Natural language processing of electronic records

A system comprising:

• one or more computers and one or more storage devices on which are stored instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:
• accessing, from computer storage, electronic records for a given subject, wherein the electronic records include natural language notes about the subject;
• identifying tokens in the natural language notes;
• generating, for each token, a corresponding intensity score representing an intensity of match between the token and a particular dimension, wherein the intensity scores are each values on a first scale range, wherein each dimension is one of a plurality of dimensions of a category out of a plurality of categories;
• determining whether the intensity score corresponding with each token is greater than a threshold value;
• for the intensity score is greater than the threshold, generating rescaled-intensity scores from the intensity scores by rescaling the intensity scores from the first scale range to a second scale range different from the first scale range and discarding the tokens with intensity scores equal to or below the threshold;
• compiling, for each dimension of each category, a dimension-score based on the rescaled-intensity scores;
• and
• categorizing the subject into at least one category based on the dimension scores.

One or more non-transitory computer-readable storage media encoded with instructions that, when executed by one or more computers, cause the one or more computers to perform operations comprising:

• accessing, from computer storage, electronic records for a given subject, wherein the electronic records include natural language notes about the subject;
• identifying tokens in the natural language notes;
• generating, for each token, a corresponding intensity score representing an intensity of match between the token and a particular dimension, wherein the intensity scores are each values on a first scale range, wherein each dimension is one of a plurality of dimensions of a category out of a plurality of categories;
• determining whether the intensity score corresponding with each token is greater than a threshold value;
• for the intensity score is greater than the threshold, generating rescaled-intensity scores from the intensity scores by rescaling the intensity scores from the first scale range to a second scale range different from the first scale range and discarding the tokens with intensity scores equal to or below the threshold;
• compiling, for each dimension of each category, a dimension-score based on the rescaled-intensity scores;
• and
• categorizing the subject into at least one category based on the dimension scores.