This disclosure describes a computerized system for managing medical information, the system including at least one computing device configured to receive a plurality of medical documents, determine skip grams comprising tokens for the plurality of medical documents, wherein each of the skip grams comprises one or more tokens of at least one of the medical documents, and populate a trie data structure based on the skip grams. The at least one computing device is further configured to prune the plurality of nodes of the trie based on one or more criteria to produce a pruned trie of nodes, determine rules for associating medical billing codes with the skip grams of the pruned trie of nodes based on pointwise mutual information, and output the determined rules.