries out a method of aligning codes between two coding standards, the method comprising:

• collecting established mappings between pairs of codes of two coding standards among coding standards, in form of theoretically established mappings between the pairs of codes of the two coding standards from an internet and from existing machine-readable publications, using text analysis techniques;
• accessing the two coding standards including descriptions accompanying each code of the pairs of codes, and finding a syntactical similarity of pairs of codes of the two coding standards using the descriptions to provide syntactical mappings, using text similarity measures;
• accessing existing cases annotated with both of the two coding standards, and finding any case-based mappings between pairs of codes of the two coding standards from the existing cases that are annotated with both coding standards, based on individual cases annotated with both coding standards and/or based on a cohort of cases annotated with both coding standards having a defined characteristic of population of cases, each population case being annotated with one of the two coding standards;
• aggregating the mappings by combining the mappings from the expert mapping module, the syntactical mapping module and the case-based mapping module;
• and
• accepting input of codes from one of the coding standards and using the aggregated mappings to extract a suitable mapping from the input codes to a code of another coding standard, from among extracted mapping candidates indicatable as most promising mapping candidates.