The invention relates to a method for converting a
medical record text into structured
metadata from a
natural language, which comprises the following steps of: 1, extracting characteristic value texts of specific organs, parts and surgical expressions in a text format from a historical case report, and carrying out characteristic value analysis on the characteristic value texts to obtain a characteristic dictionary; 2, exporting historical detection reports needing to be analyzed from a hospital, and merging the historical detection reports into a to-be-processed
data set; Step 3, traversingthe patient cases in the
data set, segmenting words according to the characteristic value dictionary, and intercepting the description of the organ, the part or the surgical expression; and step 4, persisting the
data content intercepted by the part into a structured
database. According to the method, historical cases are utilized, a traversal
algorithm is used, the use cost is reduced, the generation step of a
training set is omitted, lesions of different organs and parts can be conveniently counted, analyzed and searched for through the converted structured cases, and doctors can conveniently carry out
medical research, paper writing and teaching.